Authors on Topic

Albert Gu

2023–present: Assistant Professor , Carnegie Mellon University (US)

2015–2022: PhD student , Stanford University

Papers (11)

Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling — ICML 2024 Poster
Chimera: State Space Models Beyond Sequences — Accepted by TMLR
Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers — NeurIPS 2024 poster
Mamba: Linear-Time Sequence Modeling with Selective State Spaces — COLM
On the Benefits of Memory for Modeling Time-Dependent PDEs — ICLR 2025 Oral
Resurrecting Recurrent Neural Networks for Long Sequences — ICML 2023 OralPoster
Structured State Space Models for In-Context Reinforcement Learning — NeurIPS 2023 poster
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality — ICML 2024 Poster
Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models — NeurIPS 2024 poster
Understanding and Improving Length Generalization in Recurrent Models — ICML 2025 poster
Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism — ICML 2025 poster

Christopher Re

—–present: Full Professor , Stanford University (US)

—–present: Full Professor , Computer Science Department, Stanford University (US)

Papers (11)

Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHR Data — ICLR 2025 Poster
Hyena Hierarchy: Towards Larger Convolutional Language Models — ICML 2023 OralPoster
Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions — NeurIPS 2023 poster
LoLCATs: On Low-Rank Linearizing of Large Language Models — ICLR 2025 Poster
Mechanistic Design and Scaling of Hybrid Architectures — ICML 2024 Poster
Simple Hardware-Efficient Long Convolutions for Sequence Modeling — ICML 2023 Poster
Simple linear attention language models balance the recall-throughput tradeoff — ICML 2024 Spotlight
State-Free Inference of State-Space Models: The *Transfer Function* Approach — ICML 2024 Poster
The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry — ICLR 2024 poster
ThunderKittens: Simple, Fast, and $\textit{Adorable}$ Kernels — ICLR 2025 Spotlight
Towards Learning High-Precision Least Squares Algorithms with Sequence Models — ICLR 2025 Poster

Antonio Orvieto

2023–present: Principal Researcher , ELLIS Institute Tübingen, Max Planck Institute for Intelligent Systems, Tübingen AI Center, Tübingen, Germany (DE)

2018–2023: PhD student , Swiss Federal Institute of Technology (CH)

2016–2018: MS student , Swiss Federal Institute of Technology (IT)

2012–2015: Undergrad student , Universita' degli studi di Padova

Papers (7)

Fixed-Point RNNs: Interpolating from Diagonal to Dense — NeurIPS 2025 spotlight
Recurrent Distance Filtering for Graph Representation Learning — ICML 2024 Poster
Recurrent neural networks: vanishing and exploding gradients are not the end of the story — NeurIPS 2024 poster
Resurrecting Recurrent Neural Networks for Long Sequences — ICML 2023 OralPoster
Theoretical Foundations of Deep Selective State-Space Models — NeurIPS 2024 poster
Understanding the Differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks — NeurIPS 2024 poster
Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues — ICML 2024 Poster

Sepp Hochreiter

2006–present: Full Professor , Johannes Kepler University Linz (AT)

Papers (7)

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks — ICML 2025 poster
Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences — ICLR 2025 Poster
pLSTM: parallelizable Linear Source Transition Mark networks — NeurIPS 2025 poster
Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels — NeurIPS 2025 poster
TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning — NeurIPS 2025 poster
xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference — ICML 2025 poster
xLSTM: Extended Long Short-Term Memory — NeurIPS 2024 spotlight

Songlin Yang

2023–present: PhD student , Massachusetts Institute of Technology (US)

2020–2023: MS student , ShanghaiTech University (CN)

2016–2020: Undergrad student , Southern University of Science and Technology (CN)

Papers (7)

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free — NeurIPS 2025 oral
Gated Delta Networks: Improving Mamba2 with Delta Rule — ICLR 2025 Poster
Gated Linear Attention Transformers with Hardware-Efficient Training — ICML 2024 Poster
Gated Slot Attention for Efficient Linear-Time Sequence Modeling — NeurIPS 2024 poster
HGRN2: Gated Linear RNNs with State Expansion — COLM
Parallelizing Linear Transformers with the Delta Rule over Sequence Length — NeurIPS 2024 poster
Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation — NeurIPS 2025 poster

Taiji Suzuki

2024–present: Full Professor , The University of Tokyo

2017–2024: Associate Professor , The University of Tokyo

2013–2017: Associate Professor , Tokyo Institute of Technology

Papers (7)

Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency — NeurIPS 2025 poster
Mechanistic Design and Scaling of Hybrid Architectures — ICML 2024 Poster
State Space Models are Provably Comparable to Transformers in Dynamic Token Selection — ICLR 2025 Poster
State-Free Inference of State-Space Models: The *Transfer Function* Approach — ICML 2024 Poster
Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression — NeurIPS 2025 poster
Transformers are Minimax Optimal Nonparametric In-Context Learners — NeurIPS 2024 poster
Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape — ICML 2024 Oral

Tri Dao

2024–present: Assistant Professor , Princeton University (US)

2016–2023: PhD student , Stanford University

Papers (7)

Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling — ICML 2024 Poster
Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers — NeurIPS 2024 poster
Hyena Hierarchy: Towards Larger Convolutional Language Models — ICML 2023 OralPoster
Mamba: Linear-Time Sequence Modeling with Selective State Spaces — COLM
Simple Hardware-Efficient Long Convolutions for Sequence Modeling — ICML 2023 Poster
The Mamba in the Llama: Distilling and Accelerating Hybrid Models — NeurIPS 2024 poster
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality — ICML 2024 Poster

Michael Poli

2021–present: PhD student , Stanford University (US)

2018–2020: MS student , Korea Advanced Institute of Science and Technology (KR)

Papers (6)

Deep Latent State Space Models for Time-Series Generation — ICML 2023 Poster
Exploring Diffusion Transformer Designs via Grafting — NeurIPS 2025 oral
Hyena Hierarchy: Towards Larger Convolutional Language Models — ICML 2023 OralPoster
Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions — NeurIPS 2023 poster
Mechanistic Design and Scaling of Hybrid Architectures — ICML 2024 Poster
State-Free Inference of State-Space Models: The *Transfer Function* Approach — ICML 2024 Poster

Stefano Ermon

2022–present: Associate Professor , Stanford University (US)

2014–2022: Assistant Professor , Stanford University (US)

2008–2014: PhD student , Cornell University (US)

Papers (6)

Deep Latent State Space Models for Time-Series Generation — ICML 2023 Poster
Exploring Diffusion Transformer Designs via Grafting — NeurIPS 2025 oral
Hyena Hierarchy: Towards Larger Convolutional Language Models — ICML 2023 OralPoster
Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions — NeurIPS 2023 poster
Mechanistic Design and Scaling of Hybrid Architectures — ICML 2024 Poster
State-Free Inference of State-Space Models: The *Transfer Function* Approach — ICML 2024 Poster

Stefano Massaroli

2023–present: Researcher , RIKEN (JP)

2022–2024: Postdoc , MILA (CA)

2019–2022: PhD student , The University of Tokyo

2017–2019: MS student , The University of Tokyo

2015–2018: Undergrad student , Tongji University

2014–2017: Undergrad student , University of Bologna

Papers (6)

Deep Latent State Space Models for Time-Series Generation — ICML 2023 Poster
Exploring Diffusion Transformer Designs via Grafting — NeurIPS 2025 oral
Hyena Hierarchy: Towards Larger Convolutional Language Models — ICML 2023 OralPoster
Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions — NeurIPS 2023 poster
Mechanistic Design and Scaling of Hybrid Architectures — ICML 2024 Poster
State-Free Inference of State-Space Models: The *Transfer Function* Approach — ICML 2024 Poster

Daniel Y Fu

2018–2025: PhD student , Stanford University (US)

Papers (5)

Exploring Diffusion Transformer Designs via Grafting — NeurIPS 2025 oral
Hyena Hierarchy: Towards Larger Convolutional Language Models — ICML 2023 OralPoster
Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions — NeurIPS 2023 poster
Simple Hardware-Efficient Long Convolutions for Sequence Modeling — ICML 2023 Poster
ThunderKittens: Simple, Fast, and $\textit{Adorable}$ Kernels — ICLR 2025 Spotlight

Günter Klambauer

2023–present: Full Professor , Johannes Kepler Universität Linz (AT)

2017–2019: Assistant Professor , Johannes Kepler University Linz

2014–2017: Postdoc , Johannes Kepler University Linz

Papers (5)

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks — ICML 2025 poster
Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences — ICLR 2025 Poster
TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning — NeurIPS 2025 poster
xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference — ICML 2025 poster
xLSTM: Extended Long Short-Term Memory — NeurIPS 2024 spotlight

Jan Kautz

2013–present: VP Research , NVIDIA (US)

2006–2013: Full Professor , University College London, University of London (GB)

2003–2006: Postdoc , Massachusetts Institute of Technology (US)

1999–2003: PhD student , Saarland Informatics Campus, Max-Planck Institute (DE)

Papers (5)

Convolutional State Space Models for Long-Range Spatiotemporal Modeling — NeurIPS 2023 poster
Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning — NeurIPS 2025 poster
Gated Delta Networks: Improving Mamba2 with Delta Rule — ICLR 2025 Poster
Hymba: A Hybrid-head Architecture for Small Language Models — ICLR 2025 Spotlight
LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement — ICLR 2025 Poster

Korbinian Pöppel

2023–present: PhD student , Johannes Kepler Universität Linz (AT)

2023–2023: PhD student , Institute for Advanced Research in Artificial Intelligence (IARAI) (AT)

2019–2023: MS student , Department of Informatics, Technische Universität München (DE)

2016–2018: MS student , Ludwig-Maximilians-Universität München (DE)

Papers (5)

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks — ICML 2025 poster
pLSTM: parallelizable Linear Source Transition Mark networks — NeurIPS 2025 poster
Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels — NeurIPS 2025 poster
xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference — ICML 2025 poster
xLSTM: Extended Long Short-Term Memory — NeurIPS 2024 spotlight

Razvan Pascanu

2024–present: Affiliate Member , Mila - Quebec Artificial Intelligence Institute (CA)

2015–present: Research Scientist , Google DeepMind (GB)

2009–2014: PhD student , Université de Montréal (CA)

Papers (5)

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks — ICML 2025 poster
Kalman Filter for Online Classification of Non-Stationary Data — ICLR 2024 poster
MS-SSM: A Multi-Scale State Space Model for Efficient Sequence Modeling — COLM 2025
Resurrecting Recurrent Neural Networks for Long Sequences — ICML 2023 OralPoster
Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues — ICML 2024 Poster

Yiran Zhong

2025–2028: Principal Researcher , MiniMax (CN)

2022–2025: PI , Shanghai AI Lab (CN)

2021–2022: Researcher , SenseTime

2016–2021: PhD student , Australian National University

2016–2020: PhD student , CSIRO

2019–2019: PhD student , NVIDIA

Papers (5)

Elucidating the Design Space of Decay in Linear Attention — COLM 2025
HGRN2: Gated Linear RNNs with State Expansion — COLM
LASP: Linear Attention Sequence Parallelism — Accepted by TMLR
MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map — NeurIPS 2024 oral
Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention — ICML 2024 Poster

Zhen Qin

2023–present: Researcher , TapTap (CN)

2021–2023: Researcher , Sensetime (CN)

Papers (5)

Elucidating the Design Space of Decay in Linear Attention — COLM 2025
HGRN2: Gated Linear RNNs with State Expansion — COLM
LASP: Linear Attention Sequence Parallelism — Accepted by TMLR
MVA: Linear Attention with High-order Query-Keys Integration and Multi-level Vocabulary Decomposition — ICML 2025 poster
Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention — ICML 2024 Poster

Annan Yu

2021–2026: PhD student , Cornell University (US)

2017–2021: Undergrad student , Vanderbilt University (US)

Papers (4)

Block-Biased Mamba for Long-Range Sequence Processing — NeurIPS 2025 poster
HOPE for a Robust Parameterization of Long-memory State Space Models — ICLR 2025 Poster
Robustifying State-space Models for Long Sequences via Approximate Diagonalization — ICLR 2024 spotlight
Tuning Frequency Bias of State Space Models — ICLR 2025 Spotlight

Atri Rudra

2019–present: Professor , State University of New York, Buffalo (US)

2020–2021: Visting Associate Professor , Stanford University (US)

2013–2019: Associate Professor , State University of New York, Buffalo (US)

2007–2013: Assistant Professor , State University of New York, Buffalo (US)

2004–2007: PhD student , University of Washington (US)

2002–2004: PhD student , University of Texas, Austin (US)

1996–2000: Undergrad student , IIT, Kharagpur, India (IN)

Papers (4)

Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions — NeurIPS 2023 poster
Simple Hardware-Efficient Long Convolutions for Sequence Modeling — ICML 2023 Poster
Simple linear attention language models balance the recall-throughput tradeoff — ICML 2024 Spotlight
Towards Learning High-Precision Least Squares Algorithms with Sequence Models — ICLR 2025 Poster

Itamar Zimerman

2021–present: PhD student , Tel Aviv University (IL)

2022–2024: Researcher , International Business Machines (IL)

2018–2020: Undergrad student , Ben-Gurion University of the Negev (IL)

Papers (4)

A 2-Dimensional State Space Layer for Spatial Inductive Bias — ICLR 2024 poster
DeciMamba: Exploring the Length Extrapolation Potential of Mamba — ICLR 2025 Poster
Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation — ICLR 2025 Poster
Overflow Prevention Enhances Long-Context Recurrent LLMs — COLM 2025

Liliang Ren

2024–present: Senior Researcher , Microsoft GenAI

2020–2024: PhD student , University of Illinois, Urbana Champaign

2018–2020: MS student , University of California, San Diego

2014–2018: Undergrad student , Shanghai Jiao Tong University

Papers (4)

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation — NeurIPS 2025 poster
Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection — NeurIPS 2025 poster
Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling — ICLR 2025 Poster
Sparse Modular Activation for Efficient Sequence Modeling — NeurIPS 2023 poster

Lior Wolf

—–present: Associate Professor , Tel Aviv University (IL)

—–present: Professor , Tel Aviv University (IL)

2006–present: Full Professor , Tel Aviv University (IL)

Papers (4)

A 2-Dimensional State Space Layer for Spatial Inductive Bias — ICLR 2024 poster
DeciMamba: Exploring the Length Extrapolation Potential of Mamba — ICLR 2025 Poster
Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation — ICLR 2025 Poster
Overflow Prevention Enhances Long-Context Recurrent LLMs — COLM 2025

Maximilian Beck

2021–present: PhD student , Johannes Kepler University Linz

2017–2021: MS student , Karlsruhe Institute of Technology

2014–2017: Undergrad student , Karlsruhe Institute of Technology

Papers (4)

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks — ICML 2025 poster
Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels — NeurIPS 2025 poster
xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference — ICML 2025 poster
xLSTM: Extended Long Short-Term Memory — NeurIPS 2024 spotlight

Michael Zhang

2020–present: PhD student , Stanford University (US)

2023–2023: Intern , Apple (US)

2020–2021: Intern , NVIDIA (US)

2016–2020: Undergrad student , Harvard University (US)

Papers (4)

LoLCATs: On Low-Rank Linearizing of Large Language Models — ICLR 2025 Poster
Simple Hardware-Efficient Long Convolutions for Sequence Modeling — ICML 2023 Poster
Simple linear attention language models balance the recall-throughput tradeoff — ICML 2024 Spotlight
The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry — ICLR 2024 poster

N. Benjamin Erichson

2023–present: Researcher , Lawrence Berkeley National Lab (US)

2021–2022: Assistant Professor , University of Pittsburgh

2018–2021: Postdoc , University of California Berkeley

2017–2018: Postdoc , University of Washington, Seattle

Papers (4)

Block-Biased Mamba for Long-Range Sequence Processing — NeurIPS 2025 poster
HOPE for a Robust Parameterization of Long-memory State Space Models — ICLR 2025 Poster
Robustifying State-space Models for Long Sequences via Approximate Diagonalization — ICLR 2024 spotlight
Tuning Frequency Bias of State Space Models — ICLR 2025 Spotlight

Samet Oymak

2025–present: Associate Professor , University of Michigan - Ann Arbor (US)

2025–present: Researcher , Google (US)

2018–2023: Assistant Professor , University of California, Riverside (US)

2014–2015: Postdoc , University of California Berkeley (US)

2009–2015: Graduate Student , California Institute of Technology (US)

Papers (4)

Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks — ICML 2024 Poster
Fine-grained Analysis of In-context Linear Estimation: Data, Architecture, and Beyond — NeurIPS 2024 poster
Gating is Weighting: Understanding Gated Linear Attention through In-context Learning — COLM 2025
Theoretical Insights into In-context Learning with Unlabeled Data — NeurIPS 2025 poster

Simran Arora

—–present: PhD student , Stanford University

—–present: Undergrad student , University of Pennsylvania, University of Pennsylvania

—–present: Undergrad student , The Wharton School, University of Pennsylvania

Papers (4)

LoLCATs: On Low-Rank Linearizing of Large Language Models — ICLR 2025 Poster
Simple linear attention language models balance the recall-throughput tradeoff — ICML 2024 Spotlight
ThunderKittens: Simple, Fast, and $\textit{Adorable}$ Kernels — ICLR 2025 Spotlight
Towards Learning High-Precision Least Squares Algorithms with Sequence Models — ICLR 2025 Poster

Song Han

2023–present: Researcher , NVIDIA (US)

2022–present: Associate Professor , Massachusetts Institute of Technology (US)

2018–2022: Assistant Professor , Massachusetts Institute of Technology (US)

2012–2017: PhD student , Stanford University (US)

Papers (4)

Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search — NeurIPS 2025 poster
Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation — NeurIPS 2025 poster
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer — ICML 2025 poster
SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers — ICLR 2025 Oral

Weigao Sun

2022–present: Researcher , Shanghai Artificial Intelligence Laboratory (CN)

2020–2022: Researcher , Huawei Technologies Ltd. (CN)

2015–2020: PhD student , Huazhong University of Science and Technology (CN)

Papers (4)

HGRN2: Gated Linear RNNs with State Expansion — COLM
Improving Bilinear RNN with Closed-loop Control — NeurIPS 2025 spotlight
LASP: Linear Attention Sequence Parallelism — Accepted by TMLR
Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention — ICML 2024 Poster

Xuyang Shen

2024–present: Researcher , MiniMax (CN)

2023–2024: Researcher , Shanghai AI Lab (CN)

2023–2023: Researcher , Xianyuan Technology (frontis.ai) (CN)

2021–2023: Researcher , Sensetime Research (CN)

2020–2021: MS student , Australian National University (AU)

2017–2020: Undergrad student , Australian National University (AU)

Papers (4)

Elucidating the Design Space of Decay in Linear Attention — COLM 2025
HGRN2: Gated Linear RNNs with State Expansion — COLM
LASP: Linear Attention Sequence Parallelism — Accepted by TMLR
Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention — ICML 2024 Poster

Zheng Zhan

2025–present: Researcher , Microsoft (US)

Papers (4)

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation — NeurIPS 2025 poster
Exploring Token Pruning in Vision State Space Models — NeurIPS 2024 poster
Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection — NeurIPS 2025 poster
Sparse Learning for State Space Models on Mobile — ICLR 2025 Poster

Alessandro Achille

2019–2024: Applied Research Scientist , Amazon (US)

2020–2023: Postdoc , California Institute of Technology (US)

2015–2019: PhD student , , University of California, Los Angeles (US)

2018–2018: Intern , Amazon (US)

2017–2018: Intern , Google (GB)

2013–2015: MS student , Università di Pisa, University of Pisa (IT)

2010–2013: Undergrad student , Università di Pisa, University of Pisa (IT)

Papers (3)

B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory — NeurIPS 2024 poster
LC-PLM: Long-context Protein Language Modeling Using Bidirectional Mamba with Shared Projection Layers — Accepted by TMLR
PICASO: Permutation-Invariant Context Composition with State Space Models — ICLR 2025 Poster

Bailin Wang

2024–2025: Researcher , Apple (US)

2021–2024: Postdoc , Massachusetts Institute of Technology (US)

2018–2021: PhD student , University of Edinburgh

Papers (3)

Gated Linear Attention Transformers with Hardware-Efficient Training — ICML 2024 Poster
Gated Slot Attention for Efficient Linear-Time Sequence Modeling — NeurIPS 2024 poster
Parallelizing Linear Transformers with the Delta Rule over Sequence Length — NeurIPS 2024 poster

Benjamin Walker

2022–2026: PhD student , University of Oxford (GB)

2023–2024: Intern , Weierstrass Institute for Applied Analysis and Stochastics (DE)

2023–2023: Intern , City University of Hong Kong (HK)

2020–2021: MS student , University of Oxford (GB)

2016–2020: Undergrad student , University of Manchester (GB)

Papers (3)

Log Neural Controlled Differential Equations: The Lie Brackets Make A Difference — ICML 2024 Poster
Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models — NeurIPS 2025 spotlight
Theoretical Foundations of Deep Selective State-Space Models — NeurIPS 2024 poster

Carmen Amo Alonso

2024–2026: Postdoc , Computer Science Department, Stanford University (US)

2023–2024: Postdoc , ETHZ - ETH Zurich (CH)

Papers (3)

Bridging Expressivity and Scalability with Adaptive Unitary SSMs — NeurIPS 2025 poster
Lambda-Skip Connections: the architectural component that prevents Rank Collapse — ICLR 2025 Poster
Understanding the Differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks — NeurIPS 2024 poster

Dong Li

2024–present: Researcher , Minimax (CN)

2022–2024: Researcher , Shanghai AI Lab (CN)

Papers (3)

HGRN2: Gated Linear RNNs with State Expansion — COLM
LASP: Linear Attention Sequence Parallelism — Accepted by TMLR
Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention — ICML 2024 Poster

Eric Nguyen

2020–2025: PhD student , Stanford University

Papers (3)

Hyena Hierarchy: Towards Larger Convolutional Language Models — ICML 2023 OralPoster
Mechanistic Design and Scaling of Hybrid Architectures — ICML 2024 Poster
Simple Hardware-Efficient Long Convolutions for Sequence Modeling — ICML 2023 Poster

Gao Huang

2021–present: Associate Professor , Tsinghua University, Tsinghua University (CN)

2018–2021: Assistant Professor , Tsinghua University, Tsinghua University (CN)

2015–2018: Postdoc , Cornell University (US)

2009–2015: PhD student , Tsinghua University (CN)

Papers (3)

Bridging the Divide: Reconsidering Softmax and Linear Attention — NeurIPS 2024 poster
Demystify Mamba in Vision: A Linear Attention Perspective — NeurIPS 2024 poster
DyMoDreamer: World Modeling with Dynamic Modulation — NeurIPS 2025 poster

Guoqi Li

2022–present: Full Professor , Institute of automation, Chinese academy of science, Chinese Academy of Sciences (CN)

2017–2022: Associate Professor , Tsinghua University, Tsinghua University (CN)

2007–2011: PhD student , Nanyang Technological University (SG)

Papers (3)

MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map — NeurIPS 2024 oral
MVA: Linear Attention with High-order Query-Keys Integration and Multi-level Vocabulary Decomposition — ICML 2025 poster
Spike-driven Transformer — NeurIPS 2023 poster

Han Cai

2024–present: Researcher , NVIDIA (US)

2019–2024: PhD student , Massachusetts Institute of Technology (US)

2016–2019: MS student , Shanghai Jiao Tong University

2012–2016: Undergrad student , Shanghai Jiao Tong University

Papers (3)

Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search — NeurIPS 2025 poster
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer — ICML 2025 poster
SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers — ICLR 2025 Oral

Jianfeng Gao

2000–2025: Principal Researcher , Microsoft Research (US)

Papers (3)

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation — NeurIPS 2025 poster
Efficient Hybrid Long Sequence Modeling with State Space Augmented Transformers — COLM
SCBench: A KV Cache-Centric Analysis of Long-Context Methods — ICLR 2025 Poster

Jiecheng Lu

2023–present: PhD student , Georgia Institute of Technology (US)

2021–2023: MS student , Georgia Institute of Technology (US)

2016–2020: Undergrad student , Tianjin University (CN)

Papers (3)

Linear Transformers as VAR Models: Aligning Autoregressive Attention Mechanisms with Autoregressive Forecasting — ICML 2025 poster
WAVE: Weighted Autoregressive Varying Gate for Time Series Forecasting — ICML 2025 poster
ZeroS: Zero‑Sum Linear Attention for Efficient Transformers — NeurIPS 2025 spotlight

Jimmy T.H. Smith

2023–present: Researcher , Liquid AI (US)

2018–present: PhD student , Stanford University (US)

2022–2023: Intern , NVIDIA (US)

2016–2018: MS student , Massachusetts Institute of Technology (US)

2008–2013: Undergrad student , Georgia Institute of Technology (US)

Papers (3)

Convolutional State Space Models for Long-Range Spatiotemporal Modeling — NeurIPS 2023 poster
State-Free Inference of State-Space Models: The *Transfer Function* Approach — ICML 2024 Poster
Towards Scalable and Stable Parallelization of Nonlinear RNNs — NeurIPS 2024 poster

Johannes Brandstetter

2025–present: Principal Researcher , Emmi AI (AT)

2025–present: Associate Professor , Johannes Kepler Universität Linz (AT)

2024–2025: Principal Researcher , NXAI (AT)

2020–2025: Assistant Professor , Johannes Kepler University Linz (AT)

2022–2024: Researcher , Microsoft (NL)

Papers (3)

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks — ICML 2025 poster
Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences — ICLR 2025 Poster
xLSTM: Extended Long Short-Term Memory — NeurIPS 2024 spotlight

Junyu Chen

2021–present: Undergrad student , Tsinghua University, Tsinghua University (CN)

Papers (3)

Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search — NeurIPS 2025 poster
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer — ICML 2025 poster
SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers — ICLR 2025 Oral

Lei Zhang

2017–present: Chair Professor , The Hong Kong Polytechnic University (HK)

2015–2017: Full Professor , Hong Kong Polytechnic University (HK)

2010–2015: Associate Professor , Hong Kong Polytechnic University (HK)

2006–2010: Assistant Professor , Hong Kong Polytechnic University (HK)

2003–2006: Postdoc , McMaster University (CA)

2001–2003: Researcher , Hong Kong Polytechnic University (HK)

1998–2001: PhD student , Northwest Polytechnical University Xi'an (CN)

Papers (3)

Polyline Path Masked Attention for Vision Transformer — NeurIPS 2025 spotlight
Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion — ICLR 2025 Poster
Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection — NeurIPS 2024 spotlight

Luca Zancato

2021–present: Applied Scientist , Amazon Web Services (US)

2018–2021: PhD student , Universita' degli studi di Padova

Papers (3)

B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory — NeurIPS 2024 poster
LC-PLM: Long-context Protein Language Modeling Using Bidirectional Mamba with Shared Projection Layers — Accepted by TMLR
PICASO: Permutation-Invariant Context Composition with State Space Models — ICLR 2025 Poster

Man Yao

2024–present: Assistant Professor , Institute of automation, Chinese academy of sciences (CN)

2019–2023: PhD student , Xi'an Jiaotong University (CN)

Papers (3)

MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map — NeurIPS 2024 oral
MVA: Linear Attention with High-order Query-Keys Integration and Multi-level Vocabulary Decomposition — ICML 2025 poster
Spike-driven Transformer — NeurIPS 2023 poster

Michael W. Mahoney

2014–2024: Full Professor , University of California Berkeley (US)

Papers (3)

HOPE for a Robust Parameterization of Long-memory State Space Models — ICLR 2025 Poster
Robustifying State-space Models for Long Sequences via Approximate Diagonalization — ICLR 2024 spotlight
Tuning Frequency Bias of State Space Models — ICLR 2025 Spotlight

Muyang Li

2023–present: PhD student , Massachusetts Institute of Technology (US)

2021–2023: MS student , School of Computer Science, Carnegie Mellon University

2016–2020: Undergrad student , Shanghai Jiao Tong University

Papers (3)

Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation — NeurIPS 2025 poster
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer — ICML 2025 poster
SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers — ICLR 2025 Oral

Nadav Cohen

2024–present: Associate Professor , School of Computer Science, Tel Aviv University (IL)

2019–2024: Assistant Professor , School of Computer Science, Tel Aviv University (IL)

2017–2019: Postdoc , Institute for Advanced Study

2013–2017: PhD student , The Hebrew University of Jerusalem

Papers (3)

DeciMamba: Exploring the Length Extrapolation Potential of Mamba — ICLR 2025 Poster
Provable Benefits of Complex Parameterizations for Structured State Space Models — NeurIPS 2024 poster
The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels — NeurIPS 2025 spotlight

Nicola Muca Cirone

2022–2026: PhD student , Imperial College London (GB)

Papers (3)

Fixed-Point RNNs: Interpolating from Diagonal to Dense — NeurIPS 2025 spotlight
Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models — NeurIPS 2025 spotlight
Theoretical Foundations of Deep Selective State-Space Models — NeurIPS 2024 poster

Pavlo Molchanov

2015–present: Research Scientist , NVIDIA Research (US)

2010–2014: PhD student , Tampere University of Technology (FI)

Papers (3)

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning — NeurIPS 2025 poster
Hymba: A Hybrid-head Architecture for Small Language Models — ICLR 2025 Spotlight
LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement — ICLR 2025 Poster

Qianxiao Li

2019–present: Assistant Professor , National University of Singapore (SG)

2011–2016: PhD student , Princeton University (US)

Papers (3)

Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models — ICLR 2025 Poster
From Generalization Analysis to Optimization Designs for State Space Models — ICML 2024 Poster
StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization — ICML 2024 Poster

Raja Giryes

2025–present: Researcher , Apple (US)

2024–present: Full Professor , Tel Aviv University (IL)

2020–2024: Associate Professor , Tel Aviv University (IL)

2016–2020: Assistant Professor , Tel Aviv University (IL)

Papers (3)

DeciMamba: Exploring the Length Extrapolation Potential of Mamba — ICLR 2025 Poster
Overflow Prevention Enhances Long-Context Recurrent LLMs — COLM 2025
Provable Benefits of Complex Parameterizations for Structured State Space Models — NeurIPS 2024 poster

Rui-Jie Zhu

2023–present: PhD student , University of California, Santa Cruz (US)

2019–2023: Undergrad student , University of Electronic Science and Technology of China (CN)

Papers (3)

Gated Slot Attention for Efficient Linear-Time Sequence Modeling — NeurIPS 2024 poster
MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map — NeurIPS 2024 oral
ZeCO: Zero-Communication Overhead Sequence Parallelism for Linear Attention — NeurIPS 2025 poster

Scott Linderman

2019–present: Assistant Professor , Stanford University

2016–2019: Postdoc , Columbia University

2011–2016: PhD student , Harvard University

2004–2008: Undergrad student , Cornell University

Papers (3)

Convolutional State Space Models for Long-Range Spatiotemporal Modeling — NeurIPS 2023 poster
Predictability Enables Parallelization of Nonlinear State Space Models — NeurIPS 2025 poster
Towards Scalable and Stable Parallelization of Nonlinear RNNs — NeurIPS 2024 poster

Shihao Yang

2020–present: Assistant Professor , Georgia Institute of Technology (US)

Papers (3)

Linear Transformers as VAR Models: Aligning Autoregressive Attention Mechanisms with Autoregressive Forecasting — ICML 2025 poster
WAVE: Weighted Autoregressive Varying Gate for Time Series Forecasting — ICML 2025 poster
ZeroS: Zero‑Sum Linear Attention for Efficient Transformers — NeurIPS 2025 spotlight

Shuohang Wang

2019–2025: Researcher , Microsoft (US)

2014–2019: PhD student , Singapore Management University (SG)

Papers (3)

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation — NeurIPS 2025 poster
Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection — NeurIPS 2025 poster
Sparse Modular Activation for Efficient Sequence Modeling — NeurIPS 2023 poster

Stefano Soatto

2017–present: Vice President , Amazon Web Services (US)

2000–present: Professor , UCLA Computer Science Department, University of California, Los Angeles (US)

Papers (3)

B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory — NeurIPS 2024 poster
PICASO: Permutation-Invariant Context Composition with State Space Models — ICLR 2025 Poster
STree: Speculative Tree Decoding for Hybrid State Space Models — NeurIPS 2025 poster

Terry Lyons

2015–present: Full Professor , Alan Turing Institute

2000–present: Full Professor , University of Oxford

Papers (3)

Log Neural Controlled Differential Equations: The Lie Brackets Make A Difference — ICML 2024 Poster
Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models — NeurIPS 2025 spotlight
Theoretical Foundations of Deep Selective State-Space Models — NeurIPS 2024 poster

Xiu Li

2016–present: Professor , Tsinghua University (CN)

2010–2016: Associate Professor , Tsinghua University (CN)

2003–2010: Associate Professor , Tsinghua University (CN)

2002–2003: Assistant Professor , Tsinghua University (CN)

2000–2002: Postdoc , Tsinghua University (CN)

Papers (3)

Bridging the Divide: Reconsidering Softmax and Linear Attention — NeurIPS 2024 poster
MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models — NeurIPS 2024 poster
MambaTree: Tree Topology is All You Need in State Space Model — NeurIPS 2024 spotlight

Yang Liu

2020–2030: Researcher , Microsoft (US)

2016–2020: PhD student , University of Edinburgh (GB)

Papers (3)

Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection — NeurIPS 2025 poster
Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling — ICLR 2025 Poster
Sparse Modular Activation for Efficient Sequence Modeling — NeurIPS 2023 poster

Yanzhi Wang

2018–present: Associate Professor , Northeastern University (US)

Papers (3)

Exploring Token Pruning in Vision State Space Models — NeurIPS 2024 poster
Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection — NeurIPS 2025 poster
Sparse Learning for State Space Models on Mobile — ICLR 2025 Poster

yelong shen

2019–2025: Principal Researcher , Microsoft (US)

2011–2015: PhD student , Kent State University

Papers (3)

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation — NeurIPS 2025 poster
Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection — NeurIPS 2025 poster
Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling — ICLR 2025 Poster

Yingcong Li

2025–2030: Assistant Professor , New Jersey Institute of Technology (US)

2024–2025: PhD student , University of Michigan - Ann Arbor (US)

2020–2024: PhD student , University of California, Riverside (US)

2019–2020: MS student , University of California, Riverside

2015–2019: Undergrad student , University of Science and Technology of China

Papers (3)

Fine-grained Analysis of In-context Linear Estimation: Data, Architecture, and Beyond — NeurIPS 2024 poster
Gating is Weighting: Understanding Gated Linear Attention through In-context Learning — COLM 2025
Theoretical Insights into In-context Learning with Unlabeled Data — NeurIPS 2025 poster

Yingyan Celine Lin

2022–present: Associate Professor , Georgia Institute of Technology (US)

2017–2022: Assistant Professor , Rice University (US)

Papers (3)

Hymba: A Hybrid-head Architecture for Small Language Models — ICLR 2025 Spotlight
LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement — ICLR 2025 Poster
When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models — ICML 2024 Poster

Yu Qiao

2020–present: Principal Researcher , Shanghai Aritifcal Intelligence Laboratory (CN)

2016–2020: Professor , Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences (CN)

2010–2016: Researcher , Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Chinese Academy of Sciences (CN)

2006–2010: Researcher , The University of Tokyo, Tokyo Institute of Technology (JP)

2003–2006: PhD student , University of Electro-Communications, Tokyo Institute of Technology (JP)

Papers (3)

LASP: Linear Attention Sequence Parallelism — Accepted by TMLR
MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map — NeurIPS 2024 oral
Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures — ICLR 2025 Spotlight

Yujun Lin

2018–2025: PhD student , Massachusetts Institute of Technology (US)

2014–2018: Undergrad student , Tsinghua University (CN)

Papers (3)

Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation — NeurIPS 2025 poster
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer — ICML 2025 poster
SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers — ICLR 2025 Oral

Yunhe Wang

2018–present: Principal Researcher , Huawei Noah's Ark Lab (CN)

2013–2018: PhD student , Peking University (CN)

Papers (3)

DiJiang: Efficient Large Language Models through Compact Kernelization — ICML 2024 Oral
MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected Layers — NeurIPS 2024 poster
SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization — ICML 2024 Poster

Aakash Lahoti

2023–2028: PhD student , CMU, Carnegie Mellon University (US)

2022–2023: Researcher , CMU, Carnegie Mellon University

2021–2022: MS student , CMU, Carnegie Mellon University

2016–2020: Undergrad student , Indian Institute of Technology, Kanpur

Papers (2)

Chimera: State Space Models Beyond Sequences — Accepted by TMLR
Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers — NeurIPS 2024 poster

Aaryan Singhal

2022–2026: Undergrad student , Computer Science Department, Stanford University

Papers (2)

LoLCATs: On Low-Rank Linearizing of Large Language Models — ICLR 2025 Poster
ThunderKittens: Simple, Fast, and $\textit{Adorable}$ Kernels — ICLR 2025 Spotlight

Aditya Golatkar

2023–present: Researcher , Amazon (US)

2018–2023: PhD student , University of California, Los Angeles (US)

Papers (2)

B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory — NeurIPS 2024 poster
PICASO: Permutation-Invariant Context Composition with State Space Models — ICLR 2025 Poster

Alan Yuille

2016–present: Full Professor , Johns Hopkins University (US)

2002–2015: Full Professor , University of California, Los Angeles (US)

Papers (2)

Autoregressive Pretraining with Mamba in Vision — ICLR 2025 Poster
Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More — ICML 2025 poster

Alexander M Rush

2019–present: Associate Professor , Cornell University

2015–present: Assistant Professor , School of Engineering and Applied Sciences, Harvard University

Papers (2)

MambaByte: Token-free Selective State Space Model — COLM
The Mamba in the Llama: Distilling and Accelerating Hybrid Models — NeurIPS 2024 poster

Ali Behrouz

2024–present: Intern , Google (US)

2023–present: PhD student , Cornell University (US)

2020–2023: MS student , University of British Columbia (CA)

2015–2020: Undergrad student , Sharif University of Technology, Sharif University of Technology (IR)

Papers (2)

Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models — NeurIPS 2024 poster
MS-SSM: A Multi-Scale State Space Model for Efficient Sequence Modeling — COLM 2025

Aman Timalsina

2022–present: MS student , Purdue University (US)

2018–2022: Undergrad student , State University of New York at Buffalo (US)

Papers (2)

Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions — NeurIPS 2023 poster
Simple linear attention language models balance the recall-throughput tradeoff — ICML 2024 Spotlight

Ameya Sunil Mahabaleshwarkar

2023–present: Researcher , NVIDIA (US)

2021–2022: MS student , Carnegie Mellon University (US)

Papers (2)

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning — NeurIPS 2025 poster
Hymba: A Hybrid-head Architecture for Small Language Models — ICLR 2025 Spotlight

Amir Globerson

2020–present: Full Professor , Tel Aviv University (IL)

2018–present: Research Scientist , Google (US)

2016–2020: Associate Professor , Tel Aviv University (IL)

2013–2015: Associate Professor , Hebrew University

Papers (2)

DeciMamba: Exploring the Length Extrapolation Potential of Mamba — ICLR 2025 Poster
Provable Benefits of Complex Parameterizations for Structured State Space Models — NeurIPS 2024 poster

Andreas Auer

2022–present: PhD student , Johannes Kepler Universität Linz (AT)

2025–2025: Intern , NXAI (AT)

2024–2024: Intern , Amazon (DE)

2020–2022: MS student , Technische Universität Wien

2017–2020: Undergrad student , Technische Universität Wien

Papers (2)

TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning — NeurIPS 2025 poster
xLSTM: Extended Long Short-Term Memory — NeurIPS 2024 spotlight

Andrew Warrington

2024–2025: Researcher , GE HealthCare (US)

2021–2024: Postdoc , Stanford University (US)

2016–2021: PhD student , University of Oxford (GB)

2018–2020: Researcher , University of British Columbia (CA)

2012–2016: MS student , University of Oxford (GB)

Papers (2)

Deep Continuous-Time State-Space Models for Marked Event Sequences — NeurIPS 2025 spotlight
Towards Scalable and Stable Parallelization of Nonlinear RNNs — NeurIPS 2024 poster

Ankit Singh Rawat

2018–present: Research Scientist , Google (US)

2017–2018: Postdoc , University of Massachusetts, Amherst (US)

2016–2018: Postdoc , Massachusetts Institute of Technology (US)

2015–2016: Postdoc , Carnegie Mellon University (US)

2010–2015: PhD student , University of Texas, Austin (US)

Papers (2)

Fine-grained Analysis of In-context Linear Estimation: Data, Architecture, and Beyond — NeurIPS 2024 poster
Gating is Weighting: Understanding Gated Linear Attention through In-context Learning — COLM 2025

Arber Zela

2019–2025: PhD student , University of Freiburg (DE)

2015–2019: Undergrad student , Universität Freiburg (DE)

Papers (2)

DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products — NeurIPS 2025 poster
Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues — ICLR 2025 Oral

Armin W Thomas

2024–present: Researcher , Liquid AI (US)

2021–2024: Postdoc , Stanford University (US)

2015–2020: PhD student , Technische Universität Berlin

Papers (2)

Mechanistic Design and Scaling of Hybrid Architectures — ICML 2024 Poster
Simple Hardware-Efficient Long Convolutions for Sequence Modeling — ICML 2023 Poster

Assaf Ben-Kish

2024–present: Intern , Massachusetts Institute of Technology (US)

2022–present: PhD student , Tel Aviv University (IL)

2018–2022: Undergrad student , Technion - Israel Institute of Technology, Technion - Israel Institute of Technology (IL)

Papers (2)

DeciMamba: Exploring the Length Extrapolation Potential of Mamba — ICLR 2025 Poster
Overflow Prevention Enhances Long-Context Recurrent LLMs — COLM 2025

Aviv Bick

2022–2028: PhD student , Carnegie Mellon University (US)

2019–2021: MS student , Tel Aviv University

2016–2019: Undergrad student , Hebrew University of Jerusalem

Papers (2)

Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models — NeurIPS 2024 poster
Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism — ICML 2025 poster

Beidi Chen

2023–present: Assistant Professor , CMU, Carnegie Mellon University (US)

2022–present: Researcher , Facebook (US)

2020–2022: Postdoc , Stanford University (US)

2015–2020: PhD student , Rice University (US)

2011–2015: Undergrad student , University of California Berkeley (US)

Papers (2)

Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions — NeurIPS 2023 poster
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length — NeurIPS 2024 poster

Ben Bergen

2010–present: Full Professor , University of California, San Diego (US)

1996–2021: PhD student , University of California, Berkeley (US)

2001–2009: Assistant Professor , University of Hawaii System (US)

Papers (2)

Benjamin Frederick Spector

2022–2027: PhD student , Stanford University

2021–2022: MS student , Massachusetts Institute of Technology

2018–2022: Undergrad student , Massachusetts Institute of Technology

Papers (2)

LoLCATs: On Low-Rank Linearizing of Large Language Models — ICLR 2025 Poster
ThunderKittens: Simple, Fast, and $\textit{Adorable}$ Kernels — ICLR 2025 Spotlight

Bo XU

—–present: Full Professor , Institute of automation, Chinese academy of science, Chinese Academy of Sciences (CN)

Papers (2)

MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map — NeurIPS 2024 oral
Spike-driven Transformer — NeurIPS 2023 poster

Caglar Gulcehre

2025–present: Principal Researcher , Microsoft (GB)

2023–present: EPFL , EPFL - EPF Lausanne (CH)

2017–2023: Research Scientist , Deepmind (GB)

2016–2017: Intern , Maluuba

2012–2017: PhD student , University of Montreal

2016–2016: Microsoft , Microsoft

2015–2016: IBM , International Business Machines

Papers (2)

Resurrecting Recurrent Neural Networks for Long Sequences — ICML 2023 OralPoster
Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues — ICML 2024 Poster

Ce Zhang

—–present: Associate Professor , University of Chicago

Papers (2)

Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions — NeurIPS 2023 poster
Mechanistic Design and Scaling of Hybrid Architectures — ICML 2024 Poster

Chaodong Xiao

2024–present: PhD student , Hong Kong Polytechnic University (HK)

2017–2024: MS student , Xi'an Jiaotong University (CN)

2017–2021: Undergrad student , Xi'an Jiaotong University (CN)

Papers (2)

Polyline Path Masked Attention for Vision Transformer — NeurIPS 2025 spotlight
Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion — ICLR 2025 Poster

Chaofan Ma

—–present: Researcher , Shanghai Jiao Tong University (CN)

Papers (2)

MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition — ICML 2025 poster
SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation — NeurIPS 2025 poster

Chengchun Shi

2023–present: Associate Professor , London School of Economics (GB)

2019–2023: Assistant Professor , London School of Economics and Political Science, University of London (GB)

2014–2019: PhD student , North Carolina State University (US)

Papers (2)

AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees — NeurIPS 2025 poster
Balancing Interference and Correlation in Spatial Experimental Designs: A Causal Graph Cut Approach — ICML 2025 poster

Chi-Chih Chang

2024–present: PhD student , Cornell University (US)

2019–2023: Undergrad student , National Yang Ming Chiao Tung University

Papers (2)

Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models — ICML 2025 poster
Quamba: A Post-Training Quantization Recipe for Selective State Space Models — ICLR 2025 Poster

Cihang Xie

2021–present: Assistant Professor , University of California, Santa Cruz (US)

2016–2020: PhD student , Johns Hopkins University

2014–2015: MS student , University of California, Los Angeles

Papers (2)

Autoregressive Pretraining with Mamba in Vision — ICLR 2025 Poster
Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More — ICML 2025 poster

Cornelia Caragea

2022–present: Full Professor , University of Illinois at Chicago (US)

2018–2022: Associate Professor , University of Illinois at Chicago (US)

2017–2018: Associate Professor , Kansas State University

2012–2017: Assistant Professor , University of North Texas, Denton (US)

Papers (2)

Efficient Beam Tree Recursion — NeurIPS 2023 poster
Recursion in Recursion: Two-Level Nested Recursion for Length Generalization with Scalability — NeurIPS 2023 poster

Cristopher Salvi

2022–present: Assistant Professor , Imperial College London

2021–2022: Postdoc , Imperial College London

2018–2021: PhD student , University of Oxford

Papers (2)

Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models — NeurIPS 2025 spotlight
Theoretical Foundations of Deep Selective State-Space Models — NeurIPS 2024 poster

Daniel Goldstein

2024–present: Researcher , Recursal AI, Inc.

1994–1998: Undergrad student , Brown University (US)

Papers (2)

RADLADS: Rapid Attention Distillation to Linear Attention Decoders at Scale — COLM 2025
RWKV-7 "Goose" with Expressive Dynamic State Evolution — COLM 2025

David M. Zoltowski

2022–present: Postdoc , Stanford University

2017–2022: PhD student , Princeton University

Papers (2)

Modeling state-dependent communication between brain regions with switching nonlinear dynamical systems — ICLR 2024 poster
Predictability Enables Parallelization of Nonlinear State Space Models — NeurIPS 2025 poster

Deyu Meng

2017–2030: Full Professor , Xi'an Jiaotong University (CN)

Papers (2)

Polyline Path Masked Attention for Vision Transformer — NeurIPS 2025 spotlight
Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion — ICLR 2025 Poster

Diana Marculescu

2019–present: Full Professor , University of Texas, Austin (US)

2000–2019: Full Professor , Carnegie Mellon University (US)

1998–2000: Assistant Professor , University of Maryland, College Park (US)

1994–1998: PhD student , University of Southern California (US)

1993–1993: PhD student , New York University (US)

Papers (2)

Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models — ICML 2025 poster
Quamba: A Post-Training Quantization Recipe for Selective State Space Models — ICLR 2025 Poster

Dongchen Han

2023–present: PhD student , Tsinghua University, Tsinghua University (CN)

2019–2023: Undergrad student , Tsinghua University, Tsinghua University (CN)

Papers (2)

Bridging the Divide: Reconsidering Softmax and Linear Attention — NeurIPS 2024 poster
Demystify Mamba in Vision: A Linear Attention Perspective — NeurIPS 2024 poster

Dongmei Jiang

2022–present: Principal Researcher , Peng Cheng Laboratory (CN)

2010–2022: Full Professor , Northwestern Polytechnical University (CN)

Papers (2)

EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment — ICLR 2025 Poster
PolaFormer: Polarity-aware Linear Attention for Vision Transformers — ICLR 2025 Poster

Emad Barsoum

2023–present: Corprate Vice President , AMD (US)

2020–2023: Senior Director of AI , Cerebras Systems, Inc (US)

2004–2020: Group Engineering Manager , Microsoft (US)

2013–2019: PhD student , Columbia University (US)

2003–2004: MS student , University of California, Irvine

Papers (2)

QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion — NeurIPS 2024 poster
Zebra-Llama: Towards Extremely Efficient Hybrid Models — NeurIPS 2025 poster

Enze Xie

2024–present: Researcher , NVIDIA Research (US)

2022–2024: Researcher , Huawei Noah's Ark Lab (HK)

2019–2022: PhD student , The University of Hong Kong (HK)

Papers (2)

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer — ICML 2025 poster
SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers — ICLR 2025 Oral

Eric Alcaide

2024–present: PhD student , Universita della Svizzera Italiana (CH)

2021–present: Researcher , Eleuther AI (ES)

2021–2023: Researcher , CHARM Therapeutics (GB)

2018–2023: Undergrad student , University of Barcelona (ES)

Papers (2)

RADLADS: Rapid Attention Distillation to Linear Attention Decoders at Scale — COLM 2025
RWKV-7 "Goose" with Expressive Dynamic State Evolution — COLM 2025

Eric P. Xing

2021–present: Full Professor , Mohamed bin Zayed Univeristy of AI (AE)

2004–present: Full Professor , School of Computer Science, Carnegie Mellon University (US)

Papers (2)

Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models — NeurIPS 2024 poster
Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism — ICML 2025 poster

Feng Wang

2023–present: PhD student , Johns Hopkins University (US)

2022–2022: Intern , Microsoft (CN)

2019–2022: MS student , Tsinghua University, Tsinghua University (CN)

Papers (2)

Autoregressive Pretraining with Mamba in Vision — ICLR 2025 Poster
Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More — ICML 2025 poster

Frank Hutter

2024–present: Co-Founder & CEO , Prior Labs (DE)

2024–present: Principal Researcher , ELLIS Institute Tübingen (DE)

2013–present: Full Professor , Albert-Ludwigs-Universität Freiburg (DE)

Papers (2)

DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products — NeurIPS 2025 poster
Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues — ICLR 2025 Oral

Fusheng Liu

2020–2025: PhD student , national university of singaore, National University of Singapore

Papers (2)

Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models — ICLR 2025 Poster
From Generalization Analysis to Optimization Designs for State Space Models — ICML 2024 Poster

Hangyu Zheng

2024–2029: PhD student , University of Georgia

Papers (2)

Exploring Token Pruning in Vision State Space Models — NeurIPS 2024 poster
Sparse Learning for State Space Models on Mobile — ICLR 2025 Poster

Haocheng Xi

2024–present: PhD student , University of California, Berkeley (US)

2020–2024: Undergrad student , Tsinghua University, Tsinghua University (CN)

Papers (2)

Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search — NeurIPS 2025 poster
Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation — NeurIPS 2025 poster

Haotian Wang

2025–2032: Assistant Professor , National University of Defense Technology (CN)

2022–2025: Intern , Purdue University (US)

2022–2024: PhD student , National University of Defense Technology (CN)

2018–2022: Intern , Adobe Systems (US)

Papers (2)

Effective and Efficient Time-Varying Counterfactual Prediction with State-Space Models — ICLR 2025 Poster
RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing — NeurIPS 2025 poster

Heejun Lee

2024–present: PhD student , Korea Advanced Institute of Science and Technology (KR)

2020–2024: Undergrad student , Korea Advanced Institute of Science and Technology (KR)

Papers (2)

SEA: Sparse Linear Attention with Estimated Attention Mask — ICLR 2024 poster
Training Free Exponential Context Extension via Cascading KV Cache — ICLR 2025 Poster

Hermann Kumbong

2024–2028: PhD student , Stanford University (US)

2022–2024: MS student , Stanford University (US)

Papers (2)

Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions — NeurIPS 2023 poster
The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry — ICLR 2024 poster

Hongyi Zhou

2021–2026: PhD student , Tsinghua University (CN)

2017–2021: Undergrad student , Tsinghua University (CN)

Papers (2)

AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees — NeurIPS 2025 poster
Balancing Interference and Correlation in Spatial Experimental Designs: A Causal Graph Cut Approach — ICML 2025 poster

Hung-Yueh Chiang

2021–2025: PhD student , The University of Texas at Austin (US)

2016–2018: MS student , Department of computer science and informational engineering, National Taiwan University

2011–2015: Undergrad student , National Chiao Tung University, National Chiao Tung University

Papers (2)

Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models — ICML 2025 poster
Quamba: A Post-Training Quantization Recipe for Selective State Space Models — ICLR 2025 Poster

Il Memming Park

2022–present: Associate Professor , Champalimaud Centre for the Unknown (PT)

2015–2023: Associate Professor , Stony Brook University (US)

2010–2014: Postdoc , University of Texas, Austin (US)

Papers (2)

eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modeling — NeurIPS 2024 poster
Meta-Dynamical State Space Models for Integrative Neural Data Analysis — ICLR 2025 Spotlight

Jakob Nicolaus Foerster

2021–present: Associate Professor , University of Oxford, University of Oxford

2020–2021: Assistant Professor (status only) , Department of Computer Science, University of Toronto

2019–2021: Research Scientist , Facebook AI Research

2015–2019: PhD student , Department of Computer Science, University of Oxford

2017–2017: Intern , OpenAI

2017–2017: Intern , DeepMind

2016–2016: Intern , Google

Papers (2)

LOB-Bench: Benchmarking Generative AI for Finance - an Application to Limit Order Book Data — ICML 2025 poster
Structured State Space Models for In-Context Reinforcement Learning — NeurIPS 2023 poster

James A. Michaelov

2024–present: Postdoc , Massachusetts Institute of Technology (US)

2018–2024: PhD student , University of California, San Diego (US)

Papers (2)

Jan Peters

2022–present: Principal Researcher , German Research Center for AI (DE)

2011–present: Full Professor , TU Darmstadt (DE)

2011–2021: Researcher , Max Planck Institute for Intelligent Systems (DE)

2007–2010: Researcher , Max Planck Institute for Biological Cybernetics (DE)

2001–2007: PhD student , University of Southern California (US)

1996–2001: MS student , Technical University Munich (DE)

1996–2000: MS student , FernUni Hagen (DE)

Papers (2)

Cheap and Deterministic Inference for Deep State-Space Models of Interacting Dynamical Systems — Accepted by TMLR
Uncertainty Representations in State-Space Layers for Deep Reinforcement Learning under Partial Observability — Accepted by TMLR

Janna Lu

2022–2025: PhD student , George Mason University (US)

Papers (2)

RADLADS: Rapid Attention Distillation to Linear Attention Decoders at Scale — COLM 2025
RWKV-7 "Goose" with Expressive Dynamic State Evolution — COLM 2025

Jeffrey Willette

2019–present: Student , Korea Advanced Institute of Science and Technology (KR)

Papers (2)

SEA: Sparse Linear Attention with Estimated Attention Mask — ICLR 2024 poster
Training Free Exponential Context Extension via Cascading KV Cache — ICLR 2025 Poster

Jerome Sieber

2024–present: Postdoc , ETHZ - ETH Zurich (CH)

2020–2024: PhD student , ETHZ - ETH Zurich (CH)

Papers (2)

Lambda-Skip Connections: the architectural component that prevents Rank Collapse — ICLR 2025 Poster
Understanding the Differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks — NeurIPS 2024 poster

Jiangchao Yao

2022–present: Assistant Professor , Shanghai Jiaotong University (CN)

2022–present: Researcher , Shanghai Artificial Intelligence Laboratory (CN)

2019–2022: Researcher , Alibaba Group (CN)

Papers (2)

MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition — ICML 2025 poster
SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation — NeurIPS 2025 poster

Jiaxi Hu

2024–2028: PhD student , The Hong Kong University of Science and Technology (CN)

2022–2023: MS student , City University of Hong Kong

2018–2022: Undergrad student , Sichuan University

Papers (2)

Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective — NeurIPS 2024 poster
Improving Bilinear RNN with Closed-loop Control — NeurIPS 2025 spotlight

Jibin Wu

2022–present: Assistant Professor , Hong Kong Polytechnic University (HK)

2016–2020: PhD student , National University of Singapore (SG)

2013–2016: Undergrad student , National University of Singapore (SG)

Papers (2)

MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map — NeurIPS 2024 oral
ZeCO: Zero-Communication Overhead Sequence Parallelism for Linear Attention — NeurIPS 2025 poster

Jimmy Olsson

2020–present: Full Professor , KTH Royal Institute of Technology (SE)

Papers (2)

Online Variational Sequential Monte Carlo — ICML 2024 Poster
State and parameter learning with PARIS particle Gibbs — ICML 2023 Poster

Jin Zhu

2025–present: Assistant Professor , University of Birmingham (GB)

2023–2025: Postdoc , London School of Economics and Political Science, University of London (GB)

2022–2023: Intern , ByteDance (CN)

2019–2023: PhD student , SUN YAT-SEN UNIVERSITY (CN)

2016–2019: MS student , SUN YAT-SEN UNIVERSITY (CN)

2012–2016: Undergrad student , SUN YAT-SEN UNIVERSITY (CN)

Papers (2)

AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees — NeurIPS 2025 poster
Balancing Interference and Correlation in Spatial Experimental Designs: A Causal Graph Cut Approach — ICML 2025 poster

Jingdong Wang

2021–present: Chief Scientist for Computer Vision , Baidu (CN)

2007–2021: Senior Principal Researcher , Microsoft Research (CN)

2004–2007: PhD student , Department of Computer Science and Engineering, Hong Kong University of Science and Technology (HK)

2001–2004: MS student , Tsinghua University, Tsinghua University (CN)

1997–2001: Undergrad student , Tsinghua University, Tsinghua University (CN)

Papers (2)

LION: Linear Group RNN for 3D Object Detection in Point Clouds — NeurIPS 2024 poster
Mobile Attention: Mobile-Friendly Linear-Attention for Vision Transformers — ICML 2024 Poster

Jingfeng Wu

2023–present: Postdoc , University of California, Berkeley (US)

2019–2023: PhD student , Johns Hopkins University (US)

2016–2019: MS student , Peking University (CN)

2012–2016: Undergrad student , Peking University (CN)

Papers (2)

How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression? — ICLR 2024 spotlight
In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization — NeurIPS 2024 poster

Jishnu Ray Chowdhury

2024–present: Researcher , Bloomberg (US)

2019–2024: PhD student , University of Illinois, Chicago (US)

2018–2019: PhD student , Kansas State University (US)

Papers (2)

Efficient Beam Tree Recursion — NeurIPS 2023 poster
Recursion in Recursion: Two-Level Nested Recursion for Length Generalization with Scalability — NeurIPS 2023 poster

john leth

2014–present: Associate Professor , Automation & Control, Department of Electronic Systems, Aalborg University (DK)

Papers (2)

Optimal Sensor Scheduling and Selection for Continuous-Discrete Kalman Filtering with Auxiliary Dynamics — ICML 2025 poster
PAC-Bayesian Error Bound, via Rényi Divergence, for a Class of Linear Time-Invariant State-Space Models — ICML 2024 Poster

Julien Siems

2023–present: PhD student , University of Freiburg (DE)

2021–2021: Researcher , Department of Informatics, University of Zurich, University of Zurich

Papers (2)

DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products — NeurIPS 2025 poster
Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues — ICLR 2025 Oral

Juno Kim

2025–2030: PhD student , University of California, Berkeley (US)

2023–2025: MS student , University of Tokyo (JP)

2023–2025: Researcher , RIKEN (JP)

2018–2023: Undergrad student , Seoul National University (KR)

Papers (2)

Transformers are Minimax Optimal Nonparametric In-Context Learners — NeurIPS 2024 poster
Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape — ICML 2024 Oral

Junsong Chen

2025–2028: PhD student , University of Hong Kong (HK)

2024–2025: Intern , NVIDIA (CN)

2021–2024: MS student , Dalian University of Technology (CN)

Papers (2)

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer — ICML 2025 poster
SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers — ICLR 2025 Oral

Junxiong Wang

2024–2025: Researcher , TogetherAI (US)

2019–2024: PhD student , Cornell University (US)

Papers (2)

MambaByte: Token-free Selective State Space Model — COLM
The Mamba in the Llama: Distilling and Accelerating Hybrid Models — NeurIPS 2024 poster

Kai-Chiang Wu

2024–present: Full Professor , National Yang Ming Chiao Tung University (TW)

2019–2024: Associate Professor , National Yang Ming Chiao Tung University (TW)

2013–2019: Assistant Professor , National Yang Ming Chiao Tung University (TW)

2011–2013: Researcher , Intel (US)

Papers (2)

Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models — ICML 2025 poster
Quamba: A Post-Training Quantization Recipe for Selective State Space Models — ICLR 2025 Poster

Kangwook Lee

—–present: Researcher , KRAFTON (KR)

2025–present: Associate Professor , University of Wisconsin - Madison (US)

2019–2025: Assistant Professor , University of Wisconsin - Madison (US)

2016–2019: Postdoc , Korea Advanced Institute of Science and Technology

2010–2016: PhD student , University of California Berkeley

2006–2010: Undergrad student , Korea Advanced Institute of Science and Technology

Papers (2)

Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks — ICML 2024 Poster
Parameter-Efficient Fine-Tuning of State Space Models — ICML 2025 poster

Ligeng Zhu

2024–present: Researcher , NVIDIA (US)

2020–2024: PhD student , Massachusetts Institute of Technology (US)

2015–2018: Undergrad student , Simon Fraser University (CA)

2014–2018: Undergrad student , Zhejiang University (CN)

Papers (2)

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer — ICML 2025 poster
SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers — ICLR 2025 Oral

Limin Wang

2018–present: Full Professor , Nanjing University (CN)

2015–2018: Post Doc , ETH Zurich (CH)

2011–2015: Graduate Student , The Chinese University of Hong Kong (HK)

Papers (2)

Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training — ICML 2025 poster
VFIMamba: Video Frame Interpolation with State Space Models — NeurIPS 2024 poster

Liqiang Nie

2022–present: dean , Harbin Institute of Technology (Shenzhen) (CN)

2016–present: Full Professor , Shandong University (CN)

Papers (2)

Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL — NeurIPS 2024 poster
Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression — NeurIPS 2025 poster

Liyuan Liu

2022–present: Researcher , Microsoft (US)

2016–present: PhD student , University of Illinois, Urbana Champaign (US)

2020–2020: Intern , Tencent AI Lab (US)

2018–2018: Intern , Allen Institute for Artificial Intelligence (US)

2012–2016: Undergrad student , University of Science and Technology of China (CN)

Papers (2)

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation — NeurIPS 2025 poster
Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection — NeurIPS 2025 poster

Long Lan

2022–present: Associate Professor , National University of Defense Technology (CN)

2017–2022: Assistant Professor , National University of Defense Technology, (CN)

2013–2017: PhD student , National University of Defense Technology (CN)

Papers (2)

Effective and Efficient Time-Varying Counterfactual Prediction with State-Space Models — ICLR 2025 Poster
RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing — NeurIPS 2025 poster

Massimiliano Pontil

2016–present: Principal Researcher , Istituto Italiano di Tecnologia (IT)

2016–present: Principal Researcher , Università degli Studi di Genova, Istituto Italiano di Tecnologia (IT)

2003–present: Professor , University College London (GB)

2003–present: Full Professor , University College London, University of London (GB)

Papers (2)

DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products — NeurIPS 2025 poster
Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues — ICLR 2025 Oral

Matthew Dowling

2020–2026: PhD student , State University of New York, Stony Brook

Papers (2)

eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modeling — NeurIPS 2024 poster
Meta-Dynamical State Space Models for Integrative Neural Data Analysis — ICLR 2025 Spotlight

Matthew Trager

2020–present: Applied Scientist , Amazon

2018–2020: Postdoc , New York University

2014–2018: PhD student , Ecole Normale Superieure

Papers (2)

B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory — NeurIPS 2024 poster
PICASO: Permutation-Invariant Context Composition with State Space Models — ICLR 2025 Poster

Matthias Bethge

2009–present: Full Professor , University of Tuebingen (DE)

2007–2009: Assistant Professor , Max Planck Institute for Biological Cybernetics, Max-Planck Institute (DE)

2005–2006: Postdoc , Max Planck Institute for Biological Cybernetics, Max-Planck Institute (DE)

2004–2005: Postdoc , University of California, Berkeley (US)

1998–2003: PhD student , Universität Bremen (DE)

1993–1997: Undergrad student , Georg-August Universität Göttingen (DE)

Papers (2)

Identifying latent state transitions in non-linear dynamical systems — ICLR 2025 Poster
LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws — ICML 2025 poster

Melanie Zeilinger

2022–present: Associate Professor , ETHZ - ETH Zurich

2015–2022: Assistant Professor , ETHZ - ETH Zurich

Papers (2)

Lambda-Skip Connections: the architectural component that prevents Rank Collapse — ICLR 2025 Poster
Understanding the Differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks — NeurIPS 2024 poster

Mihaly Petreczky

2015–present: Researcher , CNRS

2015–present: Researcher , CNRS, University Lille, Ecole Centrale Lille,

2011–2015: Associate Professor , IMT Lille Douai

2009–2011: Assistant Professor , Maastricht University

2007–2009: Postdoc , Eindhoven University of Technology

2006–2007: Postdoc , Johns Hopkins University

2002–2006: PhD student , Centrum voor Wiskunde en Informatica

Papers (2)

Length independent generalization bounds for deep SSM architectures via Rademacher contraction and stability constraints — Accepted by TMLR
PAC-Bayesian Error Bound, via Rényi Divergence, for a Class of Linear Time-Invariant State-Space Models — ICML 2024 Poster

Ming Jin

2024–present: Assistant Professor , Griffith University (AU)

2020–2023: PhD student , Monash University (AU)

2018–2019: MS student , University of Melbourne (AU)

2013–2017: Undergrad student , Hebei University of Technology (CN)

Papers (2)

Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective — NeurIPS 2024 poster
DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs — NeurIPS 2025 poster

Naoki Nishikawa

2024–present: PhD student , Graduate School of Information Science and Technology, The University of Tokyo (JP)

2024–present: Researcher , RIKEN Center for Advanced Intelligence Project, RIKEN (JP)

2022–2024: MS student , Graduate School of Information Science and Technology, The University of Tokyo

2018–2022: Undergrad student , The University of Tokyo

Papers (2)

Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency — NeurIPS 2025 poster
State Space Models are Provably Comparable to Transformers in Dynamic Token Selection — ICLR 2025 Poster

Natalia Frumkin

2020–present: PhD student , University of Texas at Austin (US)

2016–2020: Undergrad student , Boston University

Papers (2)

Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models — ICML 2025 poster
Quamba: A Post-Training Quantization Recipe for Selective State Space Models — ICLR 2025 Poster

Peter Bartlett

—–present: Full Professor , University of California - Berkeley

—–present: — , University of California-Berkeley

2012–present: Researcher , University of California Berkeley

2003–present: Professor , University of California Berkeley

2011–2017: Professor , Queensland University of Technology

Papers (2)

How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression? — ICLR 2024 spotlight
In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization — NeurIPS 2024 poster

Phillip Lippe

2025–present: Researcher , Google DeepMind (US)

2024–2024: Researcher , NXAI (AT)

2020–2024: PhD student , University of Amsterdam (NL)

2023–2023: Intern , Microsoft

2023–2023: Intern , Google DeepMind

2018–2020: MSc student , University of Amsterdam

2018–2019: MSc student , Vrije Universiteit van Amsterdam

2015–2018: Undergrad student , Duale Hochschule Baden Württemberg (DHBW)

Papers (2)

Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels — NeurIPS 2025 poster
xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference — ICML 2025 poster

Pu Zhao

2021–present: Researcher , Northeastern University (US)

2016–2021: PhD student , Northeastern University (US)

2020–2020: Intern , Google (US)

2019–2019: Intern , IBM, International Business Machines (US)

2013–2016: MS student , Shanghai Jiaotong University (CN)

2009–2013: Undergrad student , Shanghai Jiaotong University (CN)

Papers (2)

Exploring Token Pruning in Vision State Space Models — NeurIPS 2024 poster
Sparse Learning for State Space Models on Mobile — ICLR 2025 Poster

Qingsong Wen

2023–present: Principal Researcher , Squirrel Ai Learning (US)

2017–2023: Researcher , Alibaba Group

2011–2017: PhD student , Georgia Institute of Technology

Papers (2)

Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective — NeurIPS 2024 poster
Improving Bilinear RNN with Closed-loop Control — NeurIPS 2025 spotlight

Ratish Puduppully

2024–present: Assistant Professor , IT University of Copenhagen (DK)

2022–2024: Researcher , A*STAR (SG)

2017–2021: PhD student , University of Edinburgh

Papers (2)

Chimera: State Space Models Beyond Sequences — Accepted by TMLR
Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers — NeurIPS 2024 poster

Ricardo Buitrago

2023–2025: MS student , Carnegie Mellon University (US)

2024–2024: Intern , Cartesia AI (US)

2024–2024: Researcher , Cartesia AI (US)

2016–2021: Undergrad student , Universidad Complutense de Madrid (ES)

Papers (2)

On the Benefits of Memory for Modeling Time-Dependent PDEs — ICLR 2025 Oral
Understanding and Improving Length Generalization in Recurrent Models — ICML 2025 poster

Riccardo Grazzi

2025–present: Researcher , Microsoft (GB)

2023–2025: Postdoc , Istituto Italiano di Tecnologia (IT)

2018–2023: PhD student , University College London

2018–2023: PhD student , Istituto Italiano di Tecnologia

2020–2020: Intern , Amazon Development Center Germany

2015–2017: MS student , Università degli studi di Firenze

Papers (2)

DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products — NeurIPS 2025 poster
Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues — ICLR 2025 Oral

Richard Baraniuk

2021–present: C. Sidney Burrus Professor , William Marsh Rice University

Papers (2)

PIDformer: Transformer Meets Control Theory — ICML 2024 Poster
WaLRUS: Wavelets for Long range Representation Using State Space Methods — NeurIPS 2025 poster

Roland Memisevic

2015–present: Chief Scientist , Twenty Billion Neurons (CA)

2012–present: Assistant Professor , Université de Montréal (CA)

2021–2030: Researcher , Qualcomm Inc, Qualcomm (US)

Papers (2)

Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance? — NeurIPS 2025 poster
Revisiting Bi-Linear State Transitions in Recurrent Neural Networks — NeurIPS 2025 poster

Rom Parnichkun

2022–present: PhD student , The University of Tokyo (JP)

2020–2022: MS student , Asian Institute of Technology (TH)

2016–2020: Undergrad student , Thammasat University (TH)

Papers (2)

Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions — NeurIPS 2023 poster
State-Free Inference of State-Space Models: The *Transfer Function* Approach — ICML 2024 Poster

Samuel L Smith

2018–present: Research Scientist , Google DeepMind

2016–present: Data scientist , babylon health

2017–2018: Google Brain Resident , Google

2016–2017: Data Scientist , babylon health

2012–2016: PhD student , University of Cambridge

2008–2012: Undergrad student , University of Cambridge

Papers (2)

Resurrecting Recurrent Neural Networks for Long Sequences — ICML 2023 OralPoster
Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues — ICML 2024 Poster

Sanmi Koyejo

2024–present: Researcher , Virtue AI (US)

2022–present: Assistant Professor , Stanford University (US)

2018–2024: Research Scientist , Google (US)

2021–2022: Associate Professor , University of Illinois, Urbana Champaign (US)

2016–2021: Assistant Professor , University of Illinois, Urbana Champaign (US)

2014–2016: Postdoc , Stanford University (US)

2013–2014: Postdoc , University of Texas, Austin (US)

Papers (2)

Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHR Data — ICLR 2025 Poster
Learning to (Learn at Test Time): RNNs with Expressive Hidden States — ICML 2025 spotlightposter

Sebastian Böck

2024–present: Researcher , NXAI (AT)

2020–2024: Researcher , EnliteAI

2017–2019: Postdoc , Austrian Research Institute for Artificial Intelligence (AT)

2010–2016: PhD student , Johannes Kepler Universität Linz (AT)

Papers (2)

TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning — NeurIPS 2025 poster
xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference — ICML 2025 poster

Shanghang Zhang

2022–2030: Assistant Professor , Peking University (CN)

2020–2022: Postdoc Research Fellow , University of California Berkeley

2018–2020: Researcher , Petuum Inc.

2013–2018: PhD student , Carnegie Mellon University

2013–2018: PhD student , University of Lisbon

2017–2017: Intern , Adobe Systems

Papers (2)

Orochi: Versatile Biomedical Image Processor — NeurIPS 2025 spotlight
RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation — NeurIPS 2024 poster

Shida Wang

2020–2025: PhD student , National University of Singapore (SG)

Papers (2)

StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization — ICML 2024 Poster
State-space models with layer-wise nonlinearity are universal approximators with exponential decaying memory — NeurIPS 2023 poster

Shiji Song

2006–present: Full Professor , Tsinghua University, Tsinghua University (CN)

1998–2000: Postdoc , Southeast University (CN)

1996–1998: Postdoc , Ocean University of China (CN)

1993–1996: PhD student , Harbin Institute of Technology (CN)

Papers (2)

Bridging the Divide: Reconsidering Softmax and Linear Attention — NeurIPS 2024 poster
Demystify Mamba in Vision: A Linear Attention Perspective — NeurIPS 2024 poster

Shirui Pan

2022–present: Full Professor , Griffith University (AU)

2019–2022: Assistant Professor , Monash University (AU)

2015–2018: Postdoc , University of Technology Sydney (AU)

2011–2015: PhD student , University of Technology Sydney (AU)

Papers (2)

Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective — NeurIPS 2024 poster
DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs — NeurIPS 2025 poster

Shizhe Diao

2024–present: Researcher , NVIDIA (US)

2021–2024: PhD student , Hong Kong University of Science and Technology (HK)

Papers (2)

Hymba: A Hybrid-head Architecture for Small Language Models — ICLR 2025 Spotlight
LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement — ICLR 2025 Poster

Soham De

2018–present: Research Scientist , DeepMind (GB)

2013–2018: PhD student , Department of Computer Science, University of Maryland, College Park

Papers (2)

Resurrecting Recurrent Neural Networks for Long Sequences — ICML 2023 OralPoster
Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues — ICML 2024 Poster

Souvik Kundu

2025–present: Principal Researcher , Intel (US)

2022–2025: Researcher , Intel (US)

2017–2022: PhD student , University of Southern California (US)

Papers (2)

MambaExtend: A Training-Free Approach to Improve Long Context Extension of Mamba — ICLR 2025 Poster
On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention for Long-Context LLM Serving — ICML 2025 poster

Stephan Günnemann

2016–present: Professor , Technical University Munich (DE)

2012–2015: Postdoc / Senior Researcher , Carnegie Mellon University (US)

2008–2012: PhD student , RWTH Aachen University (DE)

Papers (2)

Efficient Time Series Processing for Transformers and State-Space Models through Token Merging — ICML 2025 poster
UnHiPPO: Uncertainty-aware Initialization for State Space Models — ICML 2025 poster

Sung Ju Hwang

2020–present: Associate Professor , Korea Advanced Institute of Science and Technology (KR)

2016–present: Co-founder , AITRICS (KR)

2017–2019: Assistant Professor , Korea Advanced Institute of Science and Technology (KR)

2014–2017: Assistant Professor , UNIST (KR)

2013–2014: Postdoc , Disney Research, Disney (US)

2008–2013: PhD student , University of Texas, Austin (US)

Papers (2)

SEA: Sparse Linear Attention with Estimated Attention Mask — ICLR 2024 poster
Training Free Exponential Context Extension via Cascading KV Cache — ICLR 2025 Poster

Sylvain Le Corff

2022–present: Full Professor , Sorbonne Université, LPSM (FR)

2018–2022: Full Professor , Telecom SudParis (FR)

2013–2018: Associate Professor , CNRS, UPSud, University Paris-Saclay (FR)

Papers (2)

State and parameter learning with PARIS particle Gibbs — ICML 2023 Poster
Variational excess risk bound for general state space models — Accepted by TMLR

Tan Minh Nguyen

2023–present: Assistant Professor , National University of Singapore (SG)

2020–2023: Postdoc , University of California, Los Angeles (US)

2014–2020: Ph.D. student , Rice University (US)

2011–2014: Undergrad student , Rice University (US)

Papers (2)

Demystifying the Token Dynamics of Deep Selective State Space Models — ICLR 2025 Spotlight
PIDformer: Transformer Meets Control Theory — ICML 2024 Poster

Tanya Marwah

2025–2026: Postdoc , Flatiron Institute (US)

2019–2025: PhD student , Carnegie Mellon University (US)

2017–2019: Graduate Student , Carnegie Mellon University (US)

Papers (2)

Chimera: State Space Models Beyond Sequences — Accepted by TMLR
On the Benefits of Memory for Modeling Time-Dependent PDEs — ICLR 2025 Oral

Taylor Berg-Kirkpatrick

2022–present: Associate Professor , University of California, San Diego

2018–2022: Assistant Professor , University of California, San Diego

2016–2018: Assistant Professor , Carnegie Mellon University

2010–2016: PhD student , University of California Berkeley

Papers (2)

Is attention required for ICL? Exploring the Relationship Between Model Architecture and In-Context Learning Ability — ICLR 2024 poster
Single-Pass Document Scanning for Question Answering — COLM 2025

Thomas Hofmann

2014–present: Full Professor , Swiss Federal Institute of Technology (CH)

Papers (2)

Recurrent Distance Filtering for Graph Representation Learning — ICML 2024 Poster
Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models — NeurIPS 2025 spotlight

Thomas Schmied

2022–present: PhD student , Johannes Kepler Universität Linz (AT)

2024–2025: Intern , Google (GB)

2019–2021: MS student , Technische Universität Wien

Papers (2)

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks — ICML 2025 poster
pLSTM: parallelizable Linear Source Transition Mark networks — NeurIPS 2025 poster

Tianzhu Zhang

2019–present: Full Professor , University of Science and Technology of China (CN)

2014–2018: Associate Professor , CASIA (CN)

Papers (2)

BeyondMix: Leveraging Structural Priors and Long-Range Dependencies for Domain-Invariant LiDAR Segmentation — NeurIPS 2025 poster
State Space Model Meets Transformer: A New Paradigm for 3D Object Detection — ICLR 2025 Poster

Volkan Cevher

2023–present: Associate Professor , EPFL - EPF Lausanne (CH)

2022–present: Amazon Scholar , Amazon Development Center Germany (DE)

2016–2022: Associate Professor , Swiss Institute of Technology (CH)

2010–2016: Assistant Professor , EPFL - EPF Lausanne (CH)

2008–2010: Postdoc , Rice University (US)

2006–2008: postdoc , University of Maryland, College Park (US)

Papers (2)

Linear Attention for Efficient Bidirectional Sequence Modeling — NeurIPS 2025 poster
On Feature Learning in Structured State Space Models — NeurIPS 2024 poster

Wei Niu

2023–present: Assistant Professor , University of Georgia (US)

2018–2023: PhD student , College of William and Mary (US)

Papers (2)

Exploring Token Pruning in Vision State Space Models — NeurIPS 2024 poster
Sparse Learning for State Space Models on Mobile — ICLR 2025 Poster

Weixuan Sun

2023–2026: Researcher , Tencent (CN)

2019–2023: PhD student , Australian National University (AU)

2013–2017: Undergrad student , Australian National University

2013–2017: Undergrad student , Beijing Institute of Technology

Papers (2)

HGRN2: Gated Linear RNNs with State Expansion — COLM
Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention — ICML 2024 Poster

Weizhu Chen

2005–present: Vice President , Microsoft GenAI (US)

Papers (2)

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation — NeurIPS 2025 poster
Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling — ICLR 2025 Poster

Wenjing Yang

2014–2025: Associate Professor , National University of Defense Technology (CN)

2010–2014: PhD student , University of Manchester (GB)

Papers (2)

Effective and Efficient Time-Varying Counterfactual Prediction with State-Space Models — ICLR 2025 Poster
RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing — NeurIPS 2025 poster

Wieland Brendel

2023–present: Principal Researcher , ELLIS Institute Tübingen (DE)

2022–2023: Principal Researcher , Max-Planck-Institute for Intelligent Systems, Max-Planck Institute (DE)

2021–2022: Group Leader , University of Tuebingen

2018–2021: Principal Researcher , University of Tuebingen

2014–2018: Postdoc , University of Tuebingen

Papers (2)

LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws — ICML 2025 poster
Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD Prompts — NeurIPS 2024 spotlight

William Merrill

2026–present: Assistant Professor , Toyota Technological Institute at Chicago (US)

2025–2026: Postdoc , Allen Institute for Artificial Intelligence (US)

2021–2025: Graduate student , New York University (US)

2019–2021: Researcher , Allen Institute for Artificial Intelligence (US)

2015–2019: Undergrad student , Yale University (US)

Papers (2)

RWKV-7 "Goose" with Expressive Dynamic State Evolution — COLM 2025
The Illusion of State in State-Space Models — ICML 2024 Poster

Wonjun Kang

2022–present: PhD student , Seoul National University (KR)

2021–present: Researcher , Furiosa AI (KR)

2020–2022: MS student , Seoul National University (KR)

2014–2020: Undergrad student , Seoul National University (KR)

Papers (2)

Parameter-Efficient Fine-Tuning of State Space Models — ICML 2025 poster
TabFlex: Scaling Tabular Learning to Millions with Linear Attention — ICML 2025 spotlightposter

Wonmin Byeon

2018–present: Researcher , NVIDIA (US)

2016–2017: Postdoc , ETHZ - ETH Zurich (CH)

2015–2017: Postdoc , IDSIA (CH)

2010–2015: PhD student , Universität Kaiserslautern (DE)

2008–2010: MS student , Gwangju Institute of Science and Technology (KR)

Papers (2)

Convolutional State Space Models for Long-Range Spatiotemporal Modeling — NeurIPS 2023 poster
Hymba: A Hybrid-head Architecture for Small Language Models — ICLR 2025 Spotlight

Xavier Gonzalez

2020–2026: PhD student , Stanford University (US)

2018–2020: MS student , University of Oxford

2014–2018: Undergrad student , Harvard University

Papers (2)

Predictability Enables Parallelization of Nonlinear State Space Models — NeurIPS 2025 poster
Towards Scalable and Stable Parallelization of Nonlinear RNNs — NeurIPS 2024 poster

Xiang Bai

2018–2025: Full Professor , Huazhong University of Science and Technology (CN)

2014–2017: Full Professor , Huazhong University of Science and Technolgy

2010–2014: Associate Professor , Huazhong University of Science and Technology (CN)

2005–2009: PhD student , University of California, Los Angeles (CN)

Papers (2)

LION: Linear Group RNN for 3D Object Detection in Point Clouds — NeurIPS 2024 poster
PointMamba: A Simple State Space Model for Point Cloud Analysis — NeurIPS 2024 poster

Xiaoqing Ye

2019–present: Researcher and Developer , Baidu Inc. (CN)

2014–2019: PhD student , Chinese Academy of Sciences

2010–2014: Undergrad student , Wuhan University

Papers (2)

LION: Linear Group RNN for 3D Object Detection in Point Clouds — NeurIPS 2024 poster
PointMamba: A Simple State Space Model for Point Cloud Analysis — NeurIPS 2024 poster

Xin Dong

2024–present: Researcher , NVIDIA (US)

2023–2024: Researcher , Sony Research (US)

2018–2023: PhD student , Harvard University (US)

Papers (2)

Hymba: A Hybrid-head Architecture for Small Language Models — ICLR 2025 Spotlight
LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement — ICLR 2025 Poster

Xinchao Wang

2021–present: Assistant Professor , National University of Singapore (SG)

2017–2021: Assistant Professor , Stevens Institute of Technology (US)

2016–2017: Post Doc , University of Illinois, Urbana Champaign (US)

2010–2015: Graduate Student , Swiss Federal Institute of Technology Lausanne (CH)

Papers (2)

CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up — NeurIPS 2025 poster
MVGamba: Unify 3D Content Generation as State Space Sequence Modeling — NeurIPS 2024 poster

Xinghao Chen

2019–present: Researcher , Huawei Noah's Ark Lab (CN)

2013–2019: PhD student , Tsinghua University (CN)

Papers (2)

SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization — ICML 2024 Poster
TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-state — ICML 2025 poster

Xu Han

2023–2025: Researcher , Amazon Web Services (CN)

2021–2023: MS student , Georgia Institute of Technology

2016–2020: Undergrad student , Hong Kong University of Science and Technology

Papers (2)

WAVE: Weighted Autoregressive Varying Gate for Time Series Forecasting — ICML 2025 poster
ZeroS: Zero‑Sum Linear Attention for Efficient Transformers — NeurIPS 2025 spotlight

Xuan Shen

2025–present: Postdoc , Cornell University (US)

2020–2025: Phd , Northeastern University (US)

Papers (2)

Exploring Token Pruning in Vision State Space Models — NeurIPS 2024 poster
Sparse Learning for State Space Models on Mobile — ICLR 2025 Poster

Ya Zhang

2010–present: Professor , Shanghai Jiao Tong University (CN)

Papers (2)

MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition — ICML 2025 poster
SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation — NeurIPS 2025 poster

Yan Sun

2021–2024: PhD student , Georgia Institute of Technology

2019–2021: MS student , Georgia Institute of Technology

2015–2019: Undergrad student , Tsinghua University, Tsinghua University

Papers (2)

WAVE: Weighted Autoregressive Varying Gate for Time Series Forecasting — ICML 2025 poster
ZeroS: Zero‑Sum Linear Attention for Efficient Transformers — NeurIPS 2025 spotlight

Yanfeng Wang

2018–present: Full Professor , Shanghai Jiao Tong University (CN)

2013–2017: Associate Professor , Shanghai Jiao Tong University (CN)

2005–2009: PhD student , Shanghai Jiao Tong University (CN)

Papers (2)

MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition — ICML 2025 poster
SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation — NeurIPS 2025 poster

Yaowei Wang

2024–present: Full Professor , Harbin Institute of Technology, Shenzhen (CN)

2019–present: Full Professor , Pengcheng Laboratory (CN)

Papers (2)

EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment — ICLR 2025 Poster
VMamba: Visual State Space Model — NeurIPS 2024 spotlight

Yehui Tang

2023–present: Researcher , Huawei Technologies Ltd. (CN)

2018–2023: PhD student , Peking University (CN)

Papers (2)

MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected Layers — NeurIPS 2024 poster
SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization — ICML 2024 Poster

Yifan Gong

2024–present: Researcher , Adobe Systems (US)

2019–2024: PhD student , Northeastern University (US)

2017–2019: MS student , University of Toronto (CA)

2013–2017: Undergrad student , Xidian University (CN)

Papers (2)

Exploring Token Pruning in Vision State Space Models — NeurIPS 2024 poster
Sparse Learning for State Space Models on Mobile — ICLR 2025 Poster

Yifan Pu

2023–2026: PhD student , Tsinghua University, Tsinghua University (CN)

2020–2023: MS student , Tsinghua University, Tsinghua University

Papers (2)

Bridging the Divide: Reconsidering Softmax and Linear Attention — NeurIPS 2024 poster
Demystify Mamba in Vision: A Linear Attention Perspective — NeurIPS 2024 poster

Yikang Shen

2025–present: Researcher , xAI (US)

2022–2025: Researcher , International Business Machines (US)

2016–2021: PhD student , University of Montreal (CA)

2013–2016: MS student , Beihang University

2009–2013: Undergrad student , Beihang University

Papers (2)

Gated Linear Attention Transformers with Hardware-Efficient Training — ICML 2024 Poster
Parallelizing Linear Transformers with the Delta Rule over Sequence Length — NeurIPS 2024 poster

Yizeng Han

2024–present: Researcher , Alibaba Group (CN)

2018–2024: PhD student , Tsinghua University, Tsinghua University (CN)

2014–2018: Undergrad student , Tsinghua University, Tsinghua University

Papers (2)

Bridging the Divide: Reconsidering Softmax and Linear Attention — NeurIPS 2024 poster
Demystify Mamba in Vision: A Linear Attention Perspective — NeurIPS 2024 poster

Yonggan Fu

2025–present: Researcher , NVIDIA (US)

2023–2025: PhD student , Georgia Institute of Technology (US)

2019–2023: PhD student , Rice University (US)

2015–2019: Undergrad student , University of Science and Technology of China (CN)

Papers (2)

Hymba: A Hybrid-head Architecture for Small Language Models — ICLR 2025 Spotlight
LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement — ICLR 2025 Poster

Yoon Kim

2021–present: Assistant Professor , Massachusetts Institute of Technology (US)

2020–2021: Research scientist , International Business Machines (US)

2015–2020: PhD student , Harvard University (US)

Papers (2)

Gated Linear Attention Transformers with Hardware-Efficient Training — ICML 2024 Poster
Parallelizing Linear Transformers with the Delta Rule over Sequence Length — NeurIPS 2024 poster

Yoshi Suhara

2023–present: Researcher , NVIDIA (US)

2022–2023: Researcher , Grammarly

2017–2022: Researcher , Megagon Labs

2014–2017: Researcher , Massachusetts Institute of Technology

2008–2014: Researcher , NTT

Papers (2)

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning — NeurIPS 2025 poster
Hymba: A Hybrid-head Architecture for Small Language Models — ICLR 2025 Spotlight

Yoshua Bengio

1993–present: Full Professor , University of Montreal (CA)

Papers (2)

Hyena Hierarchy: Towards Larger Convolutional Language Models — ICML 2023 OralPoster
Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions — NeurIPS 2023 poster

Yu Zhang

2021–present: PhD student , Soochow University, China (CN)

2018–2021: MS student , Soochow University, China (CN)

2014–2018: Undergrad student , Soochow University, China (CN)

Papers (2)

Gated Slot Attention for Efficient Linear-Time Sequence Modeling — NeurIPS 2024 poster
Parallelizing Linear Transformers with the Delta Rule over Sequence Length — NeurIPS 2024 poster

Yuchen Zeng

2025–present: Researcher , Microsoft (US)

2024–2025: Intern , Meta (US)

2020–2025: PhD student , University of Wisconsin, Madison (US)

2024–2024: Intern , Microsoft (US)

2022–2022: Intern , MIT-IBM Watson AI Lab (US)

2018–2020: MS student , University of Wisconsin, Madison (US)

2015–2019: Undergrad student , Nankai University (CN)

Papers (2)

Parameter-Efficient Fine-Tuning of State Space Models — ICML 2025 poster
TabFlex: Scaling Tabular Learning to Millions with Linear Attention — ICML 2025 spotlightposter

Yuhong Chou

2024–2028: PhD student , The Hong Kong Polytechnic University (HK)

Papers (2)

MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map — NeurIPS 2024 oral
ZeCO: Zero-Communication Overhead Sequence Parallelism for Linear Attention — NeurIPS 2025 poster

Yuhuan Yang

2021–2026: PhD student , Shanghai Jiao Tong University (CN)

Papers (2)

MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition — ICML 2025 poster
SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation — NeurIPS 2025 poster

Yushu Wu

2021–present: PhD student , Northeastern University (US)

Papers (2)

Exploring Token Pruning in Vision State Space Models — NeurIPS 2024 poster
Sparse Learning for State Space Models on Mobile — ICLR 2025 Poster

Yuxuan Liang

2023–present: Assistant Professor , The Hong Kong University of Science and Technology (Guangzhou) (CN)

2019–2022: PhD student , National University of Singapore (SG)

2021–2021: Intern , Sea AI Lab

2018–2018: Intern , JD.com

2015–2018: Intern , Microsoft (CN)

Papers (2)

Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective — NeurIPS 2024 poster
Improving Bilinear RNN with Closed-loop Control — NeurIPS 2025 spotlight

Zhangyang Wang

2023–present: Associate Professor , University of Texas at Austin (US)

2020–2023: Assistant Professor , University of Texas, Austin (US)

2017–2020: Assistant Professor , Texas A&M University (US)

Papers (2)

On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention for Long-Context LLM Serving — ICML 2025 poster
Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing — ICLR 2025 Poster

Zhekai Zhang

2020–present: PhD student , Massachusetts Institute of Technology (US)

2015–2020: Undergrad student , Shanghai Jiao Tong University (CN)

Papers (2)

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer — ICML 2025 poster
SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers — ICLR 2025 Oral

Zheng-Hua Tan

2017–present: Full Professor , Aalborg University (DK)

1997–1999: PhD student , Shanghai Jiaotong University (CN)

Papers (2)

Optimal Sensor Scheduling and Selection for Continuous-Discrete Kalman Filtering with Auxiliary Dynamics — ICML 2025 poster
PAC-Bayesian Error Bound, via Rényi Divergence, for a Class of Linear Time-Invariant State-Space Models — ICML 2024 Poster

Zhenglun Kong

2024–present: Postdoc , Harvard Medical School, Harvard University (US)

2019–2024: PhD student , Northeastern University (US)

2017–2019: MS student , Northeastern University (US)

2013–2017: Undergrad student , Huazhong University of Science and Technology, Tsinghua University (CN)

Papers (2)

Exploring Token Pruning in Vision State Space Models — NeurIPS 2024 poster
Sparse Learning for State Space Models on Mobile — ICLR 2025 Poster

Zhenjie Mao

2024–2027: MS student , Shanghai Jiaotong University (CN)

2020–2024: Undergrad student , Shanghai Jiaotong University (CN)

Papers (2)

MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition — ICML 2025 poster
SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation — NeurIPS 2025 poster

Zhuofan Xia

2020–2026: PhD student , Tsinghua University, Tsinghua University (CN)

2016–2020: Undergrad student , Tsinghua University, Tsinghua University (CN)

Papers (2)

Bridging the Divide: Reconsidering Softmax and Linear Attention — NeurIPS 2024 poster
Demystify Mamba in Vision: A Linear Attention Perspective — NeurIPS 2024 poster

ZIJIA CHEN

2024–present: Researcher , NVIDIA (US)

2019–2023: Software Engineer , PingAn Technology

2017–2019: MS student , University of California, San Diego

2013–2017: Undergrad student , Nanjing University

Papers (2)

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning — NeurIPS 2025 poster
Hymba: A Hybrid-head Architecture for Small Language Models — ICLR 2025 Spotlight

Aaditya K Singh

2021–2025: PhD student , University College London, University of London (GB)

2023–2023: Intern , Facebook (US)

2021–2022: Intern , Google (GB)

2020–2021: MS student , Massachusetts Institute of Technology (US)

2017–2021: Undergrad student , Massachusetts Institute of Technology

Papers (1)

Training Dynamics of In-Context Learning in Linear Attention — ICML 2025 spotlightposter

Aaron Courville

2012–present: Assistant Professor , University of Montreal

2012–present: Assistant Professor , Université de Montréal

Papers (1)

Forgetting Transformer: Softmax Attention with a Forget Gate — ICLR 2025 Poster

Aaron Gokaslan

2021–present: PhD student , Cornell University (US)

2018–2019: MS student , Brown University

2014–2018: Undergrad student , Brown University

Papers (1)

Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling — ICML 2024 Poster

Abbas Rahimi

2020–present: Principal Researcher , IBM Research - Zurich (CH)

2017–2019: Postdoc , ETHZ - ETH Zurich

2015–2017: Postdoc , Electrical Engineering & Computer Science Department, University of California, Berkeley

2010–2015: PhD student , UC San Diego, University of California, San Diego

Papers (1)

Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models — NeurIPS 2025 spotlight

Abdul Fatir Ansari

2024–present: Senior Scientist , AWS AI Labs (Amazon) (DE)

2022–2024: Scientist , AWS AI Labs (Amazon) (DE)

2017–2022: PhD student , National University of Singapore (SG)

2020–2021: Intern , Amazon (SG)

Papers (1)

Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series — ICML 2023 OralPoster

Abdullah Saydemir

2022–2025: MS student , Technische Universität München (DE)

2017–2022: Undergrad student , Ozyegin University (TR)

Papers (1)

UnHiPPO: Uncertainty-aware Initialization for State Space Models — ICML 2025 poster

Abhinav Gupta

2023–present: Principal Researcher , SKILD AI (US)

2015–present: Full Professor , Carnegie Mellon University (US)

2018–2022: Researcher , Facebook (US)

Papers (1)

Hierarchical State Space Models for Continuous Sequence-to-Sequence Modeling — ICML 2024 Poster

Abhinav Moudgil

2021–present: PhD student , Concordia University (CA)

2021–present: PhD student , Mila (CA)

2020–2021: Researcher , Georgia Institute of Technology (US)

Papers (1)

Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall Capacity — ICML 2025 poster

Abhronil Sengupta

2018–present: Associate Professor , Pennsylvania State University (US)

Papers (1)

P-SPIKESSM: HARNESSING PROBABILISTIC SPIKING STATE SPACE MODELS FOR LONG-RANGE DEPENDENCY TASKS — ICLR 2025 Poster

Achal Dave

2024–present: Researcher , Anthropic (US)

2023–2024: Researcher , Toyota Research Institute (US)

2021–2023: Researcher , Amazon

2015–2021: PhD student , Carnegie Mellon University

2011–2015: Undergrad student , University of California Berkeley

Papers (1)

Linearizing Large Language Models — COLM

Adam Atkinson

2020–2025: Senior Applied Scientist , Research, Microsoft (CA)

2017–2019: Software Developer , Research, Microsoft (CA)

Papers (1)

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation — NeurIPS 2025 poster

Adam Dankowiakowski

2024–2025: MS student , University of Oxford (GB)

2021–2024: Undergrad student , University of Oxford (GB)

Papers (1)

Metric Automata Theory: A Unifying Theory of RNNs — NeurIPS 2025 poster

Adam Shabti Charles

2020–present: Assistant Professor , Johns Hopkins University

2015–2020: Postdoc , Princeton University

Papers (1)

Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics — NeurIPS 2024 poster

Adel Bibi

2023–present: Senior Researcher , University of Oxford (GB)

2022–2023: Senior Research Associate , University of Oxford (GB)

2020–2022: Postdoc , University of Oxford (GB)

2016–2020: PhD student , KAUST

2018–2018: PhD Intern , Intel

Papers (1)

Universal In-Context Approximation By Prompting Fully Recurrent Models — NeurIPS 2024 poster

Aditya Akella

2024–present: Researcher , Facebook (US)

2021–present: Full Professor , University of Texas at Austin (US)

2021–2024: software engineer , Google (US)

2006–2021: Full Professor , University of Wisconsin - Madison (US)

2000–2005: PhD student , Carnegie Mellon University (US)

Papers (1)

On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention for Long-Context LLM Serving — ICML 2025 poster

Adji Bousso Dieng

2021–2025: Assistant Professor , Princeton University (US)

2014–2020: PhD student , Columbia University (US)

2012–2013: MS student , Cornell University (US)

Papers (1)

Alternators For Sequence Modeling — Accepted by TMLR

Adrian Weller

2018–present: Principal Researcher , Alan Turing Institute (GB)

2015–present: Principal Researcher , University of Cambridge (GB)

Papers (1)

Linear Transformer Topological Masking with Graph Random Features — ICLR 2025 Poster

Adrien Gaidon

2024–present: Partner , Calibrate Ventures (US)

2021–present: Adjunct Professor , Stanford University (US)

2017–2023: Head of ML , Toyota Research Institute (TRI) (US)

2013–2016: Research Scientist , Xerox Research Centre Europe, Xerox (FR)

2008–2012: Doctoral Researcher , Inria (FR)

Papers (1)

Linearizing Large Language Models — COLM

Agrim Gupta

2019–2024: PhD student , Stanford University (US)

2022–2022: Intern , DeepMind

2017–2019: Research Engineer , Facebook

Papers (1)

Exploring Diffusion Transformer Designs via Grafting — NeurIPS 2025 oral

Ajmal Saeed Mian

2018–present: Professor , University of Western Australia (AU)

2016–2018: Associate Professor , University of Western Australia (AU)

2012–2016: Assistant Professor , University of Western Australia (AU)

2008–2012: Postdoc , University of Western Australia (AU)

Papers (1)

CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation — NeurIPS 2025 poster

Alan Arazi

2024–present: PhD student , Technion - Israel Institute of Technology, Technion (IL)

2021–present: Researcher , AI21 Labs (IL)

2014–2018: MS student , Tel Aviv University (IL)

2010–2013: Undergrad student , Tel Aviv University (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Alan Wu

2023–2025: Undergrad student , California Institute of Technology (US)

2021–2023: Undergrad student , Harvey Mudd College (US)

Papers (1)

LoLCATs: On Low-Rank Linearizing of Large Language Models — ICLR 2025 Poster

Alana Deng

2025–2029: PhD student , Simon Fraser University (CA)

2023–2025: MS student , University of Western Ontario (CA)

2019–2023: Undergrad student , Jinan University (CN)

Papers (1)

Structure-Aware Fusion with Progressive Injection for Multimodal Molecular Representation Learning — NeurIPS 2025 poster

Alasdair Paren

2025–2027: Postdoc , Chalmers University of Technology (SE)

2022–2025: Postdoc , University of Oxford (GB)

2017–2022: PhD student , University of Oxford (GB)

2016–2017: MS student , University College London (GB)

2010–2014: MS student , Imperial College London (SE)

Papers (1)

Universal In-Context Approximation By Prompting Fully Recurrent Models — NeurIPS 2024 poster

Alberto Bietti

2023–present: Researcher , Flatiron Institute (US)

2022–2023: Researcher , Meta

2020–2022: Postdoc , New York University

2020–2020: Postdoc , INRIA

2016–2019: PhD student , INRIA

2017–2017: Research Intern , Microsoft

Papers (1)

Understanding Factual Recall in Transformers via Associative Memories — ICLR 2025 Spotlight

Aleksandar Petrov

2025–present: Researcher , Google DeepMind (GB)

2025–2025: Intern , Meta (GB)

2024–2025: Intern , Google DeepMind (US)

2021–2025: PhD student , University of Oxford (GB)

2024–2024: Intern , Adobe Systems (US)

2018–2020: MS student , ETHZ - ETH Zurich (CH)

2014–2018: Undergrad student , Delft University of Technology (NL)

Papers (1)

Universal In-Context Approximation By Prompting Fully Recurrent Models — NeurIPS 2024 poster

Aleksandar Terzic

2023–present: PhD student , International Business Machines (CH)

2021–2023: MS student , ETHZ - ETH Zurich (CH)

2017–2021: Undergrad student , ETHZ - ETH Zurich (CH)

Papers (1)

Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models — NeurIPS 2025 spotlight

Alena Brändle

2022–present: PhD student , Ruprecht-Karls-Universität Heidelberg (DE)

2019–2022: MS student , Ruprecht-Karls-Universität Heidelberg (DE)

2015–2019: Undergrad student , Friedrich-Alexander Universität Erlangen-Nürnberg (DE)

2017–2018: Undergrad student , Lund University (SE)

Papers (1)

A scalable generative model for dynamical system reconstruction from neuroimaging data — NeurIPS 2024 poster

Alessandro Giacomo Bottero

2021–present: PhD student , Technische Universität Darmstadt

2021–present: PhD student , Bosch Center for Artificial Intelligence

2014–2017: MS student , Ludwig-Maximilians-Universität München

2014–2017: MS student , Technische Universität München

2011–2014: Undergrad student , University of Pavia

Papers (1)

Uncertainty Representations in State-Space Layers for Deep Reinforcement Learning under Partial Observability — Accepted by TMLR

Alessandro Mastrototaro

2024–present: Instructor , KTH Royal Institute of Technology (SE)

2019–2024: PhD student , KTH Royal Institute of Technology

2016–2018: MS student , Polytechnic Institute of Turin

2013–2016: Undergrad student , Polytechnic Institute of Turin

Papers (1)

Online Variational Sequential Monte Carlo — ICML 2024 Poster

Alessandro Moro

2012–2025: Visiting Researcher , The University of Tokyo, Tokyo Institute of Technology (JP)

2012–2025: Visiting Rsearcher , Chuo University (JP)

2011–2012: Postdoc , Chuo University (JP)

Papers (1)

State-Free Inference of State-Space Models: The *Transfer Function* Approach — ICML 2024 Poster

Alessandro Ronca

2023–present: Research Associate , University of Oxford (GB)

2019–2023: Research Associate , Sapienza University of Rome (IT)

2015–2020: PhD student , University of Oxford (GB)

Papers (1)

Metric Automata Theory: A Unifying Theory of RNNs — NeurIPS 2025 poster

Alessio Gravina

2024–present: Postdoc , University of Pisa (IT)

2020–2024: PhD student , University of Pisa (IT)

2023–2023: Intern , Huawei Technologies Ltd. (DE)

2022–2022: PhD student , IDSIA (CH)

Papers (1)

Graph Adaptive Autoregressive Moving Average Models — ICML 2025 spotlightposter

Alex Bewley

2023–present: Research Scientist , DeepMind (CH)

2019–present: Research Scientist , Google (CH)

2018–2019: Research Scientist , Wayve Technologies

2016–2018: Postdoc , University of Oxford

2013–2016: PhD student , Queensland University of Technology

2009–2013: Research Associate , University of Queensland

2004–2008: Undergrad student , University of Sydney

Papers (1)

Linear Transformer Topological Masking with Graph Random Features — ICLR 2025 Poster

Alex James Boyd

2024–present: Researcher , GE HealthCare (US)

2018–2024: PhD student , University of California, Irvine

2014–2018: Undergrad student , California Polytechnic State University - San Luis Obispo

Papers (1)

Deep Continuous-Time State-Space Models for Marked Event Sequences — NeurIPS 2025 spotlight

Alex Shestopaloff

2023–present: Senior Lecturer , Queen Mary, University of London (GB)

2020–2023: Lecturer , Queen Mary, University of London (GB)

2017–2020: Postdoc , Alan Turing Institute

Papers (1)

Outlier-robust Kalman Filtering through Generalised Bayes — ICML 2024 Poster

Alex Wong

2022–present: Assistant Professor , Yale University (US)

2019–2022: Postdoc , University of California, Los Angeles (US)

2015–2019: PhD student , University of California, Los Angeles (US)

2012–2015: MS student , University of California, Los Angeles (US)

2007–2012: Undergrad student , University of California, Los Angeles (US)

Papers (1)

STree: Speculative Tree Decoding for Hybrid State Space Models — NeurIPS 2025 poster

Alexandre Didier

2025–present: Postdoc , ETHZ - ETH Zurich (CH)

2020–2025: PhD student , ETHZ - ETH Zurich (CH)

Papers (1)

Understanding the Differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks — NeurIPS 2024 poster

Alexandre Galashov

2013–2026: MS student , Ecole Polytechnique (FR)

Papers (1)

Kalman Filter for Online Classification of Non-Stationary Data — ICLR 2024 poster

Ali Bahri

2022–present: PhD student , École de technologie supérieure, Université du Québec (CA)

2016–2019: MS student , Iran University of Science and Technology Tehran, University of Tehran

2013–2016: Undergrad student , Islamic Azad University, Tehran South

Papers (1)

TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses — NeurIPS 2025 poster

Ali Bashashati

2019–present: Assistant Professor , University of British Columbia (CA)

Papers (1)

Boltzmann Semantic Score: A Semantic Metric for Evaluating Large Vision Models Using Large Language Models — ICLR 2025 Poster

Ali Hatamizadeh

2020–present: Research scientist , NVIDIA (US)

2016–2020: PhD student , UCLA Computer Science Department, University of California, Los Angeles (US)

Papers (1)

Gated Delta Networks: Improving Mamba2 with Delta Rule — ICLR 2025 Poster

Ali Jadbabaie

2016–present: Full Professor , Massachusetts Institute of Technology (US)

2011–2016: Full Professor , University of Pennsylvania (US)

2008–2011: Associate Professor , University of Pennsylvania (US)

Papers (1)

Linear attention is (maybe) all you need (to understand Transformer optimization) — ICLR 2024 poster

Ali Khajegili Mirabadi

2022–present: PhD student , University of British Columbia (CA)

2016–2021: Undergrad student , Isfahan University of Technology, University of Tehran (IR)

Papers (1)

Boltzmann Semantic Score: A Semantic Metric for Evaluating Large Vision Models Using Large Language Models — ICLR 2025 Poster

Ali Taghibakhshi

2023–present: Researcher , NVIDIA (US)

2019–2023: PhD student , University of Illinois at Urbana-Champaign (US)

Papers (1)

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning — NeurIPS 2025 poster

Alvin Heng

2021–present: PhD student , National University of Singapore (SG)

Papers (1)

Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series — ICML 2023 OralPoster

Amal Rannen-Triki

2019–present: Researcher , Google DeepMind (GB)

2016–2020: PhD student , KU Leuven (BE)

2018–2018: Researcher , Oath (US)

2014–2016: PhD student , Yonsei University (KR)

2010–2014: MS student , Centrale-Supelec (FR)

Papers (1)

Kalman Filter for Online Classification of Non-Stationary Data — ICLR 2024 poster

Ameen Ali Ali

2022–present: PhD student , Tel Aviv University (IL)

2020–2021: MS student , Tel Aviv University

Papers (1)

Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation — ICLR 2025 Poster

Amin Nejatbakhsh

2024–2025: Research Scientist , Facebook (US)

2022–2024: Research Fellow , Flatiron Institute (US)

2017–2022: PhD student , Columbia University (US)

2016–2017: Researcher , Institute for Research in Fundamental Sciences (IR)

2011–2016: Undergrad student , Sharif University of Technology (IR)

Papers (1)

Identifying Neural Dynamics Using Interventional State Space Models — ICML 2025 poster

Amir Bergman

2023–2024: ML Engineer , Tel Aviv University (IL)

2012–2016: Undergrad student , Tel Aviv University

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Amir H. Abdi

2022–present: Principal Researcher , Microsoft

2020–present: Research Engineer , Borealis AI

2015–2020: PhD student , University of British Columbia

Papers (1)

SCBench: A KV Cache-Centric Analysis of Long-Context Methods — ICLR 2025 Poster

Amir Yazdanbakhsh

2023–present: Researcher , Google DeepMind (US)

2018–2023: Researcher , Google Brain (US)

2014–2018: PhD student , Georgia Institute of Technology (US)

2011–2014: MS student , University of Wisconsin, Madison (US)

Papers (1)

When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models — ICML 2024 Poster

Amit Roy-Chowdhury

2004–present: Professor , University of California, Riverside (US)

2002–2003: Postdoc , University of Maryland, College Park

1998–2002: PhD student , University of Maryland, College Park

1995–1997: MS student , Indian Institute of Science, Indian institute of science, Bangalore

1991–1995: Undergrad student , Jadavpur University

Papers (1)

Theoretical Insights into In-context Learning with Unlabeled Data — NeurIPS 2025 poster

Amr Ahmed

2011–2021: Researcher , Research, Google

2005–2011: PhD student , School of Computer Science, Carnegie Mellon University

Papers (1)

Linear Transformer Topological Masking with Graph Random Features — ICLR 2025 Poster

Anda Cao

2024–present: PhD student , Zhejiang University (CN)

2022–2023: MS student , Zhejiang University

2018–2022: Undergrad student , Zhejiang Sci-Tech University

Papers (1)

Vision Mamba Mender — NeurIPS 2024 poster

Andre Lim

2023–present: PhD student , University of Michigan - Ann Arbor (US)

2022–2023: Researcher , National University of Singapore (SG)

Papers (1)

Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series — ICML 2023 OralPoster

Andrea Ceni

2022–2025: Postdoc , University of Pisa (IT)

2021–2022: Postdoc , University of Exeter (GB)

2017–2021: PhD student , University of Exeter (GB)

2014–2017: MS student , University of Florence (IT)

Papers (1)

Graph Adaptive Autoregressive Moving Average Models — ICML 2025 spotlightposter

Andreas C Mueller

2020–present: Principal Researcher , Microsoft (US)

2016–2020: Postdoc , Columbia University

Papers (1)

TabFlex: Scaling Tabular Learning to Millions with Linear Attention — ICML 2025 spotlightposter

Andreas Look

2019–present: Researcher , Bosch (DE)

2016–2019: PhD student , University of Stuttgart

Papers (1)

Cheap and Deterministic Inference for Deep State-Space Models of Interacting Dynamical Systems — Accepted by TMLR

Andreas Mayr

2022–present: Postdoc , Johannes Kepler Universität Linz (AT)

2011–2022: PhD student , Johannes Kepler University Linz (AT)

2006–2011: MS student , Johannes Kepler University Linz (AT)

Papers (1)

Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences — ICLR 2025 Poster

Andrej Risteski

2019–present: Assistant Professor , Carnegie Mellon University

2017–2019: Postdoc , Massachusetts Institute of Technology

2012–2017: PhD student , Princeton University

Papers (1)

On the Benefits of Memory for Modeling Time-Dependent PDEs — ICLR 2025 Oral

Andrew Donald McLeod

2020–2024: Postdoc , University of Oxford

Papers (1)

Log Neural Controlled Differential Equations: The Lie Brackets Make A Difference — ICML 2024 Poster

Andrew M Saxe

2023–present: Full Professor , University College London, University of London (GB)

2021–2023: Associate Professor , University College London, University of London (GB)

2021–2022: Researcher , Facebook AI (US)

2019–2021: Associate Professor , University of Oxford (GB)

2015–2017: Postdoc , Harvard University (US)

2008–2015: PhD student , Stanford University (US)

Papers (1)

Training Dynamics of In-Context Learning in Linear Attention — ICML 2025 spotlightposter

Anh Tuan Tran

2025–present: Principal Researcher , QualComm (VN)

2019–2025: Research Scientist , VinAI Research (VN)

2018–2019: Applied Scientist , Amazon (US)

2012–2017: PhD student , University of Southern California (US)

2005–2010: Undergrad student , Hanoi University of Science and Technology (VN)

Papers (1)

DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation — NeurIPS 2024 poster

Anisoara Calinescu

2002–present: Associate Professor , Department of Computer Science, University of Oxford (GB)

1996–2002: PhD student , University of Oxford, University of Oxford (GB)

Papers (1)

LOB-Bench: Benchmarking Generative AI for Finance - an Application to Limit Order Book Data — ICML 2025 poster

Ankit Gupta

2020–present: Researcher , International Business Machines (US)

2015–2020: Postdoc , Tel Aviv University (IL)

2013–2015: PhD student , Chennai Mathematical Institute (IN)

2006–2010: Undergrad student , Indian Institute of Technology, Kanpur, Dhirubhai Ambani Institute Of Information and Communication Technology (IN)

Papers (1)

Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors — ICLR 2024 oral

Anming Gu

2025–2030: PhD student , University of Texas at Austin (US)

2020–2024: Undergrad student , Boston University (US)

Papers (1)

Partially Observed Trajectory Inference using Optimal Transport and a Dynamics Prior — ICLR 2025 Poster

Anna Mészáros

2023–present: PhD student , University of Cambridge

2022–2023: MS student , University of Cambridge

2019–2022: Undergrad student , Eotvos Lorand University

Papers (1)

Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD Prompts — NeurIPS 2024 spotlight

Anqi Wu

2022–present: Assistant Professor , Georgia Institute of Technology (US)

2019–2021: Postdoc , Columbia University

2015–2019: PhD student , Princeton University

Papers (1)

Learning Time-Varying Multi-Region Brain Communications via Scalable Markovian Gaussian Processes — ICML 2025 oral

Anran Zhang

2022–2025: MS student , University of the Chinese Academy of Sciences

Papers (1)

Modeling Language Tokens as Functionals of Semantic Fields — ICML 2024 Poster

Antonio Norelli

2024–present: Postdoc , University of Oxford (GB)

2019–2024: PhD student , Sapienza University of Rome (IT)

2016–2019: MS student , Sapienza University of Rome (IT)

2013–2016: Undergrad student , Sapienza University of Rome (IT)

Papers (1)

DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Models — Accepted by TMLR

Anushan Fernando

2022–present: Researcher , DeepMind

Papers (1)

Resurrecting Recurrent Neural Networks for Long Sequences — ICML 2023 OralPoster

Anyu Zhu

2024–present: MS student , Fudan University (CN)

2020–2024: Undergrad student , Central South University (CN)

Papers (1)

3DET-Mamba: Causal Sequence Modelling for End-to-End 3D Object Detection — NeurIPS 2024 poster

Aoran Wang

2025–present: Researcher , Shanghai Artificial Intelligence Laboratory (CN)

2020–2024: PhD student , University of Luxemburg (LU)

2015–2019: MS student , Karlsruher Institut für Technologie (DE)

2018–2018: MS student , Robert Bosch GmbH, Bosch (DE)

2011–2015: Undergrad student , Tongji University (CN)

Papers (1)

Structural Inference of Dynamical Systems with Conjoined State Space Models — NeurIPS 2024 poster

Apratim Bhattacharyya

2022–present: Researcher , Qualcomm Technologies, Inc. (US)

2021–2022: Postdoc , Eberhard-Karls-Universität Tübingen (DE)

2016–2021: PhD student , Saarland Informatics Campus, Max-Planck Institute (DE)

Papers (1)

Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance? — NeurIPS 2025 poster

Aranyak Mehta

2007–present: Researcher , Google Research (US)

2000–2005: PhD student , College of Computing, Georgia Institute of Technology (US)

Papers (1)

Linear Transformer Topological Masking with Graph Random Features — ICLR 2025 Poster

Arjun Karuvally

2025–present: Postdoc , Salk Institute (US)

2019–2025: PhD student , University of Massachusetts, Amherst (US)

2017–2018: MS student , University of Massachusetts, Amherst (US)

2013–2017: Undergrad student , National Institute of Technology, Trichy (IN)

Papers (1)

Bridging Expressivity and Scalability with Adaptive Unitary SSMs — NeurIPS 2025 poster

Arjun Parthasarathy

2023–present: Research Assistant , Columbia University (US)

2023–2027: Undergrad student , Columbia University (US)

2024–2024: Research Assistant , Computer Science Department, Stanford University (US)

2021–2023: Researcher , University of Southern California (US)

Papers (1)

ThunderKittens: Simple, Fast, and $\textit{Adorable}$ Kernels — ICLR 2025 Spotlight

Arjun Seshadri

2021–present: Researcher , Amazon (US)

2015–2021: PhD student , Stanford University (US)

Papers (1)

B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory — NeurIPS 2024 poster

Arjun Vikram

2022–present: Undergrad student , Stanford University (US)

Papers (1)

Learning to (Learn at Test Time): RNNs with Expressive Hidden States — ICML 2025 spotlightposter

Arkadiusz Sitek

2022–present: Researcher , Massachusetts General Hospital, Harvard Medical School (US)

2018–2021: Researcher , International Business Machines

2015–2018: Researcher , Philips Research

2006–2015: Assistant Professor , Harvard University (US)

Papers (1)

Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation — NeurIPS 2025 poster

Arnab Sen Sharma

2022–2027: PhD student , Northeastern University (US)

2014–2018: Undergrad student , Shahjalal University of Science and Technology (BD)

Papers (1)

Locating and Editing Factual Associations in Mamba — COLM

Arne Speerforck

2021–present: Full Professor , Technische Universität Hamburg (DE)

Papers (1)

Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximations — ICLR 2025 Poster

Arnur Nigmetov

2022–present: Researcher , Lawrence Berkeley National Lab

2020–2022: Postdoc , Lawrence Berkeley National Lab

2015–2020: PhD student , Technische Universität Graz

2012–2015: MS student , Universität des Saarlandes

2005–2007: MS student , Al-Farabi Kazakh National University

2001–2005: Undergrad student , Al-Farabi Kazakh National University

Papers (1)

Robustifying State-space Models for Long Sequences via Approximate Diagonalization — ICLR 2024 spotlight

Arshia Afzal

2022–2026: PhD student , EPFL - EPF Lausanne (CH)

Papers (1)

Linear Attention for Efficient Bidirectional Sequence Modeling — NeurIPS 2025 poster

Artem Zholus

2023–2027: PhD student , École Polytechnique de Montréal, Université de Montréal (CA)

2020–2022: MS student , Moscow Institute of Physics and Technology

2014–2018: Undergrad student , ITMO University

Papers (1)

Mastering Memory Tasks with World Models — ICLR 2024 oral

Arya Honarpisheh

2022–present: PhD student , Northeastern University (US)

2016–2021: Undergrad student , Sharif University of Technology (IR)

Papers (1)

Generalization Error Analysis for Selective State-Space Models Through the Lens of Attention — NeurIPS 2025 poster

Ashish Rao

2020–2024: Undergrad student , Stanford University

Papers (1)

Towards Learning High-Precision Least Squares Algorithms with Sequence Models — ICLR 2025 Poster

Ashish Sabharwal

2021–present: Principal Researcher , Allen Institute for AI (US)

2014–2021: Senior Researcher , Allen Institute for AI (US)

2010–2014: Research Scientist , IBM (US)

2008–2010: Research Associate , Cornell University (US)

2005–2008: Postdoc , Cornell University (US)

1998–2005: PhD student , University of Washington (US)

1994–1998: Undergrad student , Indian Institute of Technology, Kanpur (IN)

Papers (1)

The Illusion of State in State-Space Models — ICML 2024 Poster

Ashwath Aithal

2003–present: Researcher , NVIDIA

Papers (1)

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning — NeurIPS 2025 poster

Atsushi Yamashita

2022–present: Full Professor , The University of Tokyo

2011–2022: Associate Professor , The University of Tokyo

2008–2011: Associate Professor , Shizuoka University

2001–2008: Assistant Professor , Shizuoka University

1998–2001: PhD student , The University of Tokyo

1996–1998: MS student , The University of Tokyo

Papers (1)

State-Free Inference of State-Space Models: The *Transfer Function* Approach — ICML 2024 Poster

Aurelio Sulser

2023–2027: PhD student , ETHZ - ETH Zurich

Papers (1)

Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theory — ICLR 2025 Poster

Avery Hee-Woon Ryoo

2023–present: MS student , Mila - Québec AI Institute, Université de Montréal (CA)

2018–2023: Undergrad student , University of Waterloo (CA)

Papers (1)

Generalizable, real-time neural decoding with hybrid state-space models — NeurIPS 2025 poster

Aviral Chharia

2024–present: PhD student , Carnegie Mellon University (US)

2022–2024: MS student , Carnegie Mellon University (US)

2021–2022: Visiting Researcher , University of British Columbia (CA)

2021–2022: Visiting Researcher , University of Western Ontario (CA)

2020–2022: Research Intern , National University of Singapore (SG)

2018–2022: Undergrad student , Thapar Institute of Engineering and Technology (IN)

Papers (1)

Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba — NeurIPS 2024 poster

Aviv Tamar

2019–present: Assistant Professor , Technion, Technion

2015–2018: Postdoc , University of California Berkeley

2011–2015: PhD student , Technion

Papers (1)

MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning — ICLR 2024 poster

Avner May

2023–present: Researcher , Together.ai (US)

2020–2023: Research Scientist , Google

2018–2020: Postdoc , Stanford University

2011–2017: PhD student , Columbia University

2005–2009: Undergrad student , Harvard University

Papers (1)

The Mamba in the Llama: Distilling and Accelerating Hybrid Models — NeurIPS 2024 poster

Avshalom Manevich

2020–2025: MS student , Bar-Ilan University (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Ayesha Vermani

2022–present: PhD student , Champalimaud Centre for the Unknown

2019–present: PhD student , State University of New York, Stony Brook

Papers (1)

Meta-Dynamical State Space Models for Integrative Neural Data Analysis — ICLR 2025 Spotlight

Azalia Mirhoseini

2023–present: Assistant Professor , Computer Science Department, Stanford University

2023–present: Assistant Professor , Stanford University

2023–present: Researcher , Google

Papers (1)

Exploring Diffusion Transformer Designs via Grafting — NeurIPS 2025 oral

Babak Rahmani

2022–2025: Postdoc , Research, Microsoft (GB)

2018–2022: PhD student , Swiss Federal Institute of Technology Lausanne

2014–2016: MS student , Sharif University of Technology

2010–2014: Undergrad student , Tehran university

Papers (1)

Implicit Language Models are RNNs: Balancing Parallelization and Expressivity — ICML 2025 spotlightposter

Balint Daroczy

2023–present: Researcher , Institute for Computer Science and Control, HUN-REN SZTAKI (HU)

2018–2023: Postdoc , Institute for Computer Science and Control, HUN-REN SZTAKI (HU)

2020–2022: Postdoc , Université catholique de Louvain (BE)

Papers (1)

Length independent generalization bounds for deep SSM architectures via Rademacher contraction and stability constraints — Accepted by TMLR

Baochang Zhang

2011–present: Professor , Beihang University (CN)

Papers (1)

DAMamba: Vision State Space Model with Dynamic Adaptive Scan — NeurIPS 2025 poster

Baolin Peng

2024–present: Principal Researcher , Research, Microsoft (US)

2023–2024: Researcher , Tencent AI Lab (US)

2015–2019: PhD student , The Chinese University of Hong Kong (HK)

2012–2015: MS student , Beihang University, Tsinghua University (CN)

2008–2012: Undergrad student , Yantai University (CN)

Papers (1)

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation — NeurIPS 2025 poster

Barak Lenz

2017–2024: CTO , AI21 Labs (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Barak Peleg

2017–present: Researcher , AI21 Labs (IL)

2008–2010: MS student , Weizmann Institute of Science

1999–2001: Undergrad student , Hebrew University of Jerusalem

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Barbara Rakitsch

2018–present: Research Scientist , Robert Bosch GmbH, Bosch (DE)

2014–2015: Postdoc , European Bioinformatics Institute (GB)

2011–2014: PhD student , Max Planck Institute for Intelligent Systems, Max-Planck Institute (DE)

Papers (1)

Cheap and Deterministic Inference for Deep State-Space Models of Interacting Dynamical Systems — Accepted by TMLR

Bart Kranstauber

2019–2023: Postdoc , University of Amsterdam

Papers (1)

Deep Gaussian Markov Random Fields for Graph-Structured Dynamical Systems — NeurIPS 2023 poster

Beichen Xue

2021–2025: Undergrad student , National University of Singapore (SG)

Papers (1)

State-space models with layer-wise nonlinearity are universal approximators with exponential decaying memory — NeurIPS 2023 poster

Ben Aviram

2022–present: Researcher , AI21 Labs (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Bencheng Liao

2020–present: PhD student , Huazhong University of Science and Technology (CN)

2016–2020: Undergrad student , Huazhong University of Science and Technology (CN)

Papers (1)

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model — ICML 2024 Poster

Benjamin Bowman

2023–present: Researcher , Amazon (US)

2022–2023: Intern , Amazon (US)

2018–2023: PhD student , University of California, Los Angeles (US)

2021–2021: PhD student , Max Planck Institute for Mathematics in the Sciences, Max-Planck Institute (DE)

2014–2018: Undergrad student , Pennsylvania State University (US)

Papers (1)

B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory — NeurIPS 2024 poster

Benjamin Peherstorfer

2022–present: Associate Professor , New York University

2018–2022: Assistant Professor , New York University

2016–2018: Assistant Professor , University of Wisconsin - Madison

2014–2016: Postdoc , Massachusetts Institute of Technology

2010–2013: PhD student , Technische Universität München

Papers (1)

Hankel Singular Value Regularization for Highly Compressible State Space Models — NeurIPS 2025 poster

Benjamin Wild

2024–present: Principal Researcher , Berlin Institute of Health (DE)

2021–2024: Postdoc , Berlin Institute of Health (DE)

2017–2021: PhD student , Freie Universitaet Berlin (DE)

Papers (1)

JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation Model — NeurIPS 2025 poster

Beomchan Park

2023–present: PhD student , KAIST (KR)

Papers (1)

Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models — NeurIPS 2024 poster

Bicheng Xu

2020–present: PhD student , University of British Columbia (CA)

2017–2020: MS student , University of British Columbia (CA)

2014–2017: Undergrad student , Simon Fraser University (CA)

2012–2017: Undergrad student , Zhejiang University (CN)

Papers (1)

Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance? — NeurIPS 2025 poster

Bidipta Sarkar

2024–present: PhD student , University of Oxford (GB)

2020–2024: Undergrad student , Stanford University (US)

Papers (1)

LOB-Bench: Benchmarking Generative AI for Finance - an Application to Limit Order Book Data — ICML 2025 poster

Bin Chen

2024–present: Associate Professor , Harbin Institute of Technology, Shenzhen (CN)

2021–2024: Assistant Professor , Harbin Institute of Technology, Shenzhen (CN)

2021–2021: Postdoc , Tsinghua Shenzhen International Graduate School, Tsinghua University (CN)

2017–2021: PhD student , Tsinghua University, Tsinghua University (CN)

2019–2020: Researcher , University of Waterloo (CA)

2014–2017: MS student , South China Normal University (CN)

Papers (1)

LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling — NeurIPS 2024 poster

Bingchen Liu

2024–2025: Researcher , Playground Inc. (US)

2021–2024: Researcher , Bytedance Inc. (US)

2017–2021: PhD student , Rutgers University (US)

2015–2017: Undergrad student , Rutgers University (US)

Papers (1)

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer — ICML 2025 poster

Bingding Huang

2019–present: Professor , Shenzhen Technology University

Papers (1)

JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation Model — NeurIPS 2025 poster

Biqing Qi

2024–present: Researcher , Shanghai Artificial Intelligence Laboratory (CN)

2021–2024: Joint Supervision , Tsinghua University (CN)

2019–2024: PhD student , Harbin Institute of Technology (CN)

Papers (1)

Exploring Adversarial Robustness of Deep State Space Models — NeurIPS 2024 poster

Biswadeep Chakraborty

2025–2030: AI Scientist , Mercuria Energy Americas (US)

2020–2025: PhD student , Georgia Institute of Technology (US)

2019–2019: Research Assistant , National University of Singapore (SG)

2015–2019: Undergrad student , Jadavpur University, Kolkata (IN)

2018–2018: Research Intern , Université de Sherbrooke (CA)

2017–2017: Research Intern , Indian Academy of Sciences (IN)

Papers (1)

FLAME: Fast Long-context Adaptive Memory for Event-based Vision — NeurIPS 2025 poster

Björn Deiseroth

2021–present: Researcher , Aleph Alpha (DE)

2021–2025: PhD student , Technische Universität Darmstadt (DE)

Papers (1)

Mechanistic Design and Scaling of Hybrid Architectures — ICML 2024 Poster

Bo Hu

2001–present: Full Professor , Fudan University

1999–2000: Associate Professor , Fudan University

1997–1998: Lecturer , Fudan University

1993–1996: PhD student , Fudan University

1990–1993: MS student , Fudan University

1986–1990: Undergrad student , Fudan University

Papers (1)

EventMG: Efficient Multilevel Mamba-Graph Learning for Spatiotemporal Event Representation — NeurIPS 2025 poster

Bo Liu

2019–present: PhD student , University of Texas, Austin (US)

Papers (1)

Longhorn: State Space Models are Amortized Online Learners — ICLR 2025 Poster

Bo Miao

2025–present: Postdoc , Australian Institute for Machine Learning (AU)

2021–2025: PhD student , University of Western Australia (AU)

Papers (1)

CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation — NeurIPS 2025 poster

Bo Peng

2003–present: Undergrad student , University of Hong Kong (HK)

Papers (1)

RWKV-7 "Goose" with Expressive Dynamic State Evolution — COLM 2025

Bo Yang

2008–present: Full Professor , Jilin University (CN)

Papers (1)

Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling — NeurIPS 2024 poster

Bo Zheng

2017–present: Principal Researcher , Alibaba Group (CN)

2006–2017: Staff Engineer , Google (US)

2001–2006: PhD student , Tsinghua University (CN)

1997–2001: Undergrad student , Tsinghua University (CN)

Papers (1)

Demystify Mamba in Vision: A Linear Attention Perspective — NeurIPS 2024 poster

Bo Zheng

2023–2025: Researcher , Alibaba Group (CN)

2018–2022: PhD student , Harbin Institute of Technology (CN)

2016–2018: MS student , Harbin Institute of Technology (CN)

2012–2016: Undergrad student , Harbin Institute of Technology (CN)

Papers (1)

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free — NeurIPS 2025 oral

Bobby He

2023–present: Postdoc , Department of Computer Science, ETHZ - ETH Zurich (CH)

2019–2023: PhD student , University of Oxford (GB)

Papers (1)

Recurrent Distance Filtering for Graph Representation Learning — ICML 2024 Poster

Bolun Wang

2023–present: CEO , LuxiTech Co., Ltd

Papers (1)

Gated Slot Attention for Efficient Linear-Time Sequence Modeling — NeurIPS 2024 poster

Boqun Ma

2020–2024: Researcher , Shanghai Jiaotong University

2017–2020: MS student , Shanghai Jiaotong University

Papers (1)

State Space Models on Temporal Graphs: A First-Principles Study — NeurIPS 2024 poster

Bor-Jiun Lin

2025–2025: Researcher , National Taiwan University (TW)

2022–2024: MS student , Department of Computer Science, National Tsing Hua University, National Tsinghua University (TW)

2018–2022: Undergrad student , Department of Computer Science, National Tsing Hua University, National Tsinghua University (TW)

Papers (1)

EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling — NeurIPS 2025 spotlight

Bowen Zhou

2022–present: Full Professor , Tsinghua University (CN)

2017–2021: VP , JD.com (CN)

2003–2017: Principal Researcher , IBM TJ Watson Research Center (US)

Papers (1)

Exploring Adversarial Robustness of Deep State Space Models — NeurIPS 2024 poster

Boxing Chen

2022–present: Principal Researcher , Huawei Technologies Ltd.

2017–2022: Researcher , Alibaba Group

2009–2017: Researcher , National Research Council Canada

2007–2009: Researcher , A*STAR

2005–2007: Postdoc , Fondazione Bruno Kessler

2003–2004: Postdoc , University of Grenoble-Alpes

Papers (1)

Mamba Modulation: On the Length Generalization of Mamba Models — NeurIPS 2025 poster

Boxuan Zhang

2022–2028: PhD student , BIT (CN)

Papers (1)

DyMoDreamer: World Modeling with Dynamic Modulation — NeurIPS 2025 poster

Bozhou Zhang

2023–present: PhD student , Fudan University (CN)

2019–2023: Undergrad student , Beijing University of Aeronautics and Astronautics (CN)

Papers (1)

DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States — NeurIPS 2024 poster

Brian Hie

2024–present: Assistant Professor , Stanford University (US)

Papers (1)

Mechanistic Design and Scaling of Hybrid Architectures — ICML 2024 Poster

Bryan Catanzaro

2016–present: Vice President , NVIDIA (US)

2014–2016: Senior Researcher , Baidu (US)

2011–2014: Researcher , NVIDIA (US)

2005–2011: PhD student , University of California Berkeley (US)

2004–2005: MS student , Brigham Young University (US)

1997–2003: Undergrad student , Brigham Young University (US)

Papers (1)

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning — NeurIPS 2025 poster

Byoungwoo Park

2025–present: Intern , Georgia Institute of Technology (US)

2024–present: MS student , KAIST (KR)

Papers (1)

Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Series — ICLR 2025 Oral

Byung-Kwan Lee

2025–present: Research Scientist , NVIDIA (TW)

2024–2025: Research Intern , NVIDIA (TW)

2020–2025: PhD , KAIST (KR)

Papers (1)

Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models — NeurIPS 2024 poster

Cao Xiao

2023–present: VP of AI , GE Healthcare (US)

2022–2023: VP of ML and NLP , Relativity (US)

2021–2022: Senior Director of Data Science and Machine Learning , Amplitude (US)

2019–2021: Director of Machine Learning , IQVIA (US)

2017–2019: Research Staff Member , AI for Healthcare, IBM Research (US)

2012–2016: PhD student , University of Washington, Seattle (US)

Papers (1)

Deep Continuous-Time State-Space Models for Marked Event Sequences — NeurIPS 2025 spotlight

Caoshuo Li

2023–2026: MS student , Xiamen University (CN)

2019–2023: Undergrad student , Changchun University of Science and Technology (CN)

Papers (1)

DAMamba: Vision State Space Model with Dynamic Adaptive Scan — NeurIPS 2025 poster

Carlos D Brody

2014–present: Full Professor , Princeton University

Papers (1)

Modeling state-dependent communication between brain regions with switching nonlinear dynamical systems — ICLR 2024 poster

Carlos E. Luis

2021–present: PhD student , Technische Universität Darmstadt

2017–2019: MS student , University of Toronto

Papers (1)

Uncertainty Representations in State-Space Layers for Deep Reinforcement Learning under Partial Observability — Accepted by TMLR

Carlos Guestrin

2021–present: Full Professor , Stanford University

2016–2021: Principal Researcher , Apple

2012–2021: Full Professor , University of Washington

2004–2012: Associate Professor , Carnegie Mellon University

Papers (1)

Learning to (Learn at Test Time): RNNs with Expressive Hidden States — ICML 2025 spotlightposter

Carmel Majidi

2019–present: Full Professor , Carnegie Mellon University (US)

Papers (1)

Hierarchical State Space Models for Continuous Sequence-to-Sequence Modeling — ICML 2024 Poster

Carola-Bibiane Schönlieb

2018–present: Full Professor , University of Cambridge (GB)

2010–2018: Associate Professor , University of Cambridge (GB)

Papers (1)

Graph Adaptive Autoregressive Moving Average Models — ICML 2025 spotlightposter

Catherine Arnett

2025–present: Researcher , EleutherAI (US)

2024–2025: Researcher , PleIAs (FR)

2019–2025: PhD student , University of California, San Diego (US)

2014–2018: Undergrad student , University of Edinburgh, University of Edinburgh (GB)

Papers (1)

Revenge of the Fallen? Recurrent Models Match Transformers at Predicting Human Language Comprehension Metrics — COLM

Cesar A Uribe

2021–present: Assistant Professor , Rice University

2018–2020: Postdoc , Massachusetts Institute of Technology

2013–2018: PhD student , University of Illinois, Urbana Champaign

2011–2013: MS student , Delft University of Technology

Papers (1)

PIDformer: Transformer Meets Control Theory — ICML 2024 Poster

Chae Won Kim

2023–present: PhD student , KAIST (KR)

Papers (1)

Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models — NeurIPS 2024 poster

Chang Xu

2024–present: Associate Professor , University of Sydney (AU)

2017–2023: Assistant Professor , University of Sydney (AU)

Papers (1)

Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model — NeurIPS 2024 poster

Changdi Yang

2025–2025: Intern , Snap Inc. (US)

2019–2025: PhD student , Northeastern University (US)

2015–2019: Undergrad student , China Agricultural University (CN)

Papers (1)

Sparse Learning for State Space Models on Mobile — ICLR 2025 Poster

Changshuo Wang

2025–present: Postdoc , University College London, University of London (GB)

2023–2025: Postdoc , Nanyang Technological University (SG)

2018–2023: PhD student , University of the Chinese Academy of Sciences (CN)

Papers (1)

DyPolySeg: Taylor Series-Inspired Dynamic Polynomial Fitting Network for Few-shot Point Cloud Semantic Segmentation — ICML 2025 poster

Chao Li

2014–2018: MS student , Peking University

Papers (1)

QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion — NeurIPS 2024 poster

Chao Ma

2024–present: Full Professor , Shanghai Jiao Tong University (CN)

2022–2023: Associate Professor , Shanghai Jiao Tong University (CN)

2019–2021: Assistant Professor , Shanghai Jiao Tong University (CN)

2015–2018: Post Doc , The University of Adelaide

2013–2015: Researcher , UC Merced

2011–2015: Graduate Student , Shanghai Jiao Tong University

Papers (1)

QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model — NeurIPS 2024 poster

Chao Xu

1997–2027: Full Professor , Peking University (CN)

Papers (1)

MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected Layers — NeurIPS 2024 poster

Chen Almagor

—–present: MS student , Hebrew University in Jerusalem

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Chen Liang

2024–present: Researcher , Microsoft (US)

2019–2023: PhD student , Georgia Institute of Technology (US)

2014–2018: Undergrad student , University of Southern California (US)

Papers (1)

Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling — ICLR 2025 Poster

Chen Xu

2024–present: Engineer , Houmo (CN)

2021–2024: MS student , Nanjing University of Aeronautics and Astronautics (CN)

Papers (1)

MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods — ICLR 2025 Poster

Cheng Long

2024–present: Associate Professor , Nanyang Technological University (SG)

2018–2024: Assistant Professor , Nanyang Technological University (SG)

2016–2018: Lecturer , Queen's University Belfast (GB)

2015–2016: Postdoc , The Hong Kong University of Science and Technology (HK)

Papers (1)

Hybrid Mamba for Few-Shot Segmentation — NeurIPS 2024 poster

Chenghao Zhou

2022–present: PhD student , Peking University (CN)

Papers (1)

Orochi: Versatile Biomedical Image Processor — NeurIPS 2025 spotlight

Chengjie Wang

2022–present: PhD student , Shanghai Jiao Tong University (CN)

2014–present: Researcher , Tencent YouTu Lab (CN)

2011–2014: MS student , Shanghai Jiao Tong University (CN)

2010–2012: MS student , Waseda University (JP)

2007–2011: Undergrad student , Shanghai Jiao Tong University (CN)

Papers (1)

MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection — NeurIPS 2024 poster

Chengjun Wu

2021–2025: Undergrad student , University of Wisconsin - Madison

Papers (1)

Pretrained Hybrids with MAD Skills — COLM 2025

Chengkai Hou

2025–2028: PhD student , Peking University (CN)

2020–2023: MS student , Jilin University (CN)

2015–2019: Undergrad student , Jilin University (CN)

Papers (1)

Orochi: Versatile Biomedical Image Processor — NeurIPS 2025 spotlight

Chengliang Liu

2024–2025: Postdoc , Hong Kong University of Science and Technology (HK)

Papers (1)

Hierarchical Information Aggregation for Incomplete Multimodal Alzheimer's Disease Diagnosis — NeurIPS 2025 poster

Chengrui Li

2025–present: Researcher , Facebook (US)

2021–2026: PhD student , Georgia Institute of Technology (US)

2016–2020: Undergrad student , Sichuan University (CN)

2018–2019: Undergrad student , University of Tennessee, Knoxville (US)

Papers (1)

Learning Time-Varying Multi-Region Brain Communications via Scalable Markovian Gaussian Processes — ICML 2025 oral

Chengruidong Zhang

2025–present: Researcher , Alibaba Group (CN)

2022–2025: Researcher , Microsoft (CN)

2020–2022: MS student , New York University (US)

2015–2019: Undergrad student , Beijing University of Aeronautics and Astronautics (CN)

Papers (1)

SCBench: A KV Cache-Centric Analysis of Long-Context Methods — ICLR 2025 Poster

Chenguang Zhu

2010–2025: PhD student , Open Review (US)

Papers (1)

Sparse Modular Activation for Efficient Sequence Modeling — NeurIPS 2023 poster

ChengXiang Zhai

2013–present: Full Professor , University of Illinois, Urbana Champaign (US)

2008–2013: Associate Professor , University of Illinois at Urbana-Champaign (US)

2002–2008: Assistant Professor , University of Illinois at Urbana-Champaign (US)

1993–2002: PhD student , Carnegie Mellon University (US)

Papers (1)

Sparse Modular Activation for Efficient Sequence Modeling — NeurIPS 2023 poster

Chengyu Duan

2021–2025: Undergrad student , University of Wisconsin - Madison (US)

Papers (1)

Pretrained Hybrids with MAD Skills — COLM 2025

Chenhang HE

2023–present: Assistant Professor , The Hong Kong Polytechnic University (HK)

Papers (1)

Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection — NeurIPS 2024 spotlight

Chenhui Xu

2024–present: PhD student , State University of New York at Buffalo (US)

2022–2024: PhD student , George Mason University (US)

2017–2021: Undergrad student , University of Science and Technology of China (CN)

Papers (1)

Sub-Sequential Physics-Informed Learning with State Space Model — ICML 2025 poster

Chenyu Liu

2021–2025: PhD student , Nanyang Technological University (SG)

Papers (1)

A Multimodal BiMamba Network with Test-Time Adaptation for Emotion Recognition Based on Physiological Signals — NeurIPS 2025 poster

Chenyu Wang

2022–2024: MS student , New York University (US)

Papers (1)

Hierarchical State Space Models for Continuous Sequence-to-Sequence Modeling — ICML 2024 Poster

Chia Hsiang Kao

2023–2028: PhD student , Cornell University (US)

2015–2022: Undergrad student , National Yang Ming Chiao Tung University (TW)

Papers (1)

Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling — ICML 2024 Poster

Chris Lu

2021–2024: PhD student , University of Oxford (GB)

2016–2019: Undergrad student , University of California Berkeley

Papers (1)

Structured State Space Models for In-Context Reinforcement Learning — NeurIPS 2023 poster

Christian Desrosiers

2009–present: Full Professor , École de technologie supérieure (CA)

Papers (1)

TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses — NeurIPS 2025 poster

Christian Zhou-Zheng

2022–present: High school student , The Pingry School (US)

Papers (1)

RWKV-7 "Goose" with Expressive Dynamic State Evolution — COLM 2025

Christopher John Rozell

2018–present: Full Professor , Georgia Institute of Technology

2013–2018: Associate Professor , Georgia Institute of Technology

2008–2013: Assistant Professor , Georgia Institute of Technology

2007–2008: Postdoc , University of California Berkeley

2000–2007: PhD student , Rice University

Papers (1)

Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics — NeurIPS 2024 poster

Christopher Pal

2019–present: Full Professor , Polytechnique Montreal (CA)

2014–2019: Associate Professor , Polytechnique Montréal (CA)

2009–2014: Assistant Professor , Polytechnique Montreal (CA)

2007–2009: Assistant Professor , University of Rochester (US)

2005–2007: Research Scientist , University of Massachusetts, Amherst (US)

Papers (1)

Block-State Transformers — NeurIPS 2023 poster

Chulhee Yun

2025–present: Researcher , Google (KR)

2022–present: Assistant Professor , Korea Advanced Institute of Science & Technology (KR)

2021–2022: Postdoc , Massachusetts Institute of Technology (US)

2016–2021: PhD student , Massachusetts Institute of Technology (US)

2020–2020: Research Intern , Google (US)

Papers (1)

Linear attention is (maybe) all you need (to understand Transformer optimization) — ICLR 2024 poster

Chun Yuan

2021–present: Full Professor , Tsinghua University, Tsinghua University (CN)

1999–2002: PhD student , Tsinghua University, Tsinghua University (CN)

1997–1999: MS student , Tsinghua University, Tsinghua University (CN)

Papers (1)

Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking — NeurIPS 2025 poster

Chun-Yi Lee

2024–present: Full Professor , National Taiwan University (TW)

2023–2024: Full Professor , National Tsing Hua University (TW)

2019–2023: Associate Professor , National Tsing Hua University (TW)

2015–2019: Assistant Professor , National Tsinghua University (TW)

2012–2015: Senior Hardware Engineer , Oracle (US)

2007–2013: PhD student , Princeton University (US)

2003–2005: MS student , National Taiwan University (TW)

Papers (1)

EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling — NeurIPS 2025 spotlight

Chunhua Shen

2021–present: Full Professor , Zhejiang University (CN)

2011–2021: Professor , University of Adelaide (AU)

2002–2006: PhD , University of Adelaide

Papers (1)

Revisiting Convolution Architecture in the Realm of DNA Foundation Models — ICLR 2025 Poster

Chunjiang Ge

2020–2026: PhD student , Control science and technology, Tsinghua University, Tsinghua University (CN)

2016–2020: Undergrad student , Physics and Math, Tsinghua University, Tsinghua University (CN)

Papers (1)

Demystify Mamba in Vision: A Linear Attention Perspective — NeurIPS 2024 poster

Chunting Zhou

2022–present: Researcher , Meta AI (US)

2016–2022: PhD student , Language Technologies Institute, Carnegie Mellon University (US)

2019–2020: PhD student , Facebook

Papers (1)

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length — NeurIPS 2024 poster

Chunxu Liu

2022–present: PhD student , Nanjing University (CN)

2018–2022: Undergrad student , Nanjing University (CN)

Papers (1)

VFIMamba: Video Frame Interpolation with State Space Models — NeurIPS 2024 poster

Chuxin Wang

2023–2026: PhD student , University of Science and Technology of China (CN)

2017–2021: Undergrad student , University of Science and Technology of China (CN)

Papers (1)

State Space Model Meets Transformer: A New Paradigm for 3D Object Detection — ICLR 2025 Poster

Clara Fridman

2024–present: Researcher , AI21 Labs (IL)

2022–2024: PhD student , Bar-Ilan University (IL)

2019–2021: MS student , Bar-Ilan University (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Claudio Gallicchio

2017–present: Assistant Professor , University of Pisa

2008–2011: PhD student , University of Pisa

2001–2006: MS student , University of Bari

Papers (1)

Graph Adaptive Autoregressive Moving Average Models — ICML 2025 spotlightposter

Congcong Chen

2024–present: Researcher , Microsoft GenAI (US)

Papers (1)

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation — NeurIPS 2025 poster

Congying Chu

2022–present: Associate Professor , Institute of automation, Chinese academy of science, Chinese Academy of Sciences (CN)

2010–2016: PhD student , Institute of automation, Chinese academy of science, Chinese Academy of Sciences (CN)

Papers (1)

ZeCO: Zero-Communication Overhead Sequence Parallelism for Linear Attention — NeurIPS 2025 poster

Connor Schenck

2022–present: Researcher , Google

2013–2018: PhD student , University of Washington

Papers (1)

Linear Transformer Topological Masking with Graph Random Features — ICLR 2025 Poster

Dalton Jones

2022–present: Researcher , Qualcomm Inc, QualComm

2015–2017: MS student , Massachusetts Institute of Technology

2014–2015: MS student , University of Colorado at Boulder

Papers (1)

PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer — ICLR 2025 Poster

Dan Padnos

—–present: MS student , Hebrew University of Jerusalem (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Dan Zhang

2018–present: Research Scientist , Robert Bosch GmbH, Bosch (DE)

2014–2017: Research Group Leader , Vodafone chair for mobile communications (DE)

2007–2013: Research Assistants , Chair for Integrated Signal Processing Systems (DE)

Papers (1)

Temporal Test-Time Adaptation with State-Space Models — Accepted by TMLR

Dan Zhao

2021–2025: MS student , New York University (US)

2021–2023: Researcher , Massachusetts Institute of Technology (US)

Papers (1)

Layer by Layer: Uncovering Hidden Representations in Language Models — ICML 2025 oral

Dancheng Liu

2023–present: PhD student , University at Buffalo (US)

2021–2023: MS student , University of California, San Diego

2018–2021: Undergrad student , University of California, San Diego

Papers (1)

Sub-Sequential Physics-Informed Learning with State Space Model — ICML 2025 poster

Danda Pani Paudel

2023–present: Assistant Professor , INSAIT Sofia & ETH Zurich (BG)

2016–2024: Lecturer , ETHZ - ETH Zurich (CH)

Papers (1)

StateSpaceDiffuser: Bringing Long Context to Diffusion World Models — NeurIPS 2025 poster

Dandan Ding

2020–present: Associate Professor , Hangzhou Normal University (CN)

Papers (1)

Efficient LiDAR Reflectance Compression via Scanning Serialization — ICML 2025 poster

Daniel Durstewitz

2011–present: Full Professor , Heidelberg University (GB)

2005–2008: Associate Professor (Reader) , Plymouth University (DE)

2000–2005: Junior group leader , Ruhr-University Bochum

Papers (1)

A scalable generative model for dynamical system reconstruction from neuroimaging data — NeurIPS 2024 poster

Daniel Gissin

2017–present: MS student , Hebrew University of Jerusalem

2014–2017: Undergrad student , Hebrew University of Jerusalem

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Daniel Jannai

2019–present: MS student , Hebrew University of Jerusalem

2016–2019: Undergrad student , Hebrew University of Jerusalem

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Daniel Klotz

2024–2025: Assistant Professor , International Technological University (AT)

2023–2024: Postdoc , Helmholtz Centre for Environmental Research - UFZ (DE)

2020–2023: Postdoc , Johannes Kepler University Linz (AT)

2016–2020: PhD student , Institute for Hydrology and Water Management (AT)

Papers (1)

TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning — NeurIPS 2025 poster

Daniel Korzekwa

2016–present: Researcher , Amazon

2019–2023: PhD student , Gdansk University of Technology

1998–2003: MS student , Silesian Technical University of Gliwice

Papers (1)

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning — NeurIPS 2025 poster

Daniel Shao

2024–2026: MS student , Yale University (US)

2019–2023: Undergrad student , Fudan University (CN)

Papers (1)

Revisiting Convolution Architecture in the Realm of DNA Foundation Models — ICLR 2025 Poster

Daniel Soudry

2021–present: Associate Professor , Technion - Israel Institute of Technology, Technion (IL)

2017–2021: Assistant Professor , Technion - Israel Institute of Technology (AE)

2014–2017: Postdoc , Columbia University (IL)

2008–2013: PhD student , Technion - Israel Institute of Technology

Papers (1)

Alias-Free ViT: Fractional Shift Invariance via Linear Attention — NeurIPS 2025 poster

Daniel Wuttke

2022–present: Researcher , Denigma (DE)

2009–2022: PhD student , University of Liverpool (GB)

2008–2009: MS student , Ruhr-Universtät Bochum (DE)

2005–2008: Undergrad student , Ruhr-Universtät Bochum

Papers (1)

RWKV-7 "Goose" with Expressive Dynamic State Evolution — COLM 2025

Daniela Rus

2006–2025: Full Professor , Massachusetts Institute of Technology (US)

Papers (1)

Oscillatory State-Space Models — ICLR 2025 Oral

Daniele Paliotta

2025–2025: Researcher , Cartesia AI (US)

2024–2025: Researcher , Together AI (US)

2021–2025: PhD student , University of Geneva (CH)

2018–2020: MS student , Polytechnic Institute of Turin

2015–2018: Undergrad student , University of Roma "La Sapienza"

Papers (1)

The Mamba in the Llama: Distilling and Accelerating Hybrid Models — NeurIPS 2024 poster

Daquan Zhou

2022–present: Researcher , Bytedance (US)

2018–2022: PhD student , National University of Singapore (SG)

Papers (1)

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer — ICML 2025 poster

David Atkinson

2023–present: PhD student , Northeastern University (US)

2016–2019: Undergrad student , University of Colorado at Boulder (US)

Papers (1)

Locating and Editing Factual Associations in Mamba — COLM

David Bau

2022–present: Assistant Professor , Northeastern University (US)

2021–2022: Postdoc , Harvard University (US)

2015–2021: PhD student , Massachusetts Institute of Technology (US)

2004–2015: Engineer , Google (US)

Papers (1)

Locating and Editing Factual Associations in Mamba — COLM

David Brandfonbrener

2025–present: Researcher , Meta (US)

2023–2025: Postdoc , Harvard University (US)

2018–2023: PhD student , New York University (US)

Papers (1)

Repeat After Me: Transformers are Better than State Space Models at Copying — ICML 2024 Poster

David OSOWIECHI

2022–2025: PhD student , École de technologie supérieure, Université du Québec (CA)

Papers (1)

TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses — NeurIPS 2025 poster

David Rendleman

2021–present: Researcher , Google (US)

Papers (1)

Linear Transformer Topological Masking with Graph Random Features — ICLR 2025 Poster

David W. Romero

2023–present: Researcher , NVIDIA (US)

2022–2023: Intern , Google Research (FR)

2018–2023: PhD student , Vrije Universiteit Amsterdam (NL)

2021–2021: Intern , Mitsubishi Electric Research Labs (US)

2021–2021: Intern , Qualcomm AI Research (NL)

2016–2018: MS student , TU Berlin (DE)

2010–2016: Undergrad student , Universidad Nacional de Colombia (CO)

Papers (1)

Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions — NeurIPS 2023 poster

David W. Tank

2001–present: Full Professor , Princeton University

1983–2001: Researcher , Bell Labs

1976–1983: PhD student , Cornell University

1971–1976: Undergrad student , Case Western Reserve University

Papers (1)

Modeling state-dependent communication between brain regions with switching nonlinear dynamical systems — ICLR 2024 poster

Davide Bacciu

2020–present: Full Professor , University of Pisa (IT)

2014–2020: Assistant Professor , University of Pisa (GB)

2007–2008: PhD student , Liverpool John Moores University

2005–2008: PhD student , IMT Lucca Institute for Advanced Studies

2004–2005: Researcher , Scuola Superiore Sant'Anna Pisa

2001–2002: MS student , Uppsala University

Papers (1)

Graph Adaptive Autoregressive Moving Average Models — ICML 2025 spotlightposter

Davide Scaramuzza

2012–present: Professor , University of Zurich (CH)

Papers (1)

Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theory — ICLR 2025 Poster

Davoud Ataee Tarzanagh

2024–present: AI Scientist , Samsung (US)

2022–2024: Postdoc , University of Pennsylvania

2020–2022: Postdoc , University of Michigan

2015–2020: PhD student , University of Florida

Papers (1)

Gating is Weighting: Understanding Gated Linear Attention through In-context Learning — COLM 2025

Dawei Yang

2021–present: Researcher , Houmo (CN)

2018–2022: PhD student , Fudan University (CN)

2013–2015: MS student , University of York (GB)

Papers (1)

MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods — ICLR 2025 Poster

Dayiheng Liu

2021–present: Researcher , Alibaba Group (CN)

2017–2020: PhD student , Sichuan University (CN)

Papers (1)

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free — NeurIPS 2025 oral

Dayong Ren

2023–present: Researcher , nanjing university (CN)

2018–2023: PhD student , nanjing university (CN)

Papers (1)

ZigzagPointMamba: Spatial-Semantic Mamba for Point Cloud Understanding — NeurIPS 2025 poster

De-Chuan Zhan

2019–present: Full Professor , Nanjing University (CN)

2012–2019: Associate Professor , Nanjing University (CN)

2010–2012: Assistant Professor , University of Massachusetts at Amherst (CN)

2006–2010: PhD student , Nanjing University (CN)

2004–2006: MS student , Nanjing University (CN)

Papers (1)

Leveraging Conditional Dependence for Efficient World Model Denoising — NeurIPS 2025 poster

Deepali Jain

2018–present: Researcher , Google (US)

2016–2018: Researcher , Adobe Systems

2012–2016: Undergrad student , Indian Institution Technology Roorkee

Papers (1)

Linear Transformer Topological Masking with Graph Random Features — ICLR 2025 Poster

Deheng Zhang

2025–present: PhD student , Institute for Computer Science, Artificial Intelligence and Technology (BG)

2021–2024: MS student , ETHZ - ETH Zurich (CH)

2017–2021: Undergrad student , City University of Hong Kong (DE)

Papers (1)

StateSpaceDiffuser: Bringing Long Context to Diffusion World Models — NeurIPS 2025 poster

Deividas Eringis

2020–2023: PhD student , Aalborg University

Papers (1)

PAC-Bayesian Error Bound, via Rényi Divergence, for a Class of Linear Time-Invariant State-Space Models — ICML 2024 Poster

Denis X Charles

2005–2007: Postdoc , Microsoft Research

2001–2005: PhD student , University of Wisconsin, Madison

1998–2001: MS student , State University of New York, Buffalo

Papers (1)

Efficient Hybrid Long Sequence Modeling with State Space Augmented Transformers — COLM

Di Luo

2024–present: Assistant Professor , University of California, Los Angeles (US)

2021–2024: Postdoc , Massachusetts Institute of Technology (US)

Papers (1)

L$^2$M: Mutual Information Scaling Law for Long-Context Language Modeling — NeurIPS 2025 poster

Di Wang

2021–2026: PhD student , Wuhan University (CN)

2018–2020: MS student , Wuhan University (CN)

2014–2018: Undergrad student , China University of Petroleum (CN)

Papers (1)

RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing — NeurIPS 2025 poster

Dian Cheng

2025–present: Researcher , Independent Researcher (CN)

2021–2024: MS student , nanjing university (CN)

2015–2019: Undergrad student , Tongji University (CN)

Papers (1)

Leveraging Conditional Dependence for Efficient World Model Denoising — NeurIPS 2025 poster

Difan Zou

2022–present: Assistant Professor , University of Hong Kong (HK)

2018–2022: PhD student , University of California, Los Angeles

Papers (1)

How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression? — ICLR 2024 spotlight

Dimitris N. Metaxas

2024–present: Board of Governors Professor , Rutgers University (US)

2007–present: Distinguished Professor , Rutgers University (US)

2001–present: Full Professor , Rutgers University (US)

1997–2001: Associate Professor , University of Pennsylvania (US)

1992–1997: Assistant Professor , University of Pennsylvania (US)

Papers (1)

DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation — NeurIPS 2024 poster

Dimitris Papailiopoulos

2024–present: Principal Researcher , Research, Microsoft (US)

2022–present: Associate Professor , University of Wisconsin - Madison (US)

2016–2022: Assistant Professor , University of Wisconsin, Madison (US)

2014–2016: Postdoc , University of California Berkeley (US)

2012–2014: PhD student , University of Texas, Austin (US)

2009–2012: PhD student , University of Southern California (US)

2007–2009: MS student , Technical University of Crete (GR)

2002–2009: Undergrad student , Technical University of Crete (GR)

Papers (1)

Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks — ICML 2024 Poster

DINGDING HAN

—–present: Full Professor , Fudan University (CN)

Papers (1)

FAPEX: Fractional Amplitude-Phase Expressor for Robust Cross-Subject Seizure Prediction — NeurIPS 2025 spotlight

Dingkang Liang

2022–2025: PhD student , Huazhong University of Science and Technology (CN)

2019–2022: MS student , Huazhong University of Science and Technology (CN)

Papers (1)

PointMamba: A Simple State Space Model for Point Cloud Analysis — NeurIPS 2024 poster

Disen Lan

2025–present: PhD student , Fudan University (CN)

2021–present: Undergrad student , South China University of Technology (CN)

Papers (1)

Improving Bilinear RNN with Closed-loop Control — NeurIPS 2025 spotlight

Dmitriy Morozov

2013–present: Researcher , Lawrence Berkeley National Lab (US)

2008–2010: Postdoc , Stanford University

2003–2008: PhD student , Duke University

2001–2003: Undergrad student , North Carolina State University

Papers (1)

Robustifying State-space Models for Long Sequences via Approximate Diagonalization — ICLR 2024 spotlight

Dong Li

2019–2025: Researcher , Advanced Micro Devices (CN)

2017–2019: Researcher , Megvii Technology Inc. (CN)

2012–2017: PhD student , Tsinghua University, Tsinghua University (CN)

Papers (1)

QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion — NeurIPS 2024 poster

Dong Li

2022–2025: PhD student , University of Science and Technology of China (CN)

2020–2022: MS student , University of Science and Technology of China (CN)

2016–2020: Undergrad student , Hefei University of Technology (CN)

Papers (1)

FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining — ICML 2025 poster

Dongheng Zhang

2024–present: Researcher , University of Science and Technology of China (CN)

Papers (1)

RFMamba: Frequency-Aware State Space Model for RF-Based Human-Centric Perception — ICLR 2025 Poster

Dongjun Kim

2024–2025: Postdoc , Stanford University (US)

2023–2024: Intern , Sony AI (JP)

2016–2023: PhD student , Korea Advanced Institute of Science and Technology (KR)

2010–2016: Undergrad student , Korea Advanced Institute of Science and Technology (KR)

Papers (1)

Exploring Diffusion Transformer Designs via Grafting — NeurIPS 2025 oral

Dongsheng Jiang

2017–2026: Principal Researcher , Huawei Technologies Ltd. (CN)

2012–2017: PhD student , Fudan University

Papers (1)

SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation — NeurIPS 2025 poster

Dongsheng Li

2021–present: Principal Researcher , Microsoft Research Asia (CN)

2020–2021: Senior Researcher , Microsoft Research Asia (CN)

2015–2020: Research scientist , International Business Machines (CN)

2007–2012: PhD student , Fudan University (CN)

2003–2007: Undergrad student , University of Science and Technology of China (CN)

Papers (1)

SCBench: A KV Cache-Centric Analysis of Long-Context Methods — ICLR 2025 Poster

Dongwei Lyu

2025–present: PhD student , University of California, Berkeley (US)

2024–2025: MS student , University of Chicago (US)

2020–2024: Undergrad student , Tongji University (CN)

Papers (1)

Tuning Frequency Bias of State Space Models — ICLR 2025 Spotlight

Dongyuan Li

2024–present: Assistant Professor , The University of Tokyo (JP)

2024–present: Researcher , Institute of Science Tokyo (JP)

2021–2024: PhD student , Tokyo Institute of Technology (JP)

Papers (1)

DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs — NeurIPS 2025 poster

Dor Muhlgay

2019–present: Researcher , AI21 Labs

2016–2018: MS student , Tel Aviv University

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Dor Zimberg

2020–2024: Researcher , AI 21 labs (IL)

2016–2018: Undergrad student , Open University of Israel (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Duy-Tung Pham

2024–present: Researcher , AI Center, FPT Software (VN)

2020–2024: Undergrad student , Hanoi University of Science and Technology (VN)

Papers (1)

Demystifying the Token Dynamics of Deep Selective State Space Models — ICLR 2025 Spotlight

Dániel Rácz

2020–present: Researcher , Institute for Computer Science and Control, Eötvös Loránd Research Network

2020–2024: PhD student , Eötvös Lorand University

Papers (1)

Length independent generalization bounds for deep SSM architectures via Rademacher contraction and stability constraints — Accepted by TMLR

E. Mika Diamanti

2019–present: Postdoc , Princeton University

2014–2019: PhD student , University College London, University of London

Papers (1)

Modeling state-dependent communication between brain regions with switching nonlinear dynamical systems — ICLR 2024 poster

Edden M. Gerber

2023–2024: Researcher , AI21 Labs (IL)

2011–2018: PhD student , Hebrew University of Jerusalem (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Eden Lumbroso

2022–present: MS student , Tel Aviv University

2019–2021: Undergrad student , Tel Aviv University

Papers (1)

Provable Benefits of Complex Parameterizations for Structured State Space Models — NeurIPS 2024 poster

Edo Cohen-Karlik

2018–2022: PhD student , Tel Aviv University

Papers (1)

Provable Benefits of Complex Parameterizations for Structured State Space Models — NeurIPS 2024 poster

Edward Chien

2020–present: Assistant Professor , Boston University

2017–2020: Postdoc , Massachusetts Institute of Technology

2015–2017: Postdoc , Bar Ilan University, Technion

2009–2015: PhD student , Rutgers University

2005–2009: Undergrad student , Dartmouth College

Papers (1)

Partially Observed Trajectory Inference using Optimal Transport and a Dynamics Prior — ICLR 2025 Poster

Edwin V. Bonilla

2018–present: Principal Research Scientist , CSIRO's Data61

2014–2018: Senior Lecturer , University of New South Wales

Papers (1)

Free-Form Variational Inference for Gaussian Process State-Space Models — ICML 2023 Poster

Ekdeep Singh Lubana

2025–present: Researcher , Goodfire AI (US)

2024–2026: Postdoc , Harvard University, Harvard University (US)

2019–2024: PhD student , University of Michigan (US)

2015–2019: Undergrad student , Indian Institution Technology Roorkee (IN)

Papers (1)

Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing — ICML 2025 poster

Ekin Akyürek

2019–2025: PhD student , Massachusetts Institute of Technology

Papers (1)

Learning Linear Attention in Polynomial Time — NeurIPS 2025 oral

Elad Dolev

2021–present: Instructor , AI21 Labs (IL)

2006–2012: Undergrad student , Technion - Israel Institute of Technology (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Elias Abad Rocamora

2023–2027: PhD student , EPFL - EPF Lausanne (CH)

2025–2025: Intern , Google DeepMind (CH)

2022–2023: MS student , Universidad Carlos III de Madrid (ES)

2022–2022: Undergrad student , EPFL - EPF Lausanne (CH)

2018–2022: Undergrad student , Universidad Politécnica de Cataluna (ES)

Papers (1)

Linear Attention for Efficient Bidirectional Sequence Modeling — NeurIPS 2025 poster

Elisabeth Gassiat

1998–present: Full Professor , Université Paris-Saclay (FR)

Papers (1)

Variational excess risk bound for general state space models — Accepted by TMLR

Elliot L Epstein

2021–2026: PhD student , Stanford University (US)

Papers (1)

Simple Hardware-Efficient Long Convolutions for Sequence Modeling — ICML 2023 Poster

Emiel van Loon

2017–present: Associate Professor , University of Amsterdam

2003–2017: Assistant Professor , University of Amsterdam

Papers (1)

Deep Gaussian Markov Random Fields for Graph-Structured Dynamical Systems — NeurIPS 2023 poster

Emilio Parisotto

—–present: PhD student , School of Computer Science, Carnegie Mellon University

—–present: PhD student , Department of Computer Science, University of Toronto

Papers (1)

Structured State Space Models for In-Context Reinforcement Learning — NeurIPS 2023 poster

Emir Haleva

—–present: Adjunct Lecturer , Tel Aviv University, Tel Aviv University

—–present: Researcher , Huawei Technologies Ltd.

Papers (1)

Linear Log-Normal Attention with Unbiased Concentration — ICLR 2024 poster

Enze Xu

2023–present: PhD student , College of William and Mary (US)

2021–2023: MS student , Wake Forest University (US)

Papers (1)

A Generalizable Physics-Enhanced State Space Model for Long-Term Dynamics Forecasting in Complex Environments — ICML 2025 poster

Eran Krakovsky

2020–present: MS student , Reichman University (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Eran Malach

2025–present: Researcher , Apple (US)

2023–2025: Postdoc , Harvard University (US)

2019–2023: PhD student , Hebrew University of Jerusalem, Israel

2017–2019: MS student , Hebrew University Jerusalem Israel

2013–2017: Undergrad student , Hebrew University Jerusalem Israel

Papers (1)

Repeat After Me: Transformers are Better than State Space Models at Copying — ICML 2024 Poster

Eren Manavoglu

2002–2006: PhD student , Pennsylvania State University

2000–2002: MS student , Pennsylvania State University

Papers (1)

Efficient Hybrid Long Sequence Modeling with State Space Augmented Transformers — COLM

Erez Safahi

1970–2038: Researcher , AI21 Labs (US)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Erez Schwartz

2015–2019: Undergrad student , Technion, Technion

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Eric C. Larson

2013–present: Associate Professor , Southern Methodist University, Southern Methodist University (US)

Papers (1)

On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective — Accepted by TMLR

Eric Moulines

2025–present: Full Professor , Mohamed bin Zayed University of Artificial Intelligence (AE)

2025–present: Full Professor , Ecole Pour l'Informatique et les Techniques Avancees (FR)

2015–2025: Full Professor , Ecole polytechnique (FR)

1996–2015: Full Professor , Télécom ParisTech (FR)

1990–1996: Assistant Professor , Télécom ParisTech (FR)

Papers (1)

State and parameter learning with PARIS particle Gibbs — ICML 2023 Poster

Eric Nalisnick

2024–present: Assistant Professor , Johns Hopkins University (US)

2020–2024: Assistant Professor , University of Amsterdam (NL)

2018–2020: Postdoc , University of Cambridge

2013–2018: PhD student , University of California, Irvine

2012–2013: MS student , Lehigh University

2008–2012: Undergrad student , Lehigh University

Papers (1)

Temporal Test-Time Adaptation with State-Space Models — Accepted by TMLR

Eric Volkmann

2024–present: PhD student , Johannes Kepler Universität Linz (AT)

2020–2023: MS student , Ruprecht-Karls-Universität Heidelberg (DE)

2017–2020: Undergrad student , Ruprecht-Karls-Universität Heidelberg (DE)

Papers (1)

A scalable generative model for dynamical system reconstruction from neuroimaging data — NeurIPS 2024 poster

Eshaan Nichani

2021–present: PhD student , Princeton University (US)

2020–2021: MS student , Massachusetts Institute of Technology

2016–2020: Undergrad student , Massachusetts Institute of Technology

Papers (1)

Understanding Factual Recall in Transformers via Associative Memories — ICLR 2025 Spotlight

Ethan Baron

2022–present: MS student , Tel Aviv University

2022–2024: MS student , Tel Aviv University (IL)

2019–2022: Undergrad student , Computer Science Departmen, Technion-Israel Institute of Technology

Papers (1)

A 2-Dimensional State Space Layer for Spatial Inductive Bias — ICLR 2024 poster

Ethan Steinberg

2024–present: Researcher , Stanford University (US)

2024–present: Researcher , Prealize Health (US)

2017–2024: PhD student , Stanford University (US)

2012–2017: Undergrad student , Rice University (US)

Papers (1)

Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHR Data — ICLR 2025 Poster

Eugene Cheah

2023–present: CEO / Co-Founder , Featherless AI (US)

2023–present: CEO / Co-Founder , Recursal AI (US)

2016–2023: CTO / Co-Founder , Uilicious (SG)

Papers (1)

RADLADS: Rapid Attention Distillation to Linear Attention Decoders at Scale — COLM 2025

Eva L Dyer

2025–present: Associate Professor , University of Pennsylvania, University of Pennsylvania (US)

2017–2025: Associate Professor , Georgia Institute of Technology (US)

Papers (1)

Generalizable, real-time neural decoding with hybrid state-space models — NeurIPS 2025 poster

Evgenii Nikishin

2021–present: PhD student , University of Montreal

2022–2022: Research Scientist Intern , DeepMind

2019–2020: PhD student , Cornell University

2017–2019: MS student , Higher School of Economics

Papers (1)

Forgetting Transformer: Softmax Attention with a Forget Gate — ICLR 2025 Poster

Ewa Szczurek

2024–present: Principal Researcher , Helmholtz Zentrum München (DE)

2022–present: Associate Professor , University of Warsaw (PL)

2015–2022: Assistant Professor , University of Warsaw (PL)

2012–2014: Postdoc , ETHZ - ETH Zurich

2010–2012: Postdoc , Max Planck Institut, Max-Planck Institute

Papers (1)

Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation — NeurIPS 2025 poster

Fabian Falck

2024–present: Researcher , Microsoft Research (GB)

2020–2024: PhD student , University of Oxford (GB)

2019–2020: Researcher , Carnegie Mellon University (US)

2018–2019: Researcher , Imperial College London (GB)

2017–2018: MS student , Imperial College London (GB)

2016–2017: MS student , Karlsruhe Institute of Technology (DE)

2012–2016: Undergrad student , Karlsruhe Institute of Technology (DE)

Papers (1)

Implicit Language Models are RNNs: Balancing Parallelization and Expressivity — ICML 2025 spotlightposter

Fan Jiang

2018–2024: Principal Researcher , Advanced Micro Devices (CN)

2003–2010: PhD student , Tsinghua University, Tsinghua University

1999–2003: Undergrad student , Tsinghua University, Tsinghua University

Papers (1)

QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion — NeurIPS 2024 poster

Fangjun Wang

2020–2025: Researcher , Fujitsu Research and Development Center Co. Ltm. (CN)

2017–2020: MS student , Shanghai Jiaotong University (CN)

2011–2015: Undergrad student , Beijing University of Aeronautics and Astronautics (CN)

Papers (1)

Mamba Only Glances Once (MOGO): A Lightweight Framework for Efficient Video Action Detection — NeurIPS 2025 poster

Fangxun Shu

2025–present: Researcher , ByteDance Inc. (CN)

2021–2025: Researcher , Alibaba Group (CN)

2018–2021: MS student , Shanghai Jiaotong University (CN)

Papers (1)

Autoregressive Pretraining with Mamba in Vision — ICLR 2025 Poster

Farnoush Rezaei Jafari

2021–present: PhD student , Technische Universität Berlin (DE)

2018–2021: MS student , Technische Universität Berlin (DE)

Papers (1)

MambaLRP: Explaining Selective State Space Sequence Models — NeurIPS 2024 poster

Fatih Porikli

2019–present: Senior Director , QualComm (US)

2016–2019: Vice President , Huawei Technologies Ltd. (US)

2013–2019: Full Professor , Australian National University (AU)

2000–2013: Distinguished Scientist , Mitsubishi Electric Research Labs (US)

1996–2000: PhD student , New York University (US)

Papers (1)

PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer — ICLR 2025 Poster

Federico Arangath Joseph

2022–2025: MS student , ETHZ - ETH Zurich (CH)

2019–2022: Undergrad student , Polytechnic Institute of Milan (IT)

Papers (1)

Lambda-Skip Connections: the architectural component that prevents Rank Collapse — ICLR 2025 Poster

Federico Danieli

2022–present: Researcher , Apple

2021–2022: Postdoc , University of Oxford

2016–2021: PhD student , University of Oxford

Papers (1)

Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall Capacity — ICML 2025 poster

Federico Soldà

2020–present: PhD student , ETHZ - ETH Zurich (CH)

Papers (1)

Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theory — ICLR 2025 Poster

Fei Deng

2024–present: Research Scientist , Google (US)

2022–2024: Research Intern , Google (US)

2018–2024: PhD student , Rutgers University (US)

Papers (1)

Slot State Space Models — NeurIPS 2024 poster

Fei Huang

2023–present: Researcher , Alibaba Group (CN)

2018–2023: PhD student , Department of Computer Science and Technolog, Tsinghua University (CN)

2021–2022: Intern , ByteDance AI Lab (CN)

Papers (1)

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free — NeurIPS 2025 oral

Fei Xie

2022–2026: PhD student , Shanghai Jiaotong University (CX)

2019–2022: MS student , Southeast University

Papers (1)

QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model — NeurIPS 2024 poster

Fei Yu

2021–present: Full Professor , GM Lab (CN)

Papers (1)

Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking — NeurIPS 2025 poster

Feihu Xu

2017–present: Full Professor , University of Science and Technology of China

Papers (1)

Toward Dynamic Non-Line-of-Sight Imaging with Mamba Enforced Temporal Consistency — NeurIPS 2024 poster

Felix Berkenkamp

2025–2099: Senior Research Scientist , Aleph Alpha Research (DE)

2019–2024: Research Scientist , Bosch Center for AI (DE)

2019–2019: Intern , Google (GB)

2015–2019: PhD student , Swiss Federal Institute of Technology (CH)

2015–2019: PhD student , Toronto University (CA)

2017–2017: Intern , Research, Microsoft (US)

Papers (1)

Uncertainty Representations in State-Space Layers for Deep Reinforcement Learning under Partial Observability — Accepted by TMLR

Felix Sarnthein

2024–present: PhD student , ELLIS Institute Tuebingen (DE)

2024–present: PhD student , ETH Zurich (CH)

2024–present: PhD student , Max-Planck Institute (DE)

2020–2023: MS student , ETH Zurich (CH)

Papers (1)

Fixed-Point RNNs: Interpolating from Diagonal to Dense — NeurIPS 2025 spotlight

Feng Liu

2020–present: Assistant Professor , Stevens Institute of Technology (US)

2018–2020: Researcher , Massachusetts General Hospital, Harvard University (US)

2014–2018: PhD student , University of Texas, Arlington (US)

2010–2013: MS student , Huazhong University of Science and Technology (CN)

Papers (1)

Inference of Whole Brain Electrophysiological Networks Through Multimodal Integration of Simultaneous Scalp and Intracranial EEG — NeurIPS 2025 poster

Fengbin Guan

2023–present: MS student , University of Science and Technology of China (CN)

Papers (1)

QMamba: On First Exploration of Vision Mamba for Image Quality Assessment — ICML 2025 poster

Fengxiang Wang

2023–present: PhD student , National University of Defense Technology (CN)

Papers (1)

RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing — NeurIPS 2025 poster

Ferenc Huszár

2020–present: Associate Professor , University of Cambridge

2016–2020: Senior Machine Learning Researcher , Twitter

2015–2016: Principal Research Scientist , Magic Pony Technology

2009–2012: PhD student , University of Cambridge

Papers (1)

Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD Prompts — NeurIPS 2024 spotlight

Fernando De la Torre

2003–present: Associate Professor , School of Computer Science, Carnegie Mellon University (US)

Papers (1)

Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba — NeurIPS 2024 poster

Feryal Behbahani

2019–present: Research Scientist , DeepMind

2017–2019: Latent Logic , Latent Logic

2016–2017: Postdoc , Imperial College London

2012–2016: PhD student , Imperial College London

2010–2011: MS student , Imperial College London

Papers (1)

Structured State Space Models for In-Context Reinforcement Learning — NeurIPS 2023 poster

Filip Tronarp

2023–present: Assistant Professor , Lund University (SE)

2020–2023: Postdoc , University of Tuebingen (DE)

2016–2020: PhD student , Aalto University (FI)

Papers (1)

The Rank-Reduced Kalman Filter: Approximate Dynamical-Low-Rank Filtering In High Dimensions — NeurIPS 2023 poster

Fiona Lippert

2020–2024: PhD student , University of Amsterdam

Papers (1)

Deep Gaussian Markov Random Fields for Graph-Structured Dynamical Systems — NeurIPS 2023 poster

Firas Laakom

2024–present: Postdoc , King Abdullah University of Science and Technology (SA)

2019–2024: PhD student , Tampere University (FI)

Papers (1)

FACTS: A Factored State-Space Framework for World Modelling — ICLR 2025 Poster

Francesco Tonin

2024–present: Postdoc , EPFL - EPF Lausanne (CH)

2019–2023: PhD student , KU Leuven

Papers (1)

Linear Attention for Efficient Bidirectional Sequence Modeling — NeurIPS 2025 poster

Francisco Vicente Carrasco

2023–present: Researcher , CMU, Carnegie Mellon University (US)

2021–2023: Researcher , Epic Games (US)

2017–2021: Researcher , Facebook (US)

2013–2015: MS student , Carnegie Mellon University (US)

2007–2008: MS student , Universidad Politécnica de Cartagena (ES)

2002–2007: Undergrad student , Universidad Politécnica de Cartagena (ES)

Papers (1)

Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba — NeurIPS 2024 poster

Francois-Xavier Briol

2025–present: Full Professor , University College London, University of London (GB)

2023–2025: Associate Professor , University College London, University of London (GB)

2019–2023: Researcher , Alan Turing Institute (GB)

2019–2023: Assistant Professor , University College London (GB)

2018–2019: Postdoc , Imperial College London (GB)

2018–2019: Postdoc , University of Cambridge (GB)

2014–2019: PhD student , The university of Warwick (GB)

Papers (1)

Outlier-robust Kalman Filtering through Generalised Bayes — ICML 2024 Poster

Franz Nowak

2024–present: PhD student , ETHZ - ETH Zurich

2021–2023: MS student , ETHZ - ETH Zurich

2016–2019: Undergrad student , University of Cambridge

Papers (1)

Bridging Expressivity and Scalability with Adaptive Unitary SSMs — NeurIPS 2025 poster

Freda Shi

2024–present: Faculty Member , Vector Institute (CA)

2024–present: Assistant Professor , University of Waterloo (CA)

2024–2024: Visiting Student , Massachusetts Institute of Technology (US)

2018–2024: PhD student , Toyota Technological Institute at Chicago (US)

2013–2018: Undergraduate Student , Peking University

Papers (1)

Gated Slot Attention for Efficient Linear-Time Sequence Modeling — NeurIPS 2024 poster

Frederic Sala

2021–present: Assistant Professor , University of Wisconsin, Madison (US)

2017–2020: Postdoc , Stanford University (US)

2011–2016: PhD student , University of California, Los Angeles (US)

Papers (1)

Pretrained Hybrids with MAD Skills — COLM 2025

Fuchun Sun

2003–present: Full Professor , Tsinghua University (CN)

Papers (1)

Slimming the Fat-Tail: Morphing-Flow for Adaptive Time Series Modeling — ICML 2025 poster

Gabriel Cardoso

2024–present: Assistant Professor , Mines ParisTech (FR)

2021–2024: PhD student , École Polytechnique (FR)

Papers (1)

State and parameter learning with PARIS particle Gibbs — ICML 2023 Poster

Gabriel Mongaras

2021–2025: Undergrad student , Southern Methodist University, Southern Methodist University (US)

Papers (1)

On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective — Accepted by TMLR

Gal Cohen

2022–2025: MS student , Bar-Ilan University (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Gal Fadlon

2023–2025: MS student , Ben-Gurion University of the Negev

Papers (1)

Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series — NeurIPS 2024 poster

Gal Shachaf

2019–present: MS student , Tel Aviv University (IL)

2014–2019: Undergrad student , Technion (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Gang Hua

2025–present: Director of Applied Science , Amazon (US)

2024–2025: Vice President , Dolby (US)

2018–2024: Chief Scientist and Managing Director , Wormpex AI Research (US)

2015–2018: Senior Principal Researcher/Research Manager , Microsoft Research

2014–2015: Senior Research Scientist , Amazon

2011–2015: Associate Professor , Stevens Institute of Technology

2010–2011: Research Staff Member , IBM T. J. Watson Research Center

2009–2010: Senior Researcher , Nokia Research Center Hollywood

2006–2009: Researcher , Microsoft Live Labs Research

2002–2006: PhD student , Northwestern University

1999–2002: MS student , Xi'an Jiaotong University

1994–1999: Undergrad student , Xi'an Jiaotong University

Papers (1)

State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding — NeurIPS 2025 poster

Gang Wang

2020–2024: Professor , Beijing Institute of Technology (CN)

2015–2018: PhD student , University of Minnesota, Minneapolis

2015–2018: PhD student/postdoc , University of Minnesota, Minneapolis

2015–2018: PhD student , University of Minnesota - Twin Cities

2015–2018: PhD student , University of Minnesota - Twin Cities (US)

2011–2018: PhD student , Beijing Institute of Technology

2007–2015: Student , Beijing Institute of Technology

Papers (1)

DyMoDreamer: World Modeling with Dynamic Modulation — NeurIPS 2025 poster

Gaojie Jin

2024–present: Assistant Professor , University of Exeter (GB)

2023–2024: Associate Professor , Chinese Academy of Sciences, Chinese Academy of Sciences (CN)

2019–2023: PhD student , University of Liverpool

Papers (1)

Toward Linearly Regularizing the Geometric Bottleneck of Linear Generalized Attention — Accepted by TMLR

Gaole Dai

2022–2027: PhD student , Peking University (CN)

2018–2022: Undergrad student , University of Toronto, Mississauga (CA)

Papers (1)

Orochi: Versatile Biomedical Image Processor — NeurIPS 2025 spotlight

Gautam Singh

2025–present: Postdoctoral Researcher , Lawrence Livermore National Labs (US)

2023–2024: Research Intern , NVIDIA (US)

2018–2024: PhD student , Rutgers University (US)

2021–2021: Applied Science Intern , Amazon (US)

2015–2018: Research Scientist , IBM Research India (IN)

2011–2015: Undergrad student , Indian Institute of Technology Guwahati (IN)

Papers (1)

Slot State Space Models — NeurIPS 2024 poster

Ge Meng

2021–2025: PhD student , Xiamen University (CN)

2018–2021: MS student , Xiamen University (CN)

Papers (1)

FRN: Fractal-Based Recursive Spectral Reconstruction Network — NeurIPS 2025 poster

Ge Yang

2019–present: Full Professor , National Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of sciences (CN)

2014–2019: Associate Professor , Carnegie Mellon University (US)

2009–2014: Assistant Professor , Carnegie Mellon University (US)

Papers (1)

Dual-Res Tandem Mamba-3D: Bilateral Breast Lesion Detection and Classification on Non-contrast Chest CT — NeurIPS 2025 poster

Genghan Zhang

2023–present: PhD student , Stanford University (US)

2024–2024: Intern , NVIDIA (US)

2023–2023: Researcher , Infinigence

2019–2023: Undergrad student , Electronic Engineering, Tsinghua University, Tsinghua University

Papers (1)

Learning to (Learn at Test Time): RNNs with Expressive Hidden States — ICML 2025 spotlightposter

Genta Suzuki

2005–present: Researcher , Fujitsu Limited (JP)

2003–2005: MS student , Keio University (JP)

Papers (1)

Mamba Only Glances Once (MOGO): A Lightweight Framework for Efficient Video Action Detection — NeurIPS 2025 poster

Geon-Hyeong Kim

2022–present: Researcher , LG AI Research (KR)

2015–2022: PhD student , Korea Advanced Institute of Science and Technology (KR)

2013–2015: MS student , Korea Advanced Institute of Science and Technology (KR)

2009–2013: Undergrad student , Korea Advanced Institute of Science & Technology (KR)

Papers (1)

Information-Theoretic State Space Model for Multi-View Reinforcement Learning — ICML 2023 OralPoster

George Karypis

—–present: Full Professor , University of Minnesota, Minneapolis

Papers (1)

LC-PLM: Long-context Protein Language Modeling Using Bidirectional Mamba with Shared Projection Layers — Accepted by TMLR

Georgia Koppe

2024–present: Full Professor , Heidelberg University, Ruprecht-Karls-Universität Heidelberg (DE)

2018–present: Principal Researcher , Central Institute of Mental Health (DE)

2015–2018: Postdoc , Central Institute of Mental Health (DE)

Papers (1)

A scalable generative model for dynamical system reconstruction from neuroimaging data — NeurIPS 2024 poster

Gerardo Duran-Martin

2025–2028: Postdoc , University of Oxford (GB)

2022–2025: PhD student , Queen Mary University (GB)

Papers (1)

Outlier-robust Kalman Filtering through Generalised Bayes — ICML 2024 Poster

Gerhard Neumann

2020–present: Full Professor , Karlsruhe Institute of Technology (DE)

2016–2019: Full Professor , University of Lincoln

2014–2016: Assistant Professor , TU Darmstadt

2005–2012: PhD student , TU Graz

Papers (1)

On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning — Accepted by TMLR

Gil Sadeh

2016–present: Researcher , Amazon (IL)

Papers (1)

LC-PLM: Long-context Protein Language Modeling Using Bidirectional Mamba with Shared Projection Layers — Accepted by TMLR

Gilad Adler

2004–2007: MS student , Technion - Israel Institute of Technology, Technion

1993–1997: Undergrad student , Electrical Engineering Department, Technion – Israel Institute of Technology, Technion - Israel Institute of Technology

Papers (1)

MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning — ICLR 2024 poster

Giorgio Giannone

2025–present: Researcher , Red Hat AI (US)

2024–2025: Researcher , Amazon (US)

2023–2023: PhD student , Massachusetts Institute of Technology

2020–2023: PhD student , Technical University of Denmark

2016–2018: MS student , Sapienza University of Rome

Papers (1)

Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling — NeurIPS 2024 poster

Gizem Mert

2024–present: Researcher , Helmholtz Zentrum München (DE)

2021–2025: MS student , University of Trento (IT)

Papers (1)

Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation — NeurIPS 2025 poster

Gongwei Chen

2023–2025: Postdoc , Harbin Institute of Technology (CN)

2016–2023: PhD student , Institute of Computing Technology, Chinese Academy of Sciences (CN)

Papers (1)

Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL — NeurIPS 2024 poster

Gregor Bachmann

2020–2024: PhD student , Swiss Federal Institute of Technology (CH)

Papers (1)

The Pitfalls of Next-Token Prediction — ICML 2024 Poster

Grégoire Montavon

2025–present: Full Professor , Charité - Universitätsmedizin Berlin (DE)

2022–2025: Lecturer , Freie Universität Berlin (DE)

Papers (1)

MambaLRP: Explaining Selective State Space Sequence Models — NeurIPS 2024 poster

Guangyu Song

2024–present: Researcher , Tano Labs (CA)

2013–2018: Undergrad student , Queen's University (CA)

Papers (1)

RWKV-7 "Goose" with Expressive Dynamic State Evolution — COLM 2025

Guanzhong Tian

2021–present: Assistant Professor , Ningbo Innovation Center, Zhejiang University. (CN)

Papers (1)

MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection — NeurIPS 2024 poster

Guihong Li

2024–present: Researcher , Advanced Micro Devices (US)

2019–2024: PhD student , University of Texas, Austin (US)

2018–2019: MS student , Tsinghua University, Tsinghua University

2014–2018: Undergrad student , Beijing University of Posts and Telecommunications

Papers (1)

Zebra-Llama: Towards Extremely Efficient Hybrid Models — NeurIPS 2025 poster

Guillaume Lajoie

2018–present: Associate Professor , Mila - Quebec Artificial Intelligence Institute (US)

2015–2017: Postdoc , University of Washington (DE)

2014–2015: Postdoc , Max Planck Inst. for Dynamics and Self-Organization (US)

2008–2013: PhD student , University of Washington

Papers (1)

Generalizable, real-time neural decoding with hybrid state-space models — NeurIPS 2025 poster

Guillaume Pourcel

2024–2025: Intern , INRIA (FR)

2019–2025: PhD student , University of Groningen (NL)

2024–2024: Intern , INRIA (FR)

Papers (1)

Learning long range dependencies through time reversal symmetry breaking — NeurIPS 2025 oral

Guodong Li

2021–2033: Professor , The University of Hong Kong (HK)

Papers (1)

From Layers to States: A State Space Model Perspective to Deep Neural Network Layer Dynamics — ICLR 2025 Poster

Guohao Dai

2022–present: Associate Professor , Shanghai Jiaotong University (CN)

2023–2023: Principal Researcher , Infinigence

2019–2022: Postdoc , Tsinghua University, Tsinghua University

2014–2019: PhD student , Tsinghua University, Tsinghua University

2014–2019: PhD student , Electronic Engineering, Tsinghua University, Tsinghua University

2010–2014: Undergrad student , Tsinghua University, Tsinghua University

Papers (1)

Evaluating Quantized Large Language Models — ICML 2024 Poster

Guohong Fu

2019–present: Full Professor , Soochow University, China, (CN)

2007–2019: Full Professor , Heilongjiang University (CN)

2006–2007: Research Fellow , City University of Hong Kong (CN)

2003–2006: Honorary Assistant Professor , The University of Hong Kong (CN)

2002–2005: Postdoc , The University of Hong Kong (CN)

1997–2001: PhD student , Computer Science, Harbin Institute of Technology (CN)

1990–1993: MS student , Mechanical Design, Harbin Institute of Technology (CN)

1986–1990: Undergrad student , Automobile Design, Harbin Institute of Technology (CN)

Papers (1)

Gated Slot Attention for Efficient Linear-Time Sequence Modeling — NeurIPS 2024 poster

Guosheng Lin

2023–present: Associate Professor , Nanyang Technological University (SG)

2017–2023: Assistant Professor , Nanyang Technological University (SG)

2014–2017: Postdoc , The University of Adelaide (AU)

2010–2014: PhD student , The University of Adelaide (AU)

Papers (1)

Hybrid Mamba for Few-Shot Segmentation — NeurIPS 2024 poster

Guowen Zhang

2022–present: PhD student , Hong Kong Polytechnic University (HK)

2019–2022: MS student , Dalian University of Technology (CN)

2015–2019: Undergrad student , Dalian University of Technology (CN)

Papers (1)

Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection — NeurIPS 2024 spotlight

Guozhen Zhang

2024–present: Intern , Tencent Hunyuan (CN)

2023–present: PhD student , Nanjing University (CN)

2023–2024: Intern , Platform & Content Group (CN)

2021–2023: MS student , Nanjing University (CN)

2019–2022: Intern , Harbin Institute of Technology

Papers (1)

VFIMamba: Video Frame Interpolation with State Space Models — NeurIPS 2024 poster

Gustavo Adolfo Vargas Hakim

2021–2025: PhD student , École de technologie supérieure, Université du Québec (CA)

Papers (1)

TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses — NeurIPS 2025 poster

Hagay Michaeli

2021–present: PhD student , Technion - Israel Institute of Technology, Technion - Israel Institute of Technology (IL)

2017–2021: Undergrad student , Technion - Israel Institute of Technology, Technion - Israel Institute of Technology

Papers (1)

Alias-Free ViT: Fractional Shift Invariance via Linear Attention — NeurIPS 2025 poster

Haijin Zeng

2025–present: Postdoc , Harvard University (US)

2021–2025: PhD student , IMEC & Universiteit Gent (BE)

Papers (1)

MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging — NeurIPS 2024 poster

Haim Rozenblum

2022–present: Researcher , AI21 Labs (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Hainuo Wang

2024–2029: PhD student , Tianjin University (CN)

Papers (1)

MODEM: A Morton-Order Degradation Estimation Mechanism for Adverse Weather Image Recovery — NeurIPS 2025 poster

Haixu Wu

2020–2025: PhD student , Tsinghua University, Tsinghua University (CN)

2016–2020: Undergrad student , Tsinghua University, Tsinghua University (CN)

Papers (1)

Mobile Attention: Mobile-Friendly Linear-Attention for Vision Transformers — ICML 2024 Poster

Haiyan Zhao

2024–present: Researcher , Tsinghua University (CN)

Papers (1)

RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing — NeurIPS 2025 poster

Hajime Asama

1984–1986: PhD student , The University of Tokyo

1982–1984: MS student , The University of Tokyo

1978–1982: Undergrad student , The University of Tokyo

Papers (1)

State-Free Inference of State-Space Models: The *Transfer Function* Approach — ICML 2024 Poster

Hamidreza Hashempoor

2023–present: Researcher , Independent Researcher (KR)

2020–2023: MS student , Seoul National University

Papers (1)

Gated Inference Network: Inference and Learning State-Space Models — NeurIPS 2024 poster

Han Zhou

2022–present: PhD student , McMaster University (CA)

Papers (1)

ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correction — NeurIPS 2024 poster

Hang Guo

2023–2026: MS student , Tsinghua University (CN)

2019–2023: Undergrad student , Nankai University (CN)

Papers (1)

LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling — NeurIPS 2024 poster

Hang Yu

2020–present: Senior Algorithm Expert , Ant Group (CN)

2015–2020: Senior Research Fellow , Nanyang Technological University (SG)

Papers (1)

Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions — ICLR 2025 Poster

Hang Zhou

2021–2025: PhD student , Huazhong University of Science and Technology (CN)

Papers (1)

Coupled Mamba: Enhanced Multimodal Fusion with Coupled State Space Model — NeurIPS 2024 poster

Hanqin Gong

2022–2027: PhD student , University of Science and Technology of China (CN)

Papers (1)

RFMamba: Frequency-Aware State Space Model for RF-Based Human-Centric Perception — ICLR 2025 Poster

Hantao Yu

2022–present: PhD student , Columbia University (US)

2018–2022: Undergrad student , University of California, San Diego (US)

Papers (1)

Fundamental Limitations on Subquadratic Alternatives to Transformers — ICLR 2025 Poster

Hanting Chen

2022–present: Researcher , Huawei Technologies Ltd. (CN)

2017–2022: PhD student , Peking University (CN)

Papers (1)

DiJiang: Efficient Large Language Models through Compact Kernelization — ICML 2024 Oral

Hanwang Zhang

2023–2025: Associate Professor , Nanyang Technological University (SG)

Papers (1)

MVGamba: Unify 3D Content Generation as State Space Sequence Modeling — NeurIPS 2024 poster

Hao Chen

2022–present: Assistant Professor , Zhejiang University (CN)

2020–2021: Researcher , Huawei Technologies Ltd. (CN)

2017–2020: PhD student , The University of Adelaide (AU)

Papers (1)

Revisiting Convolution Architecture in the Realm of DNA Foundation Models — ICLR 2025 Poster

Hao Cheng

2020–present: Researcher , Microsoft Research (US)

2014–2019: PhD student , University of Washington, Seattle (US)

Papers (1)

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation — NeurIPS 2025 poster

Hao Phung

2024–present: PhD student , Cornell University (US)

2021–2024: Intern , VinAI Research (VN)

2016–2020: Undergrad student , Ho Chi Minh city University of Science, Vietnam National University (VN)

Papers (1)

DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation — NeurIPS 2024 poster

Hao Zhang

2023–present: Assistant Professor , University of California, San Diego (US)

2023–present: Researcher , Snowflake (US)

2016–present: Research Scientist , Petuum, Inc (US)

2014–present: PhD student , Carnegie Mellon University (US)

2021–2023: Postdoc , University of California, Berkeley (US)

2011–2014: MS student , Shanghai Jiao Tong University (CN)

Papers (1)

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length — NeurIPS 2024 poster

Hao Zheng

2022–present: Researcher , Tencent (CN)

2016–2022: PhD student , Shanghai Jiaotong University (CN)

Papers (1)

Samba: Severity-aware Recurrent Modeling for Cross-domain Medical Image Grading — NeurIPS 2024 poster

Hao Zou

2018–present: PhD student , Tsinghua University, Tsinghua University (CN)

2013–2018: Undergrad student , Tsinghua University, Tsinghua University (CN)

Papers (1)

Effective and Efficient Time-Varying Counterfactual Prediction with State-Space Models — ICLR 2025 Poster

Haoang Chi

2025–present: Assistant Professor , National University of Defense Technology (CN)

2025–present: Postdoc , Tsinghua University (CN)

2019–2025: PhD student , National University of Defense Technology (CN)

2015–2019: Undergrad student , Nanjing University (CN)

Papers (1)

Effective and Efficient Time-Varying Counterfactual Prediction with State-Space Models — ICLR 2025 Poster

Haochen Qin

2022–2024: Researcher , Huawei Technologies Ltd. (CN)

2021–2022: MS student , University of Edinburgh, University of Edinburgh (GB)

2019–2020: Undergrad student , University of Waterloo (CA)

2016–2020: Undergrad student , Southwest University of Finance and Economics (CN)

Papers (1)

MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected Layers — NeurIPS 2024 poster

Haochen Yu

2022–2027: PhD student , University of Science and Technology Beijing (CN)

Papers (1)

MVSMamba: Multi-View Stereo with State Space Model — NeurIPS 2025 poster

Haohong Lin

2021–present: PhD student , Carnegie Mellon University (CN)

2017–2021: Undergrad student , Zhejiang University

Papers (1)

A Generalizable Physics-Enhanced State Space Model for Long-Term Dynamics Forecasting in Complex Environments — ICML 2025 poster

Haolan Zhan

2021–present: PhD student , Monash University (AU)

2017–2020: MS student , Institute of Software, Chinese Academy of Sciences

2013–2017: Undergrad student , Wuhan University

Papers (1)

Samba: Severity-aware Recurrent Modeling for Cross-domain Medical Image Grading — NeurIPS 2024 poster

Haoliang Li

2021–present: Assistant Professor , City University of Hong Kong (HK)

2014–2018: PhD student , Nanyang Technological University (SG)

Papers (1)

Log Neural Controlled Differential Equations: The Lie Brackets Make A Difference — ICML 2024 Poster

Haonan Han

2022–2027: PhD student , Tsinghua University, Tsinghua University (CN)

2018–2022: Undergrad student , Harbin Institute of Technology (CN)

Papers (1)

MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models — NeurIPS 2024 poster

Haonan Li

2025–2025: Researcher , Mohamed bin Zayed University of Artificial Intelligence (AE)

2023–2025: Postdoc , Mohamed bin Zayed University of Artificial Intelligence (AE)

2018–2022: PhD student , University of Melbourne (AU)

2013–2017: Undergrad student , Shanghai Jiaotong University (CN)

Papers (1)

Bi-Mamba: Towards Accurate 1-Bit State Space Model — Accepted by TMLR

Haoqin Tu

2024–present: PhD student , University of California, Santa Cruz (US)

2021–2024: MS student , University of Chinese Academy of Sciences (CN)

Papers (1)

Autoregressive Pretraining with Mamba in Vision — ICLR 2025 Poster

Haoran Xu

2024–present: Researcher , Microsoft (US)

2021–2024: PhD student , Johns Hopkins University (US)

Papers (1)

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation — NeurIPS 2025 poster

Haoran You

2025–present: Researcher , Adobe Systems (US)

2022–2025: PhD student , Georgia Institute of Technology (US)

2019–2022: PhD student , Rice University (US)

Papers (1)

When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models — ICML 2024 Poster

Haotian Tang

2025–present: Research Scientist , Google DeepMind (US)

2020–2025: PhD student , Massachusetts Institute of Technology (US)

2024–2024: Intern , NVIDIA (US)

2023–2023: Intern , Waymo Research (US)

2023–2023: Intern , Alphabet Inc. (US)

2022–2022: Intern , OmniML (US)

2016–2020: Undergrad student , Shanghai Jiao Tong University (CN)

2019–2019: Intern , Tencent Youtu Lab (CN)

Papers (1)

SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers — ICLR 2025 Oral

Haowen Hou

2023–present: Assistant Professor , Shenzhen University (CN)

2017–2022: Senior AI Engineer , Tencent (CN)

2013–2017: Ph.D. Student , National University of Singapore (SG)

Papers (1)

RWKV-7 "Goose" with Expressive Dynamic State Evolution — COLM 2025

Haoxin Wang

2022–present: Assistant Professor , Georgia State University (US)

2020–2022: Researcher , Toyota Motor Corporation (US)

Papers (1)

MamBEV: Enabling State Space Models to Learn Birds-Eye-View Representations — ICLR 2025 Poster

Haoxing Chen

2022–present: Researcher , Ant Research Institute (CN)

2020–2023: MS student , Nanjing University (CN)

2016–2020: Undergrad student , Southeast University (CN)

Papers (1)

Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training — ICML 2025 poster

Haoxuan Li

2025–2026: Researcher , Peking University (CN)

2021–2025: PhD student , Peking University (CN)

Papers (1)

Effective and Efficient Time-Varying Counterfactual Prediction with State-Space Models — ICLR 2025 Poster

Haoyang He

2022–2027: PhD student , Zhejiang University (CN)

Papers (1)

MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection — NeurIPS 2024 poster

Haoye Dong

2024–2026: Senior Research Fellow , National University of Singapore (SG)

2022–2024: Postdoc , Carnegie Mellon University (US)

2020–2022: Senior Researcher , HUYA Inc.

2016–2019: PhD student , Sun Yat-sen University (CN)

Papers (1)

Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba — NeurIPS 2024 poster

Harold Soh

2017–present: Assistant Professor , National University of Singapore

2015–2017: Postdoc , University of Toronto

2014–2015: Postdoc , Massachusetts Institute of Technology

2009–2013: PhD student , Imperial College London

Papers (1)

Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series — ICML 2023 OralPoster

Harry Jake Cunningham

2021–2025: PhD student , University College London, University of London (GB)

2020–2021: MS student , Imperial College London (GB)

Papers (1)

Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling — NeurIPS 2024 poster

Haruhiko Kishima

2017–2024: Full Professor , Graduate School of Medicine, Osaka University

Papers (1)

EvoBrain: Dynamic Multi-Channel EEG Graph Modeling for Time-Evolving Brain Networks — NeurIPS 2025 spotlight

Hava T Siegelmann

2012–present: Full Professor , University of Massachusetts at Amherst

Papers (1)

Bridging Expressivity and Scalability with Adaptive Unitary SSMs — NeurIPS 2025 poster

Hechang Chen

2021–2026: Associate Professor , Jilin University (CN)

2018–2021: Assistant Professor , Jilin University (CN)

Papers (1)

Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling — NeurIPS 2024 poster

Heiner Kremer

2024–present: Researcher , Microsoft (GB)

2019–2024: PhD student , Max Planck Institute for Intelligent Systems, Max-Planck Institute (DE)

Papers (1)

Implicit Language Models are RNNs: Balancing Parallelization and Expressivity — ICML 2025 spotlightposter

Heinz Koeppl

2014–2035: Full Professor , TU Darmstadt

Papers (1)

Graph Structure Inference with BAM: Neural Dependency Processing via Bilinear Attention — NeurIPS 2024 poster

Heng Wang

2024–present: research scientist , NVIDIA (US)

2021–2024: research scientist , Bytedance (US)

2017–2021: research scientist , Facebook

2014–2017: research scientist , Amazon

2009–2014: Research Scientist , INRIA

Papers (1)

Autoregressive Pretraining with Mamba in Vision — ICLR 2025 Poster

Hengheng Gong

2019–present: PhD student , Beijing Institute of Technology

2015–2019: Undergrad student , Beijing Institute of Technology

Papers (1)

Probabilistic Time Series Modeling with Decomposable Denoising Diffusion Model — ICML 2024 Poster

Hengshuang Zhao

2021–present: Assistant Professor , The University of Hong Kong (HK)

2021–2022: Postdoc , Massachusetts Institute of Technology (US)

2020–2021: Postdoc , University of Oxford (GB)

2015–2019: PhD student , The Chinese University of Hong Kong (HK)

2011–2015: Undergrad student , Huazhong University of Science and Technology (CN)

Papers (1)

LION: Linear Group RNN for 3D Object Detection in Point Clouds — NeurIPS 2024 poster

Herve Lombaert

2024–present: Associate Professor , Polytechnique Montreal (CA)

2017–present: Associate Professor , ETS Montreal (CA)

2016–2017: Assistant Professor , Inria (FR)

2013–2016: Postdoc , Inria (FR)

2013–2015: Postdoc , Microsoft Research (GB)

2012–2013: Postdoc , McGill University (CA)

2008–2012: PhD student , Polytechnique Montreal (CA)

2007–2012: PhD , Polytechnique Montreal (CA)

Papers (1)

TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses — NeurIPS 2025 poster

Hidenori Tanaka

2022–present: Researcher , Harvard University, Harvard University (US)

2019–present: Senior Research Scientist , Physics & Informatics Lab, NTT Research, Inc. (US)

2018–2019: Postdoctoral Fellow , Stanford University

2014–2018: PhD student , Harvard University

2010–2014: Undergrad student , Kyoto University

Papers (1)

Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing — ICML 2025 poster

Hilal AlQuabeh

2024–present: Postdoc , Mohamed bin Zayed University of Artificial Intelligence (AE)

2021–2024: PhD student , Mohamed bin Zayed University of Artificial Intelligence (AE)

2016–2018: MS student , Masdar University Of Science And Technology (AE)

2011–2015: Undergrad student , Tafila Technical University (JO)

Papers (1)

Uncovering the Spectral Bias in Diagonal State Space Models — NeurIPS 2025 poster

Hitesh Ballani

2009–present: Researcher , Research, Microsoft (GB)

2003–2009: PhD student , Cornell University (US)

Papers (1)

Implicit Language Models are RNNs: Balancing Parallelization and Expressivity — ICML 2025 spotlightposter

Hoang Phan

2023–2028: PhD student , New York University (US)

2018–2022: Undergrad student , Hanoi University of Science and Technology (VN)

Papers (1)

DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation — NeurIPS 2024 poster

Hofit Bata

2021–present: Researcher , AI21 Labs (IL)

2017–2021: Researcher , Mobileye (IL)

2018–2020: MS student , , Hebrew University of Jerusalem (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Hong Cai

2020–present: Researcher , Qualcomm AI Research (US)

2015–2020: PhD student , UC Santa Barbara (US)

2013–2015: MS student , UC Santa Barbara (US)

2009–2013: Undergrad student , The Hong Kong University of Science and Technology (HK)

Papers (1)

PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer — ICLR 2025 Poster

Hongbin Xu

2025–present: Researcher , ByteDance Inc. (CN)

2021–2025: PhD student , South China University of Technology (CN)

2020–2021: Intern , Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Chinese Academy of Sciences (CN)

2018–2021: MS student , South China University of Technology (CN)

Papers (1)

Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking — NeurIPS 2025 poster

Hongjuan Pei

2024–2026: Postdoc , University of the Chinese Academy of Sciences (CN)

2015–2023: PhD student , Communication University of China (CN)

2011–2013: MS student , Beijing University of Posts and Telecommunications (CN)

Papers (1)

DAMamba: Vision State Space Model with Dynamic Adaptive Scan — NeurIPS 2025 poster

Hongjue Zhao

2024–present: PhD student , University of Illinois at Urbana-Champaign (US)

2019–2023: Undergrad student , Zhejiang University (CN)

Papers (1)

A Generalizable Physics-Enhanced State Space Model for Long-Term Dynamics Forecasting in Complex Environments — ICML 2025 poster

Hongkai Li

2022–2026: Undergrad student , Beijing Jiaotong University (CN)

Papers (1)

A Multimodal BiMamba Network with Test-Time Adaptation for Emotion Recognition Based on Physiological Signals — NeurIPS 2025 poster

Hongkang Li

2025–present: Postdoc , University of Pennsylvania, University of Pennsylvania (US)

2019–2024: PhD student , Rensselaer Polytechnic Institute (US)

2015–2019: Undergrad student , University of Science and Technology of China (CN)

Papers (1)

Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis — ICLR 2025 Poster

Hongsheng Li

2022–present: Associate Professor , The Chinese University of Hong Kong (CN)

2018–2022: Assistant Professor , The Chinese University of Hong Kong (CN)

2015–2018: Research Assistant Professor , The Chinese University of Hong Kong (CN)

2013–2015: Associate Professor , University of Electronic Science and Technology of China (CN)

Papers (1)

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures — ICLR 2025 Spotlight

Hongshu Guo

2022–2026: PhD student , South China University of Technology (CN)

Papers (1)

Meta-Black-Box-Optimization through Offline Q-function Learning — ICML 2025 poster

Hongtian Yu

2024–2027: PhD student , University of the Chinese Academy of Sciences (CN)

2021–2024: MS student , University of the Chinese Academy of Sciences (CN)

2017–2021: Undergrad student , University of the Chinese Academy of Sciences (CN)

Papers (1)

VMamba: Visual State Space Model — NeurIPS 2024 spotlight

Hongxu Chen

2022–2025: MS student , Zhejiang University (CN)

Papers (1)

MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection — NeurIPS 2024 poster

Hongyan Liu

2011–present: Full Professor , Tsinghua University, Tsinghua University (CN)

2003–2011: Associate Professor , Tsinghua University (CN)

2001–2003: Assistant Professor , Tsinghua University (CN)

1997–2001: PhD student , Tsinghua University, Tsinghua University (CN)

Papers (1)

MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation — NeurIPS 2025 poster

Hongyu Ke

2023–2025: PhD student , Georgia State University (US)

2022–2023: MS student , State University of New York at Buffalo (US)

2018–2022: Undergrad student , State University of New York at Stony Brook (US)

Papers (1)

MamBEV: Enabling State Space Models to Learn Birds-Eye-View Representations — ICLR 2025 Poster

Hongyu Zang

2024–2025: Researcher , Meituan (CN)

Papers (1)

Learning Latent Dynamic Robust Representations for World Models — ICML 2024 Poster

Hongyuan Liu

2023–present: PhD student , University of Science and Technology Beijing (CN)

2019–2023: Undergrad student , University of Science and Technology Beijing (CN)

Papers (1)

MVSMamba: Multi-View Stereo with State Space Model — NeurIPS 2025 poster

Hongzhen Wang

2023–present: Researcher , Tsinghua University, Tsinghua University (CN)

2018–2021: Researcher , Tencent AI Lab (CN)

2013–2018: PhD student , , Institute of automation, Chinese academy of science (CN)

Papers (1)

RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing — NeurIPS 2025 poster

Hossein Babaei

2019–2025: PhD student , Rice university (US)

Papers (1)

WaLRUS: Wavelets for Long range Representation Using State Space Methods — NeurIPS 2025 poster

Hossein Farahani

2024–present: Lecturer , University of British Columbia (CA)

2019–2024: Researcher , University of British Columbia (CA)

2008–2013: PhD student , KTH Royal Institute of Technology, Stockholm, Sweden (SE)

Papers (1)

Boltzmann Semantic Score: A Semantic Metric for Evaluating Large Vision Models Using Large Language Models — ICLR 2025 Poster

Hsin-Pai Cheng

2021–present: Researcher , Qualcomm Inc, QualComm (US)

2017–2021: PhD student , Duke University (US)

Papers (1)

PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer — ICLR 2025 Poster

Huaiyu Wan

2015–present: Full Professor , Beijing Jiaotong University (CN)

2013–2014: Postdoc , Tsinghua University (CN)

2007–2012: PhD student , Beijing Jiaotong University (CN)

Papers (1)

TrajMamba: An Efficient and Semantic-rich Vehicle Trajectory Pre-training Model — NeurIPS 2025 spotlight

Huajie Shao

2021–present: Assistant Professor , College of William and Mary (US)

2015–2021: PhD student , University of Illinois, Urbana Champaign (US)

Papers (1)

A Generalizable Physics-Enhanced State Space Model for Long-Term Dynamics Forecasting in Complex Environments — ICML 2025 poster

Huanlei Chen

2021–present: Researcher , Shanghai Motor Vehicle Inspection Certification & Tech Innovation Center Co., Ltd. (CN)

2016–2021: Assistant Professor , Tongji University (CN)

2008–2013: PhD student , Technische Universität München (DE)

Papers (1)

CSV-Occ: Fusing Multi-frame Alignment for Occupancy Prediction with Temporal Cross State Space Model and Central Voting Mechanism — ICML 2025 poster

Huayu Mai

2023–2026: PhD student , University of Science and Technology of China (CN)

2021–2023: MS student , University of Science and Technology of China

2017–2021: Undergrad student , University of Science and Technology of China

Papers (1)

BeyondMix: Leveraging Structural Priors and Long-Range Dependencies for Domain-Invariant LiDAR Segmentation — NeurIPS 2025 poster

Huazhong Yang

1998–present: Full Professor , Tsinghua University (CN)

1997–1998: PhD student , Tsinghua University (CN)

1996–1998: Associate Professor , Tsinghua University (CN)

1993–1996: Assistant Professor , Tsinghua University (CN)

1991–1993: MS student , Tsinghua University (CN)

1984–1989: Undergrad student , Tsinghua University (CN)

Papers (1)

Evaluating Quantized Large Language Models — ICML 2024 Poster

Hui Feng

2016–present: Associate Professor , Fudan University (CN)

2008–2014: PhD student , Fudan University (CN)

Papers (1)

EventMG: Efficient Multilevel Mamba-Graph Learning for Spatiotemporal Event Representation — NeurIPS 2025 poster

Hui LIN

2021–2024: MS student , Xi'an Jiaotong University

Papers (1)

Polyline Path Masked Attention for Vision Transformer — NeurIPS 2025 spotlight

Huijia Zhu

2015–present: Researcher , Ant Group (CN)

2007–2015: Researcher , International Business Machines (CN)

Papers (1)

Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training — ICML 2025 poster

Huimin Ma

2018–present: Full Professor , University of Science and Technology Beijing (CN)

2006–2019: Associate Professor , Tsinghua University (CN)

Papers (1)

MVSMamba: Multi-View Stereo with State Space Model — NeurIPS 2025 poster

Huiqiang Jiang

2021–present: RSDE , Microsoft (CN)

2018–2021: MS student , Peking University

2014–2018: Undergrad student , Zhejiang University

Papers (1)

SCBench: A KV Cache-Centric Analysis of Long-Context Methods — ICLR 2025 Poster

Hunter Nisonoff

2019–2025: PhD student , University of California Berkeley (US)

Papers (1)

Unlocking Guidance for Discrete State-Space Diffusion and Flow Models — ICLR 2025 Poster

Huzefa Rangwala

2022–present: Principal Researcher , Amazon (US)

2008–2015: Full Professor , Computer Science, George Mason University (US)

Papers (1)

LC-PLM: Long-context Protein Language Modeling Using Bidirectional Mamba with Shared Projection Layers — Accepted by TMLR

HyeongJoo Hwang

2025–present: Researcher , Samsung (KR)

2024–2025: Postdoc , Korea Advanced Institute of Science & Technology (KR)

2020–2024: PhD student , Korea Advanced Institute of Science & Technology (KR)

2018–2020: MS student , Korea Advanced Institute of Science & Technology (KR)

Papers (1)

Information-Theoretic State Space Model for Multi-View Reinforcement Learning — ICML 2023 OralPoster

Hyung Il Koo

2017–present: Researcher , FuriosaAI (KR)

2012–present: Full Professor , Ajou University (KR)

2005–2010: PhD student , Seoul National University (KR)

2002–2004: MS student , Seoul National University (KR)

1996–2002: Undergrad student , Seoul National University (KR)

Papers (1)

Parameter-Efficient Fine-Tuning of State Space Models — ICML 2025 poster

Hyungi Lee

2025–present: Assistant Professor , Kookmin University (KR)

2022–2025: PhD student , Korea Advanced Institute of Science & Technology (KR)

2020–2022: MS student , Korea Advanced Institute of Science and Technology (KR)

2013–2020: Undergrad student , Korea Advanced Institute of Science and Technology (KR)

Papers (1)

Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Series — ICLR 2025 Oral

Hyungju Jeon

2023–present: PhD student , Champalimaud Centre for the Unknown

2015–2022: Researcher , Korea Institute of Science and Technology

2012–2014: MS student , Duke University

Papers (1)

Meta-Dynamical State Space Models for Integrative Neural Data Analysis — ICLR 2025 Spotlight

Idan Arbiv

2025–2029: PhD student , Ben Gurion University of the Negev (IL)

2023–2025: MS student , Ben-Gurion University of the Negev (IL)

Papers (1)

Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series — NeurIPS 2024 poster

Ido Amos

2025–present: PhD student , Hebrew University, Hebrew University of Jerusalem (IL)

2024–2025: Intern , Research, Google (IL)

2022–2025: MS student , Tel Aviv University (IL)

2023–2024: Intern , International Business Machines

Papers (1)

Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors — ICLR 2024 oral

Ido Blass

2024–2028: PhD student , Bar-Ilan University (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Igor Vasiljevic

2022–present: Research Scientist , Toyota Research Institute (US)

2017–2022: PhD student , Toyota Technological Institute at Chicago (US)

2015–2016: MS student , University of Chicago (US)

2010–2013: Undergrad student , University of Chicago (US)

Papers (1)

Linearizing Large Language Models — COLM

Ilan Naiman

2024–present: Researcher , Amazon (IL)

2020–present: PhD student , Ben Gurion University of the Negev, Technion (IL)

Papers (1)

Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series — NeurIPS 2024 poster

Inbal Magar

2019–2022: MS student , Hebrew University in Jerusalem

2016–2019: Undergrad student , Hebrew University in Jerusalem

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Ion Stoica

2000–present: Full Professor , University of California, Berkeley (US)

1996–2000: PhD student , Carnegie Mellon University

Papers (1)

Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation — NeurIPS 2025 poster

Irina Lehmann

2018–present: Full Professor , Charité - Universitätsmedizin Berlin (DE)

2003–2017: Head of the Department , Helmholtz Centre for Environmental Research - UFZ (DE)

2000–2003: Independent group leader , Helmholtz Centre for Environmental Research - UFZ (DE)

1996–2000: Assistant Professor , Medical Faculty University of Leipzig (DE)

1991–1996: Postdoc , Medical Faculty University of Leipzig (DE)

1982–1987: MS student , Universität Leipzig (DE)

Papers (1)

JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation Model — NeurIPS 2025 poster

Isaac Reid

2022–present: PhD student , University of Cambridge

2017–2021: Undergrad student , University of Oxford

Papers (1)

Linear Transformer Topological Masking with Graph Random Features — ICLR 2025 Poster

Ismail Ben Ayed

2020–present: Full Professor , École de technologie supérieure, Université du Québec (CA)

2015–2020: Associate Professor , École de technologie supérieure, Université du Québec (CA)

2007–2015: Research Scientist , GE (CA)

2004–2007: PhD student , Institut national de la recherche scientifique (CA)

Papers (1)

TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses — NeurIPS 2025 poster

Itai Pemper

2023–present: MS student , Ben Gurion University of the Negev (IL)

Papers (1)

Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series — NeurIPS 2024 poster

Itay Dalmedigos

2021–2024: Researcher , AI21 (IL)

2017–2020: MS student , Technion - Israel Institute of Technology, Technion

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Ivan Lee

2023–present: PhD student , University of California, San Diego (US)

2020–2023: MS student , University of California, San Diego (US)

Papers (1)

Is attention required for ICL? Exploring the Relationship Between Model Architecture and In-Context Learning Ability — ICLR 2024 poster

Ivana Dusparic

2016–present: Associate Professor , University of Dublin, Trinity College (IE)

Papers (1)

Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient — ICLR 2025 Poster

J Zico Kolter

2012–present: Full Professor , Carnegie Mellon University (US)

2010–2012: Postdoc , Massachusetts Institute of Technology (US)

2005–2010: PhD student , Stanford University (US)

Papers (1)

Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models — NeurIPS 2024 poster

Jack Morris

2024–present: PhD student , Georgia State University (US)

2014–2019: Undergrad student , Emory University (US)

Papers (1)

MamBEV: Enabling State Space Models to Learn Birds-Eye-View Representations — ICLR 2025 Poster

Jackson Petty

2022–present: PhD student , New York University (US)

2017–2022: Undergrad student , Yale University (US)

Papers (1)

The Illusion of State in State-Space Models — ICML 2024 Poster

Jacob Andreas

2019–present: Associate Professor , Massachusetts Institute of Technology (US)

2018–2024: Researcher , Microsoft

2013–2018: PhD student , University of California Berkeley

2012–2013: MS student , University of Cambridge

2008–2012: Undergrad student , Columbia University

Papers (1)

Learning Linear Attention in Polynomial Time — NeurIPS 2025 oral

Jaden Park

2024–2029: PhD student , Department of Computer Science, University of Wisconsin - Madison (US)

2025–2025: Intern , Adobe Research (US)

2023–2024: Intern , Krafton (KR)

2017–2023: Undergrad student , Seoul National University (KR)

Papers (1)

Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks — ICML 2024 Poster

Jaewoong Cho

2022–present: Researcher , KRAFTON

2016–2022: PhD student , Korea Advanced Institute of Science and Technology

2014–2016: MS student , Korea Advanced Institute of Science and Technology

2009–2014: Undergrad student , Korea Advanced Institute of Science and Technology

Papers (1)

Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks — ICML 2024 Poster

Jalal Naghiyev

2024–present: Intern , Georg-August Universität Göttingen (DE)

2025–2027: MS student , Technical University of Munich (DE)

2019–2023: Undergrad student , ITMO University (RU)

Papers (1)

Layer by Layer: Uncovering Hidden Representations in Language Models — ICML 2025 oral

James R. Glass

1988–present: Principal Researcher , Massachusetts Institute of Technology (US)

1985–1988: PhD student , Massachusetts Institute of Technology (US)

1982–1984: MS student , Massachusetts Institute of Technology (US)

1978–1982: Undergrad student , Carleton University (CA)

Papers (1)

Overflow Prevention Enhances Long-Context Recurrent LLMs — COLM 2025

James Zou

2016–2025: Associate Professor , Stanford University (US)

Papers (1)

Simple linear attention language models balance the recall-throughput tradeoff — ICML 2024 Spotlight

Janarthanan Rajendran

2024–present: Assistant Professor , Dalhousie University

2021–present: Postdoc , University of Montreal

2021–2023: Postdoc , Mila

2016–2021: PhD student , University of Michigan

2019–2019: Intern , Google

2018–2018: Intern , International Business Machines

2011–2016: MS student , Indian Institute of Technology Madras

2011–2016: Undergrad student , Indian Institute of Technology Madras

Papers (1)

Mastering Memory Tasks with World Models — ICLR 2024 oral

Jannes Gladrow

2019–present: Researcher , Research, Microsoft (GB)

2016–2019: PhD student , University of Cambridge

Papers (1)

Implicit Language Models are RNNs: Balancing Parallelization and Expressivity — ICML 2025 spotlightposter

Jason Alan Fries

2017–present: Research Scientist , Stanford University (US)

2015–2017: Postdoc , Stanford University

2009–2015: PhD student , University of Iowa

Papers (1)

Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHR Data — ICLR 2025 Poster

Jason D. Lee

—–present: Assistant Professor , Princeton University

Papers (1)

Understanding Factual Recall in Transformers via Associative Memories — ICLR 2025 Spotlight

Jean Mercat

2021–present: Researcher , Toyota Research Institute (US)

2017–2021: PhD student , CentraleSupelec (FR)

Papers (1)

Linearizing Large Language Models — COLM

Jennifer Listgarten

2018–present: Full Professor , University of California Berkeley

Papers (1)

Unlocking Guidance for Discrete State-Space Diffusion and Flow Models — ICLR 2025 Poster

Jeremias Knoblauch

2019–2021: PhD student , Alan Turing Institute

2016–2021: PhD student , The university of Warwick

Papers (1)

Outlier-robust Kalman Filtering through Generalised Bayes — ICML 2024 Poster

Jerry Huang

2023–present: PhD student , Montreal Institute for Learning Algorithms, Université de Montréal (CA)

2025–2025: Visiting Student , The University of Tokyo (JP)

Papers (1)

Mamba Modulation: On the Length Generalization of Mamba Models — NeurIPS 2025 poster

Jerry Weihong Liu

2022–present: PhD student , Stanford University (US)

2022–2024: Intern , Lawrence Berkeley National Lab (US)

2020–2022: Intern , Lawrence Livermore National Labs (US)

2018–2021: Undergrad student , Duke University (US)

Papers (1)

Towards Learning High-Precision Least Squares Algorithms with Sequence Models — ICLR 2025 Poster

Jessica Grogan

2021–present: PhD student , State University of New York at Buffalo

Papers (1)

Towards Learning High-Precision Least Squares Algorithms with Sequence Models — ICLR 2025 Poster

Jhonathan Osin

2020–2022: MS student , Tel Aviv University, Technion

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Jia-Hua Lee

2022–2026: Undergrad student , Department of Computer Science, National Tsing Hua University, National Tsinghua University (TW)

Papers (1)

EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling — NeurIPS 2025 spotlight

Jiacong Hu

2025–present: Researcher , Zhejiang University (CN)

2020–2025: PhD student , Zhejiang University (CN)

Papers (1)

Vision Mamba Mender — NeurIPS 2024 poster

Jiahan Cao

2020–present: MS student , Nanjing University (CN)

2016–2020: Undergrad student , Nanjing University (CN)

Papers (1)

Leveraging Conditional Dependence for Efficient World Model Denoising — NeurIPS 2025 poster

Jiahao Chen

2023–2026: Undergrad student , East China University of Science and Technology (CN)

Papers (1)

CSV-Occ: Fusing Multi-frame Alignment for Occupancy Prediction with Temporal Cross State Space Model and Central Voting Mechanism — ICML 2025 poster

Jiahao Zhu

2023–present: MS student , Hangzhou Normal University (CN)

Papers (1)

Efficient LiDAR Reflectance Compression via Scanning Serialization — ICML 2025 poster

Jiaheng Zhou

2022–present: PhD student , Institute of Automation, Chinese Academy of Sciences (CN)

2018–2022: Undergrad student , Harbin Institute of Technology (CN)

Papers (1)

Dual-Res Tandem Mamba-3D: Bilateral Breast Lesion Detection and Classification on Non-contrast Chest CT — NeurIPS 2025 poster

Jiahuan Zhou

2022–present: Assistant Professor , Peking University (CN)

2018–2022: Postdoc , Northwestern University (US)

2013–2018: PhD student , Northwestern University (US)

2009–2013: Undergrad student , Tsinghua University (CN)

Papers (1)

State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding — NeurIPS 2025 poster

Jiahui Zhang

2024–2028: PhD student , University of Science and Technology of China (CN)

Papers (1)

Enhancing the Maximum Effective Window for Long-Term Time Series Forecasting — NeurIPS 2025 poster

Jiajie Li

2023–2027: PhD student , State University of New York at Buffalo (US)

2025–2025: Intern , ByteDance Inc. (US)

2022–2022: Intern , IBM, International Business Machines (US)

2020–2022: MS student , State University of New York at Buffalo (US)

Papers (1)

Sub-Sequential Physics-Informed Learning with State Space Model — ICML 2025 poster

Jiaju Lin

2023–present: PhD student , Pennsylvania State University

2020–2023: MS student , East China Normal University

2016–2020: Undergrad student , Shanghai Ocean University

Papers (1)

RWKV-7 "Goose" with Expressive Dynamic State Evolution — COLM 2025

Jiajun Zhu

2025–2030: PhD student , University of Texas at Austin (US)

2020–2025: Undergrad student , Zhejiang University (CN)

Papers (1)

Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing — ICLR 2025 Poster

Jiakang Yuan

2024–present: Intern , Shanghai Artificial Intelligence Laboratory (CN)

2022–present: PhD student , Fudan University (CN)

2022–2024: Intern , Shanghai AI Laboratory (CN)

2018–2022: Undergrad student , Fudan University (CN)

Papers (1)

3DET-Mamba: Causal Sequence Modelling for End-to-End 3D Object Detection — NeurIPS 2024 poster

JiaKui Hu

2025–present: Intern , Alibaba Group (CN)

2023–present: PhD student , Peking University (CN)

2024–2025: Intern , Baidu (CN)

2023–2023: Intern , Institute of automation, Chinese academy of science, Chinese Academy of Sciences (CN)

2019–2023: Undergrad student , Xi'an University of Electronic Science and Technology (CN)

Papers (1)

Spike-driven Transformer — NeurIPS 2023 poster

Jialong Guo

2023–present: Researcher , Huawei Technologies Ltd. (CN)

2019–2022: MS student , University of the Chinese Academy of Sciences (CN)

Papers (1)

SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization — ICML 2024 Poster

Jiaming Liu

2023–2027: PhD student , Peking University (CN)

2019–2022: MS student , Beijing University of Post and Telecommunication (CN)

2015–2019: Undergrad student , Beijing University of Post and Telecommunication (CN)

Papers (1)

RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation — NeurIPS 2024 poster

Jian Jiao

2010–present: Principal Researcher , Microsoft (US)

Papers (1)

Efficient Hybrid Long Sequence Modeling with State Space Augmented Transformers — COLM

Jian Sun

2013–present: Full Professor , Beijing Institute of Technology

Papers (1)

DyMoDreamer: World Modeling with Dynamic Modulation — NeurIPS 2025 poster

Jian Tang

2017–present: Assistant Professor , HEC Montreal

2017–present: Assistant Professor , Mila, HEC Montreal

Papers (1)

Overcoming Long Context Limitations of State Space Models via Context Dependent Sparse Attention — NeurIPS 2025 poster

Jian Wang

2023–present: Instructor , ByteDance Inc. (CN)

2016–2023: Engineer , Baidu

2014–2016: Engineer , Alibaba Group

2012–2014: Engineer , Space Star

2010–2012: MS student , Wuhan University

Papers (1)

Mobile Attention: Mobile-Friendly Linear-Attention for Vision Transformers — ICML 2024 Poster

Jian Yang

2007–present: Full Professor , Nanjing University of Science and Technology (CN)

2006–2007: Postdoc , New Jersey Institute of Technology (US)

2004–2006: Postdoc , Hong Kong Polytechnic University (CN)

2003–2003: Postdoc , Universidad de Zaragoza (ES)

Papers (1)

MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space — NeurIPS 2024 poster

Jianan Zhao

2022–2027: PhD student , Université de Montréal

2017–2020: MS student , Beijing University of Post and Telecommunication

2013–2017: Undergrad student , Beijing University of Post and Telecommunication

Papers (1)

Overcoming Long Context Limitations of State Space Models via Context Dependent Sparse Attention — NeurIPS 2025 poster

Jianbin Jiao

2005–present: Full Professor , University of the Chinese Academy of Sciences (CN)

Papers (1)

VMamba: Visual State Space Model — NeurIPS 2024 spotlight

Jiancheng Lv

2008–present: Full Professor , Sichuan University (CN)

2006–2008: Postdoc , National University of Singapore (SG)

2003–2006: PhD student , University of Electronic Science and Technology of China, Tsinghua University (CN)

Papers (1)

Pruning-Robust Mamba with Asymmetric Multi-Scale Scanning Paths — NeurIPS 2025 poster

Jianfei Jiang

2024–2028: PhD student , University of Science and Technology Beijing (CN)

2021–2024: MS student , Anhui University (CN)

Papers (1)

MVSMamba: Multi-View Stereo with State Space Model — NeurIPS 2025 poster

Jiangning Zhang

2022–2025: Principal Researcher , Tencent Youtu Lab (CN)

2017–2022: PhD student , Zhejiang University (CN)

Papers (1)

MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection — NeurIPS 2024 poster

Jiangshan Wang

2023–present: MS student , Tsinghua University, Tsinghua University (CN)

2019–2023: Undergrad student , Beijing University of Posts and Telecommunications (CN)

Papers (1)

MambaTree: Tree Topology is All You Need in State Space Model — NeurIPS 2024 spotlight

Jianguo Li

2020–present: Director , Ant Group

2006–2020: Senior Staff Research Scientist , Intel Labs

2001–2006: PhD student , Tsinghua University

Papers (1)

Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions — ICLR 2025 Poster

Jiangwei Weng

2023–present: PhD student , Nanjing University of Science and Technology (CN)

Papers (1)

MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space — NeurIPS 2024 poster

Jiangyong Yu

2022–present: Engineer , Houmo (CN)

2021–2022: Engineer , Baidu (CN)

2018–2020: Engineer , Nanjing FibreHome Starrysky (CN)

2015–2018: MS student , Nanjing University of Information Science and Technology (CN)

Papers (1)

MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods — ICLR 2025 Poster

Jiani Zhong

2021–2025: Undergrad student , The Chinese University of Hong Kong (CN)

Papers (1)

Multi-dataset Joint Pre-training of Emotional EEG Enables Generalizable Affective Computing — NeurIPS 2025 poster

Jianjun Qian

2014–present: Full Professor , Nanjing University of Science and Techonology (CN)

Papers (1)

MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space — NeurIPS 2024 poster

Jiankai Sun

—–present: PhD student , Stanford University (US)

Papers (1)

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation — NeurIPS 2025 poster

Jiansheng Chen

2021–present: Full Professor , University of Science and Technology Beijing (CN)

2016–2021: Associate Professor , Tsinghua University, Tsinghua University (CN)

2009–2016: Assistant Professor , Tsinghua University, Tsinghua University (CN)

Papers (1)

MVSMamba: Multi-View Stereo with State Space Model — NeurIPS 2025 poster

Jianwei Zheng

2023–present: Full Professor , Zhejiang University of Technology (CN)

2005–2010: PhD student , Zhejiang University of Technology (CN)

Papers (1)

Alias-Free Mamba Neural Operator — NeurIPS 2024 poster

Jianxu Chen

2021–present: Assistant Professor , Leibniz-Institut für Analytische Wissenschaften (DE)

2017–2021: Scientist , Allen Institute for Cell Science (US)

Papers (1)

Orochi: Versatile Biomedical Image Processor — NeurIPS 2025 spotlight

Jianyou Wang

2021–2027: PhD student , University of California, San Diego (US)

2017–2021: Undergrad student , Duke University

Papers (1)

Single-Pass Document Scanning for Question Answering — COLM 2025

Jiaqi Leng

2022–2026: Undergrad student , Fudan University (CN)

Papers (1)

Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access — NeurIPS 2025 poster

Jiaqi Li

2023–2027: Researcher , China Mobile Research Institute (CN)

2018–2023: PhD student , Tsinghua University, Tsinghua University (CN)

2014–2018: Undergrad student , Beihang University, Tsinghua University (CN)

Papers (1)

Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training — ICML 2025 poster

Jiarui Jiang

2024–present: MS student , Harbin Institute of Technology, Shenzhen (CN)

2020–2024: Undergrad student , Harbin Institute of Technology, Shenzhen (CN)

Papers (1)

Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression — NeurIPS 2025 poster

Jiarui Xu

2020–present: PhD student , University of California, San Diego (US)

2015–2020: Undergrad student , The Hong Kong University of Science and Technology (HK)

Papers (1)

Learning to (Learn at Test Time): RNNs with Expressive Hidden States — ICML 2025 spotlightposter

Jiaxing Liu

2021–2025: Undergrad student , Zhejiang University (CN)

Papers (1)

RWKV-7 "Goose" with Expressive Dynamic State Evolution — COLM 2025

Jiaxu Liu

2021–2025: PhD student , University of Liverpool (GB)

2019–2021: Undergrad student , Australian National University

2017–2019: Undergrad student , Shandong University

Papers (1)

Toward Linearly Regularizing the Geometric Bottleneck of Linear Generalized Attention — Accepted by TMLR

Jiayi Lyu

2021–present: PhD student , University of the Chinese Academy of Sciences (CN)

2017–2021: Undergrad student , Capital Normal University (CN)

Papers (1)

DAMamba: Vision State Space Model with Dynamic Adaptive Scan — NeurIPS 2025 poster

Jiayuan Mao

2025–present: Researcher , Amazon (US)

2019–2025: PhD student , Massachusetts Institute of Technology (US)

2014–2019: Undergrad student , Tsinghua University (CN)

Papers (1)

Learning Linear Attention in Polynomial Time — NeurIPS 2025 oral

Jiazhou Zhou

2024–present: PhD student , The Hong Kong University of Science and Technology (CN)

2023–2024: Researcher , The Hong Kong University of Science and Technology (CN)

2020–2023: MS student , University of Electronic Science and Technology of China (CN)

2016–2020: Undergrad student , University of Electronic Science and Technology of China (CN)

Papers (1)

PASS: Path-selective State Space Model for Event-based Recognition — NeurIPS 2025 poster

Jie Chen

1998–present: Full Professor , Beijing Institute of Technology

Papers (1)

DyMoDreamer: World Modeling with Dynamic Modulation — NeurIPS 2025 poster

Jie Huang

2020–present: PhD student , University of Science and Technology of China (CN)

Papers (1)

FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining — ICML 2025 poster

Jie Wen

2023–present: Associate Professor , Harbin Institute of Technology (CN)

2021–2022: Assistant Professor , Harbin Institute of Technology

2019–2021: Postdoc , Harbin Institute of Technology (CN)

2015–2019: PhD student , Harbin Institute of Technology (CN)

2012–2015: MS student , Harbin Engineering University (CN)

Papers (1)

Hierarchical Information Aggregation for Incomplete Multimodal Alzheimer's Disease Diagnosis — NeurIPS 2025 poster

Jieru Mei

2024–present: Researcher , Google (US)

2018–2024: PhD student , Johns Hopkins University (US)

2014–2018: Undergrad student , Huazhong University of Science and Technology (CN)

Papers (1)

Autoregressive Pretraining with Mamba in Vision — ICLR 2025 Poster

Jiezhang Cao

2024–2026: Postdoc , Harvard University (US)

2020–2024: PhD student , ETH Zürich (CH)

2017–2020: MS student , South China University of Technology (CN)

Papers (1)

MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging — NeurIPS 2024 poster

Jifeng Dai

2022–present: Associate Professor , Tsinghua University, Tsinghua University (CN)

2019–2022: Executive Research Director , SenseTime Group Ltd (CN)

2014–2019: Principle Research Manager , Microsoft (CN)

2009–2014: Ph.D. student , Tsinghua University, Tsinghua University (CN)

2005–2009: B.S. student , Tsinghua University, Tsinghua University (CN)

Papers (1)

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures — ICLR 2025 Spotlight

Jifeng Hu

2021–2026: PhD student , Jilin University (CN)

Papers (1)

Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling — NeurIPS 2024 poster

Jihoon Hong

2024–present: PhD student , Georgia Institute of Technology (US)

2017–2024: Undergrad student , Seoul National University

Papers (1)

LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement — ICLR 2025 Poster

Jihoon Tack

2025–present: Researcher , Microsoft Research (US)

2024–2025: Intern , Meta FAIR (US)

2019–2025: PhD student , Korea Advanced Institute of Science and Technology (KR)

2023–2023: Intern , University of Oxford (GB)

Papers (1)

Sparsified State-Space Models are Efficient Highway Networks — Accepted by TMLR

Jin Xu

2024–present: Researcher , Microsoft (GB)

2018–2023: PhD student , University of Oxford (GB)

2018–2018: Intern , Tencent AI Lab (CN)

2016–2017: MS student , University of Edinburgh (GB)

2010–2014: Undergrad student , Fudan University (CN)

Papers (1)

On Feature Learning in Structured State Space Models — NeurIPS 2024 poster

Jina Kim

2022–2026: Undergrad student , Korea Advanced Institute of Science & Technology (KR)

Papers (1)

SEA: Sparse Linear Attention with Estimated Attention Mask — ICLR 2024 poster

Jinbo Hu

2022–2026: Undergrad student , Shanghai Jiaotong University (CN)

Papers (1)

Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation — NeurIPS 2025 poster

Jincai Huang

2015–2025: Full Professor , National University of Defense Technology (CN)

1998–2003: PhD student , National University of Defense Technology (CN)

1994–1998: Undergrad student , National University of Defense Technology (CN)

Papers (1)

Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning? — NeurIPS 2024 poster

Jincheng YU

2024–present: Intern , NVIDIA (CN)

2019–2024: MS student , The Hong Kong University of Science and Technology (HK)

2015–2019: Undergrad student , Zhejiang University (CN)

Papers (1)

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer — ICML 2025 poster

Jindi Lv

2023–2027: PhD student , Sichuan University (CN)

2020–2023: MS student , Sichuan University (CN)

Papers (1)

Pruning-Robust Mamba with Asymmetric Multi-Scale Scanning Paths — NeurIPS 2025 poster

Jindong Jiang

2025–present: Researcher , NVIDIA (US)

2020–2025: PhD student , Rutgers University (US)

2018–2020: MS student , Rutgers University (US)

Papers (1)

Slot State Space Models — NeurIPS 2024 poster

Jing Ding

2014–present: Full Professor , Fudan University (CN)

Papers (1)

FAPEX: Fractional Amplitude-Phase Expressor for Robust Cross-Subject Seizure Prediction — NeurIPS 2025 spotlight

Jing Nathan Yan

2024–present: Researcher , Google (US)

2019–2024: PhD student , Cornell University (US)

Papers (1)

MambaByte: Token-free Selective State Space Model — COLM

Jing Zhang

2024–present: Full Professor , Wuhan University (CN)

2019–2024: Research Fellow , The University of Sydney (AU)

2010–2015: PhD student , University of Science and Technology of China (CN)

Papers (1)

RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing — NeurIPS 2025 poster

Jingcheng Wu

2024–2027: PhD student , Universität Stuttgart (DE)

2021–2023: MS student , Ludwig-Maximilians-Universität München (DE)

Papers (1)

DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Models — Accepted by TMLR

Jinghua Hou

2022–2025: MS student , Huazhong University of Science and Technology (CN)

2018–2022: Undergrad student , Huazhong University of Science and Technology (CN)

Papers (1)

LION: Linear Group RNN for 3D Object Detection in Point Clouds — NeurIPS 2024 poster

Jinghua Wang

2022–present: Associate Professor , Harbin Institute of Technology (CN)

2017–2021: Assistant Professor , Shenzhen University (CN)

2014–2016: Postdoc , Nanyang Technological University (SG)

2009–2013: PhD student , The Hong Kong Polytechnic University (HK)

Papers (1)

Hierarchical Information Aggregation for Incomplete Multimodal Alzheimer's Disease Diagnosis — NeurIPS 2025 poster

Jingjun Yi

2023–present: MS student , LIESMARS (CN)

2019–2023: Undergrad student , School of Remote Sensing Information Engineering (CN)

Papers (1)

Samba: Severity-aware Recurrent Modeling for Cross-domain Medical Image Grading — NeurIPS 2024 poster

Jingren Zhou

2015–present: Researcher , Alibaba Group (CN)

2004–2015: Researcher , Research, Microsoft (US)

1999–2004: PhD student , Columbia University (US)

Papers (1)

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free — NeurIPS 2025 oral

Jingyan Tu

2023–2026: MS student , Xiamen University (CN)

2019–2023: Undergrad student , Anhui University (CN)

Papers (1)

FRN: Fractal-Based Recursive Spectral Reconstruction Network — NeurIPS 2025 poster

Jingyi Li

—–present: PhD student , National University of Singapore (SG)

Papers (1)

Balancing Interference and Correlation in Spatial Experimental Designs: A Causal Graph Cut Approach — ICML 2025 poster

Jinjun Xiong

2021–present: Professor , State University of New York at Buffalo (US)

2006–2021: Researcher , International Business Machines (US)

Papers (1)

Sub-Sequential Physics-Informed Learning with State Space Model — ICML 2025 poster

Jintang Li

2021–2025: PhD student , Sun Yat-sen University (CN)

Papers (1)

State Space Models on Temporal Graphs: A First-Principles Study — NeurIPS 2024 poster

Jintao Guo

2022–2026: PhD student , Nanjing University (CN)

2020–2022: MS student , Nanjing university (CN)

2016–2020: Undergrad student , University of Science and Technology of China (CN)

Papers (1)

START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation — NeurIPS 2024 poster

Jinwoo Shin

2022–present: Full Professor , Korea Advanced Institute of Science & Technology (KR)

2016–2022: Associate Professor , Korea Advanced Institute of Science and Technology (KR)

2013–2016: Assistant Professor , Korea Advanced Institute of Science and Technology (KR)

2012–2013: Postdoc , International Business Machines (US)

2010–2012: Postdoc , Georgia Institute of Technology (US)

2005–2010: PhD student , Massachusetts Institute of Technology (US)

Papers (1)

Sparsified State-Space Models are Efficient Highway Networks — Accepted by TMLR

Jiwen Lu

2024–present: Full Professor , Tsinghua University (CN)

2015–2023: Associate Professor , Tsinghua University (CN)

2011–2015: Research Scientist , Advanced Digital Sciences Center (SG)

Papers (1)

Bridging the Divide: Reconsidering Softmax and Linear Attention — NeurIPS 2024 poster

Johan S. Wind

2021–2025: PhD student , University of Oslo

Papers (1)

RWKV-7 "Goose" with Expressive Dynamic State Evolution — COLM 2025

Johannes Brunnemann

2022–present: Lecturer , Technische Universität Hamburg (DE)

2011–present: Researcher , XRG Simulation GmbH (DE)

2009–2010: Postdoc , Universität Paderborn (DE)

2006–2009: Postdoc , Universität Hamburg (DE)

Papers (1)

Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximations — ICLR 2025 Poster

Johannes Schimunek

2025–present: Postdoc , Johannes Kepler Universität Linz (AT)

2019–2025: PhD student , Johannes Kepler Universität Linz (AT)

Papers (1)

Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences — ICLR 2025 Poster

Johannes von Oswald

2023–present: Researcher , Google (CH)

2018–2023: PhD student , Swiss Federal Institute of Technology (CH)

Papers (1)

Linear Transformers are Versatile In-Context Learners — NeurIPS 2024 poster

John Timothy Halloran

2023–present: Principal Researcher , Leidos (US)

2021–2023: Researcher , Amazon

2016–2021: Postdoc , University of California, Davis

2010–2016: PhD student , University of Washington

2008–2010: MS student , University of Hawaii, Manoa

2002–2008: Undergrad student , Seattle University

Papers (1)

Mamba State-Space Models Are Lyapunov-Stable Learners — Accepted by TMLR

Jonathan Berant

2023–present: Researcher , Google (US)

2019–present: Associate Professor , Tel Aviv University (IL)

2017–2021: Research scientist , Allen Institute for Artificial Intelligence (IL)

2016–2019: Assistant Professor , Tel Aviv University, Technion (IL)

2015–2016: Postdoc , Google (US)

2012–2015: Postdoc , Stanford University (US)

2007–2012: PhD student , Tel Aviv University (US)

Papers (1)

Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors — ICLR 2024 oral

Jonathan May

2015–present: Research Scientist , USC/ISI (US)

2017–2021: Assistant Professor , University of Southern California (US)

2001–2004: Researcher , RTX BBN Technologies (US)

2001–2001: Intern , Oracle (US)

Papers (1)

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length — NeurIPS 2024 poster

Jonathan Pilault

2019–present: PhD student , Polytechnique Montreal

2012–2015: Undergrad student , McGill University

Papers (1)

Block-State Transformers — NeurIPS 2023 poster

Jonathan Schmidt

2022–present: PhD student , Eberhard-Karls-Universität Tübingen

2019–2021: MS student , Eberhard-Karls-Universität Tübingen

2019–2020: MS student , Max Planck Institute for Intelligent Systems, Max-Planck Institute

2014–2018: Undergrad student , Eberhard-Karls-Universität Tübingen

Papers (1)

The Rank-Reduced Kalman Filter: Approximate Dynamical-Low-Rank Filtering In High Dimensions — NeurIPS 2023 poster

Jonathan W. Pillow

2014–present: Professor , Princeton University (US)

2009–2014: Assistant Professor , University of Texas, Austin (US)

2005–2008: Postdoc , University College London

1998–2005: PhD student , New York University

Papers (1)

Modeling state-dependent communication between brain regions with switching nonlinear dynamical systems — ICLR 2024 poster

Jongho Park

2025–present: PhD student , University of California, Berkeley (US)

2021–2025: Researcher , Krafton Inc. (KR)

2019–2021: MS student , University of Wisconsin, Madison (US)

2015–2019: Undergrad student , University of California Berkeley (US)

Papers (1)

Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks — ICML 2024 Poster

Joo Hwee Lim

2018–present: Principal Researcher , I2R, ASTAR (SG)

Papers (1)

MVGamba: Unify 3D Content Generation as State Space Sequence Modeling — NeurIPS 2024 poster

Joohwan Ko

2024–present: PhD student , Department of Computer Science, University of Massachusetts at Amherst (US)

2022–2024: MS student , Korea Advanced Institute of Science & Technology (KR)

Papers (1)

Layer-Adaptive State Pruning for Deep State Space Models — NeurIPS 2024 poster

Jordan Vice

2023–present: Postdoc , University of Western Australia (AU)

2020–2022: PhD student , Curtin University of Technology (AU)

2015–2019: Undergrad student , Curtin University of Technology (AU)

Papers (1)

CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation — NeurIPS 2025 poster

Joseph Kampeas

2020–present: Researcher , Huawei Technologies Ltd.

Papers (1)

Linear Log-Normal Attention with Unbiased Concentration — ICLR 2024 poster

Josh Alman

—–present: PhD student , Massachusetts Institute of Technology (US)

—–present: PhD student , Stanford University (US)

—–present: Postdoc , Harvard University (US)

2021–present: Assistant Professor , Columbia University (US)

Papers (1)

Fundamental Limitations on Subquadratic Alternatives to Transformers — ICLR 2025 Poster

Josh Cohen

2016–2019: MS student , Technion - Israel Institute of Technology, Technion

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Joshua Ainslie

2017–present: Software Engineer , Google (US)

2005–2007: MS student , Stanford University

2003–2007: Undergrad student , Stanford University

Papers (1)

Linear Transformer Topological Masking with Graph Random Features — ICLR 2025 Poster

Joshua B. Tenenbaum

2002–present: Professor , Massachusetts Institute of Technology (US)

1993–1998: PhD student , Massachusetts Institute of Technology (US)

Papers (1)

Learning Linear Attention in Polynomial Time — NeurIPS 2025 oral

Josue Nassar

2022–present: Researcher , Optum Labs

2022–2022: Postdoc , Center for Computational Neuroscience, Flatiron Institute

2017–2022: PhD student , State University of New York, Stony Brook

Papers (1)

Meta-Dynamical State Space Models for Integrative Neural Data Analysis — ICLR 2025 Spotlight

Juan Carlos Niebles

2021–present: Director, Research , Salesforce Research (US)

2021–present: Adjunct Professor , Stanford University (US)

2015–2021: Senior Research Scientist , Stanford University (US)

2011–2019: Associate Professor , Universidad del Norte (CO)

2007–2010: Graduate Student , Princeton University (US)

2005–2007: Graduate Student , University of Illinois at Urbana-Champaign (US)

Papers (1)

Exploring Diffusion Transformer Designs via Grafting — NeurIPS 2025 oral

Juan Lopez Alcaraz

2022–2025: PhD student , Carl von Ossietzky Universität Oldenburg

Papers (1)

Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models — Accepted by TMLR

Juergen Gall

2013–present: Professor , University of Bonn (DE)

2012–2013: Researcher , Max Planck Institute for Intelligent Systems, Max-Planck Institute (DE)

2009–2012: Postdoc , ETH Zurich (CH)

2006–2009: PhD student , Saarland Informatics Campus, Max-Planck Institute (DE)

Papers (1)

RiverMamba: A State Space Model for Global River Discharge and Flood Forecasting — NeurIPS 2025 poster

Juho Lee

2023–present: Associate Professor , Korea Advanced Institute of Science & Technology (KR)

2020–2023: Assistant Professor , Korea Advanced Institute of Science & Technology (KR)

2019–2020: Research Scientist , AITRICS (KR)

2018–2019: Postdoc , University of Oxford (GB)

2011–2018: PhD student , POSTECH (KR)

Papers (1)

Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Series — ICLR 2025 Oral

Jules Berman

2022–2025: PhD student , New York University (US)

2021–2022: Researcher , Flatiron Institute

Papers (1)

Hankel Singular Value Regularization for Highly Compressible State Space Models — NeurIPS 2025 poster

Julia Vinogradska

2017–2021: Researcher , Bosch

2014–2017: PhD student , TU Darmstadt

Papers (1)

Uncertainty Representations in State-Space Layers for Deep Reinforcement Learning under Partial Observability — Accepted by TMLR

Julie Fadlon

2020–present: Researcher , University of California, San Diego (US)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Julius Aka

2024–present: PhD student , University of Augsburg (DE)

2021–present: MS student , Hamburg University of Technology (DE)

2022–2024: Researcher , XRG Simulation GmbH (DE)

Papers (1)

Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximations — ICLR 2025 Poster

Jun Chen

2019–present: Full Professor , McMaster University (CA)

2013–2019: Associate Professor , McMaster University (CA)

2007–2013: Assistant Professor , McMaster University (CA)

2006–2007: Postdoc , IBM, International Business Machines (US)

2005–2006: Postdoc , University of Illinois at Urbana-Champaign (US)

2001–2005: PhD student , Cornell University (US)

Papers (1)

ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correction — NeurIPS 2024 poster

Jun He

2014–present: Full Professor , Renmin University of China (CN)

1997–2014: Associate Professor , Renmin University of China (CN)

2003–2009: PhD student , Renmin University of China (CN)

1990–1997: Assistant Professor , Renmin University of China (CN)

1988–1991: MS student , Renmin University of China (CN)

Papers (1)

MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation — NeurIPS 2025 poster

jun lan

2020–2025: Researcher , AntGroup (CN)

2014–2017: MS student , Shanghai Jiaotong University (CN)

Papers (1)

Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training — ICML 2025 poster

Jun Li

2019–present: Full Professor , Nanjing University of Science and Technology (CN)

2018–2019: Postdoc , Massachusetts Institute of Technology (US)

2015–2018: Postdoc , Northeastern University (US)

2011–2015: PhD student , Nanjing University of Science and Technology

2012–2013: Visiting PhD student , Rutgers University

Papers (1)

MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space — NeurIPS 2024 poster

Jun Pang

2015–present: Principal Researcher , University of Luxembourg (LU)

2008–2015: Researcher , University of Luxemburg (LU)

2006–2008: Postdoc , Carl von Ossietzky Universität Oldenburg (DE)

2004–2006: Postdoc , INRIA (FR)

2000–2004: PhD student , Centrum voor Wiskunde en Informatica (NL)

Papers (1)

Structural Inference of Dynamical Systems with Conjoined State Space Models — NeurIPS 2024 poster

Jun Song

2021–present: Researcher , Alibaba Group (CN)

Papers (1)

Demystify Mamba in Vision: A Linear Attention Perspective — NeurIPS 2024 poster

Jun Zhao

2022–2026: PhD student , Fudan University (CN)

2019–2022: MS student , Fudan University (CN)

2015–2019: Undergrad student , Northeastern University (CN)

Papers (1)

Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access — NeurIPS 2025 poster

Jun-hao Zhuang

2024–present: Intern , Tencent ARC Lab (CN)

2023–present: MS student , Tsinghua University, Tsinghua University (CN)

2023–2024: Intern , Shanghai AI Laboratory (CN)

2022–2023: Intern , Alibaba Group (CN)

2019–2023: Undergrad student , University of Electronic Science and Technology of China (CN)

Papers (1)

Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking — NeurIPS 2025 poster

Junbo Zhao

2020–present: Assistant Professor , Zhejiang University (CN)

2014–2019: PhD student , New York University (US)

2010–2014: Undergrad student , Wuhan University (CN)

Papers (1)

Revisiting Convolution Architecture in the Realm of DNA Foundation Models — ICLR 2025 Poster

Jung Taek Seo

2001–2024: Associate Professor , Gachon University (KR)

Papers (1)

Swift Hydra: Self-Reinforcing Generative Framework for Anomaly Detection with Multiple Mamba Models — ICLR 2025 Poster

Junhao Xiong

2021–present: PhD student , University of California, Berkeley (US)

2016–2019: Undergrad student , Johns Hopkins University (US)

Papers (1)

Unlocking Guidance for Discrete State-Space Diffusion and Flow Models — ICLR 2025 Poster

Junqi Gao

2023–2027: PhD student , Harbin Institute of Technology (CN)

2024–2025: Intern , Shanghai Artificial Intelligence Laboratory (CN)

Papers (1)

Exploring Adversarial Robustness of Deep State Space Models — NeurIPS 2024 poster

Junqing Yu

2010–2035: Full Professor , Huazhong University of Science and Technology (CN)

Papers (1)

Coupled Mamba: Enhanced Multimodal Fusion with Coupled State Space Model — NeurIPS 2024 poster

Juntian Ye

2018–present: PhD student , University of Science and Technology of China

2014–2018: Undergrad student , University of Science and Technology of China

Papers (1)

Toward Dynamic Non-Line-of-Sight Imaging with Mamba Enforced Temporal Consistency — NeurIPS 2024 poster

Junwei Zhu

2023–2026: MS student , Zhejiang University of Technology (CN)

Papers (1)

Alias-Free Mamba Neural Operator — NeurIPS 2024 poster

Junxuan Wang

2025–present: PhD student , Shanghai Innovation Institute (CN)

2021–2025: Undergrad student , Fudan University (CN)

Papers (1)

Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures — ICLR 2025 Poster

Junyan Cheng

2022–present: PhD student , Dartmouth College (US)

2025–2025: Intern , Microsoft Research Redmond (US)

2024–2024: Intern , Allen Institute for Artificial Intelligence (US)

2020–2021: MS student , University of Southern California (US)

Papers (1)

Language Modeling by Language Models — NeurIPS 2025 spotlight

Junyang Lin

2022–present: Principal Researcher , Alibaba Group (CN)

2019–2022: Researcher , Alibaba Group (CN)

Papers (1)

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free — NeurIPS 2025 oral

Jusen Du

2025–present: PhD student , Tsinghua University (CN)

2021–2025: Undergrad student , Nanjing University (CN)

Papers (1)

Improving Bilinear RNN with Closed-loop Control — NeurIPS 2025 spotlight

Jörg Bornschein

2016–present: Research Scientist , Google Deepmind (GB)

2013–2016: Postdoc , University of Montreal (CA)

2008–2013: PhD student , Frankfurt Institute For Advances Studies (DE)

Papers (1)

Kalman Filter for Online Classification of Non-Stationary Data — ICLR 2024 poster

Jörg Eiden

2005–present: Researcher , XRG Simulation GmbH (DE)

1997–2002: MS student , Technische Universität Hamburg (DE)

1994–1997: Undergrad student , Rheinisch Westfälische Technische Hochschule Aachen (DE)

Papers (1)

Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximations — ICLR 2025 Poster

Jörg K.H. Franke

2025–present: PhD student , ELLIS Institute Tübingen (DE)

2019–present: PhD student , Universität Freiburg (DE)

2022–2022: Intern , Amazon (US)

2017–2019: Master student , Karlsruhe Institute of Technology (DE)

Papers (1)

Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues — ICLR 2025 Oral

Jörg Nick

2023–present: Postdoc , Eberhard-Karls-Universität Tübingen

2018–2023: PhD student , Eberhard-Karls-Universität Tübingen

2016–2018: MS student , Eberhard-Karls-Universität Tübingen

Papers (1)

The Rank-Reduced Kalman Filter: Approximate Dynamical-Low-Rank Filtering In High Dimensions — NeurIPS 2023 poster

Jürgen Schmidhuber

2021–present: Director, AI Initiative , King Abdullah University of Science and Technology (SA)

2021–present: Adj. Professor , Universita della Svizzera Italiana (CH)

2014–present: Chief Scientist , NNAISENSE (CH)

1995–present: Scientific Director , IDSIA (CH)

Papers (1)

FACTS: A Factored State-Space Framework for World Modelling — ICLR 2025 Poster

Kai Han

2018–present: Principal Researcher , Huawei Noah's Ark Lab (CN)

2019–2023: PhD student , Institute of Software, Chinese Academy of Sciences (CN)

2015–2018: MS student , Peking University (CN)

2011–2015: Undergrad student , Zhejiang University (CN)

Papers (1)

MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected Layers — NeurIPS 2024 poster

Kai Ma

2018–present: Principal Scientist , Tencent (CN)

2014–2018: Staff Research Scientist , Siemens Corporate Research (US)

2007–2013: PhD student , University of Illinois at Chicago (US)

Papers (1)

VFIMamba: Video Frame Interpolation with State Space Models — NeurIPS 2024 poster

Kai Sun

2021–present: PhD student , Tsinghua University (CN)

2017–2020: MS student , Beijing University of Aeronautics and Astronautics (CN)

Papers (1)

Slimming the Fat-Tail: Morphing-Flow for Adaptive Time Series Modeling — ICML 2025 poster

Kai Tian

2023–present: MS student , Tsinghua University (CN)

2019–2023: Undergrad student , Jilin University (CN)

Papers (1)

Exploring Adversarial Robustness of Deep State Space Models — NeurIPS 2024 poster

Kai Wang

2025–present: Postdoc , NUS (SG)

2021–2025: PhD student , national university of singaore, National University of Singapore (SG)

2017–2020: MS student , Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Chinese Academy of Sciences (CN)

2013–2014: Undergrad student , Beijing Normal University (CN)

Papers (1)

Pruning-Robust Mamba with Asymmetric Multi-Scale Scanning Paths — NeurIPS 2025 poster

Kai Ye

2024–present: PhD student , London School of Economics and Political Science, University of London (GB)

2022–2023: MS student , London School of Economics and Political Science, University of London (GB)

Papers (1)

AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees — NeurIPS 2025 poster

Kai Zhang

2024–2025: Associate Professor , Nanjing University (CN)

2019–2024: Postdoc , ETH Zurich (CH)

2014–2019: PhD student , Harbin Institute of Technology (CN)

Papers (1)

MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging — NeurIPS 2024 poster

Kai Zhu

2022–2026: Undergrad student , Renmin University of China (CN)

Papers (1)

State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding — NeurIPS 2025 poster

Kaichen Zhou

2024–2027: Postdoc , Massachusetts Institute of Technology (US)

2020–2024: PhD student , Department of Computer Science, University of Oxford (GB)

2015–2019: Researcher , Imperial College London, Imperial College London

Papers (1)

RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation — NeurIPS 2024 poster

Kaifeng Tan

2025–2028: MS student , Shenzhen University (CN)

2021–2025: Undergrad student , JiangXi University of Science and Technology (CN)

Papers (1)

RWKV-7 "Goose" with Expressive Dynamic State Evolution — COLM 2025

kaixing yang

2022–2027: PhD student , Renmin University of China (CN)

2018–2022: Undergrad student , Nankai University (CN)

Papers (1)

MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation — NeurIPS 2025 poster

Kaiyue Wen

2024–2029: PhD student , Stanford University (US)

2020–2024: Undergrad student , Tsinghua University, Tsinghua University (CN)

2023–2023: Intern , CMU, Carnegie Mellon University (US)

2022–2023: Intern , Stanford University (US)

Papers (1)

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free — NeurIPS 2025 oral

Kang Li

—–present: PhD student , University of Oxford (GB)

Papers (1)

LOB-Bench: Benchmarking Generative AI for Finance - an Application to Limit Order Book Data — ICML 2025 poster

Kang You

2024–present: PhD student , Nanjing university (CN)

2020–2023: MS student , Nanjing University of Aeronautics and Astronautics (CN)

Papers (1)

Efficient LiDAR Reflectance Compression via Scanning Serialization — ICML 2025 poster

Kanghao Chen

2023–present: PhD student , Hong Kong University of Science and Technology (Guangzhou) (CN)

2022–2023: Researcher , SenseTime

2020–2022: MS student , SUN YAT-SEN UNIVERSITY (CN)

Papers (1)

PASS: Path-selective State Space Model for Event-based Recognition — NeurIPS 2025 poster

Karan Dalal

2022–present: Undergrad student , University of California, Berkeley (US)

Papers (1)

Learning to (Learn at Test Time): RNNs with Expressive Hidden States — ICML 2025 spotlightposter

Karn Tiwari

2022–present: PhD student , Indian Institute of Science, Indian institute of science, Bangalore

2018–2022: Undergrad student , National Institute of Technology Karnataka

Papers (1)

Latent Mamba Operator for Partial Differential Equations — ICML 2025 poster

Katherine Rich

2020–2025: PhD student , University of British Columbia

2015–2020: Undergrad student , University of Toronto

Papers (1)

Boltzmann Semantic Score: A Semantic Metric for Evaluating Large Vision Models Using Large Language Models — ICLR 2025 Poster

Ke Zhang

2020–2024: PhD student , University of Dublin, Trinity College (IE)

Papers (1)

Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient — ICLR 2025 Poster

Kee-Eung Kim

2020–present: Full Professor , Korea Advanced Institute of Science and Technology (KR)

2012–2020: Associate Professor , Korea Advanced Institute of Science and Technology (KR)

Papers (1)

Information-Theoretic State Space Model for Multi-View Reinforcement Learning — ICML 2023 OralPoster

Keisuke Fukuda

2017–present: Researcher , Preferred Networks, Inc. (JP)

2013–2017: PhD student , Tokyo Institute of Technology, Tokyo Institute of Technology (JP)

2011–2013: MS student , Tokyo Institute of Technology, Tokyo Institute of Technology (JP)

Papers (1)

Deep Bayesian Filter for Bayes-Faithful Data Assimilation — ICML 2025 poster

Kejing Xia

2025–present: PhD student , Georgia Institute of Technology (US)

2021–2025: Undergrad student , Wuhan University (CN)

Papers (1)

LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement — ICLR 2025 Poster

Kelly Peng

2017–2026: Researcher , Stanford University (US)

2012–2015: Undergrad student , Electrical Engineering & Computer Science Department, University of California, Berkeley (US)

Papers (1)

Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation — NeurIPS 2025 poster

Kengo Murata

2024–present: Researcher , Fujitsu Research and Development Center Co. Ltm. (JP)

2021–2024: PhD student , Aoyama Gakuin University, Tokyo Institute of Technology (JP)

2019–2021: MS student , Aoyama Gakuin University, Tokyo Institute of Technology (JP)

Papers (1)

Mamba Only Glances Once (MOGO): A Lightweight Framework for Efficient Video Action Detection — NeurIPS 2025 poster

Kenneth L. Clarkson

2007–present: Research Staff Member , International Business Machines (US)

Papers (1)

Predictability Enables Parallelization of Nonlinear State Space Models — NeurIPS 2025 poster

Kentaro Inui

2023–present: Full Professor , MBZUAI (AE)

2016–present: Researcher , RIKEN (JP)

2010–present: Full Professor , Tohoku University (JP)

2002–2010: Associate Professor , Nara Institute of Science and Technology, Japan

1998–2002: Associate Professor , Kyushu Institute of Technology, Tokyo Institute of Technology

1995–1998: Assistant Professor , Tokyo Institute of Technology, Tokyo Institute of Technology

Papers (1)

Uncovering the Spectral Bias in Diagonal State Space Models — NeurIPS 2025 poster

Kentaro Oguchi

2019–present: Director and Senior Principal Researcher , Toyota Motor North America (US)

2003–2019: Director , Toyota InfoTechnology Center (US)

1989–2003: Researcher , Toyota Central R&D Labs. Inc. (JP)

Papers (1)

MamBEV: Enabling State Space Models to Learn Birds-Eye-View Representations — ICLR 2025 Poster

Kento Nishi

2022–2026: Undergrad student , Harvard University (US)

Papers (1)

Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing — ICML 2025 poster

Keshigeyan Chandrasegaran

2023–2028: PhD student , Stanford University (US)

2019–2023: Researcher , Singapore University of Technology and Design (SG)

2016–2019: Undergrad student , Singapore University of Technology and Design (SG)

Papers (1)

Exploring Diffusion Transformer Designs via Grafting — NeurIPS 2025 oral

Kevin Galim

2021–present: Researcher , Furiosa AI (KR)

2020–2021: Researcher , Funzin

2016–2019: MS student , Technische Universität München

2013–2016: Undergrad student , Technische Universität München (DE)

Papers (1)

Parameter-Efficient Fine-Tuning of State Space Models — ICML 2025 poster

Kevin Li

2023–present: PhD student , Carnegie Mellon University (US)

2019–2023: Undergrad student , Georgia Institute of Technology

Papers (1)

Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models — NeurIPS 2024 poster

Kevin Patrick Murphy

2011–present: Principal Researcher , Google (US)

2004–2011: Associate Professor , University of British Columbia (CA)

Papers (1)

Outlier-robust Kalman Filtering through Generalised Bayes — ICML 2024 Poster

Kewei Tu

2024–present: Full Professor , ShanghaiTech University (CN)

2020–2024: Associate Professor , ShanghaiTech University (CN)

2014–2020: Assistant Professor , ShanghaiTech University (CN)

Papers (1)

Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access — NeurIPS 2025 poster

Kexin Wang

2021–2026: PhD student , Institute of automation, Chinese academy of science, Chinese Academy of Sciences (CN)

2017–2021: Undergrad student , Beijing University of Aeronautics and Astronautics (CN)

Papers (1)

MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map — NeurIPS 2024 oral

Klaus Robert Muller

2020–present: Researcher , Google (DE)

2012–present: Full Professor , Korea University (KR)

2006–present: Full Professor , TU Berlin (DE)

Papers (1)

MambaLRP: Explaining Selective State Space Sequence Models — NeurIPS 2024 poster

Kristian Kersting

2022–present: Full Professor , German Research Center for AI (DE)

2020–present: Full Professor , The Hessian Center for AI (DE)

2017–present: Full Professor , TU Darmstadt (DE)

2013–2017: Associate Professor , TU Dortmund (DE)

2012–2013: Assistant Professor , Agriculture Department, University of Bonn, Germany (DE)

2008–2012: Postdoc , Fraunhofer IAIS, Germany (DE)

2007–2007: Postdoc , Computer Science and Artificial Intelligence Laboratory, Electrical Engineering & Computer Science (US)

2006–2007: Postdoc , CS Department, University of Freiburg, Germany (DE)

2000–2006: PhD student , CS Department, University of Freiburg, Germany (DE)

1996–2000: MS student , CS Department, University of Freiburg, Germany (DE)

Papers (1)

Mechanistic Design and Scaling of Hybrid Architectures — ICML 2024 Poster

Kristjan Greenewald

2018–present: Research Scientist , MIT-IBM Watson AI Lab, IBM Research (US)

2017–2018: Postdoc , Harvard University (US)

2012–2017: PhD student , University of Michigan (US)

Papers (1)

Partially Observed Trajectory Inference using Optimal Transport and a Dynamics Prior — ICLR 2025 Poster

Krithik Ramesh

2023–present: Undergrad student , Massachusetts Institute of Technology (US)

2023–present: Researcher , Broad Institute (US)

2021–2022: Undergrad student , University of Auckland

Papers (1)

LoLCATs: On Low-Rank Linearizing of Large Language Models — ICLR 2025 Poster

Krzysztof Marcin Choromanski

2016–present: research scientist & adjunct assistant professor , Google Brain Robotics & Columbia University (US)

Papers (1)

Linear Transformer Topological Masking with Graph Random Features — ICLR 2025 Poster

Kumar Avinava Dubey

—–present: Research Scientist , Google Research

2012–2019: PhD student , Carnegie Mellon University

Papers (1)

Linear Transformer Topological Masking with Graph Random Features — ICLR 2025 Poster

Kumiko Tanaka-Ishii

2023–present: Full Professor , Waseda University (JP)

2016–2023: Full Professor , University of Tokyo

2012–2016: Full Professor , Kyushu University

2000–2012: Associate Professor , University of Tokyo

Papers (1)

Correlation Dimension of Autoregressive Large Language Models — NeurIPS 2025 poster

Kurt Keutzer

1998–present: Full Professor , University of California Berkeley (US)

1991–1998: Principal Researcher , Synopsys Inc. (US)

1984–1991: Researcher , Bell Labs (US)

1979–1984: PhD student , Indiana University at Bloomington (US)

1974–1978: Undergrad student , Maharishi International University (US)

Papers (1)

Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation — NeurIPS 2025 poster

Kush Bhatia

2022–present: Postdoc , Stanford University

2016–2022: PhD student , University of California Berkeley

2010–2014: Undergrad student , Indian Institute of Technology Delhi

Papers (1)

The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry — ICLR 2024 poster

Kushal Arora

2018–present: PhD student , McGill University

Papers (1)

Linearizing Large Language Models — COLM

Kwangjun Ahn

2024–present: Researcher , Microsoft (US)

2019–2024: PhD student , Massachusetts Institute of Technology (US)

Papers (1)

Linear attention is (maybe) all you need (to understand Transformer optimization) — ICLR 2024 poster

Kyle A. Johnsen

2019–present: PhD student , Georgia Institute of Technology

2015–2019: Undergrad student , Brigham Young University

Papers (1)

Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics — NeurIPS 2024 poster

Kyle Richardson

2018–present: Research Scientist , Allen Institute for Artificial Intelligence (US)

2011–2018: Doctoral Researcher , University of Stuttgart, University of Stuttgart (DE)

Papers (1)

Language Modeling by Language Models — NeurIPS 2025 spotlight

Lanyun Zhu

2025–present: Postdoc , Nanyang Technological University (SG)

2025–2025: Postdoc , City University of Hong Kong (HK)

2021–2025: PhD student , Singapore University of Technology and Design (SG)

2016–2020: Undergrad student , Beihang University (CN)

Papers (1)

Hybrid Mamba for Few-Shot Segmentation — NeurIPS 2024 poster

Lars Mikelsons

2018–present: Full Professor , University of Augsburg (DE)

2007–2011: PhD student , University of Duisburg-Essen (DE)

Papers (1)

Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximations — ICLR 2025 Poster

Le Gan

2025–present: Associate Professor , Nanjing University of Science and Technology (CN)

2018–2025: Researcher , Nanjing University (CN)

2015–2018: PhD student , Nanjing University (CN)

Papers (1)

Leveraging Conditional Dependence for Efficient World Model Denoising — NeurIPS 2025 poster

Le Viet Quan

2024–2026: MS student , Vietnam National University Hanoi (VN)

2020–2024: Undergrad student , Vietnam National University Hanoi (VN)

Papers (1)

Pseudo-Riemannian Graph Transformer — NeurIPS 2025 poster

Le Yu

2025–present: Researcher , Alibaba Group (CN)

2019–2024: PhD student , Beijing University of Aeronautics and Astronautics (CN)

2015–2019: Undergrad student , Beijing University of Aeronautics and Astronautics (CN)

Papers (1)

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free — NeurIPS 2025 oral

Lea M. Hadzic

2023–2027: Undergrad student , Computer Science Department, Stanford University (US)

Papers (1)

Exploring Diffusion Transformer Designs via Grafting — NeurIPS 2025 oral

Leandro Sánchez-Betancourt

2023–present: Researcher , University of Oxford

2022–2023: Lecturer , King's College London, University of London

2021–2021: Postdoc , Imperial College London

2017–2021: PhD student , University of Oxford

Papers (1)

Outlier-robust Kalman Filtering through Generalised Bayes — ICML 2024 Poster

Leena Chennuru Vankadara

2025–present: Lecturer , University College London, University of London (GB)

2023–2025: Applied Scientist II , Amazon Development Center Germany (DE)

2018–2022: PhD student , University of Tuebingen

Papers (1)

On Feature Learning in Structured State Space Models — NeurIPS 2024 poster

Lei Gu

2021–2027: Assistant Professor , mpi for heart and lung research (DE)

2019–2021: Instructor , Harvard Medical School, Harvard University (US)

Papers (1)

JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation Model — NeurIPS 2025 poster

Lei Qi

2020–present: Associate Professor , Southeast University (CN)

2015–2022: PhD student , nanjing university (CN)

2012–2015: MS student , Nanjing University of Science and Technology (CN)

2007–2011: Undergrad student , Nanjing Normal University (CN)

Papers (1)

START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation — NeurIPS 2024 poster

Lei Xie

2016–present: Full Professor , Zhejiang University (CN)

Papers (1)

MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection — NeurIPS 2024 poster

Lei Zhang

2021–present: Chief Scientist , International Digital Economy Academy (CN)

2001–2021: Principal Researcher , Microsoft (US)

1998–2001: PhD student , Tsinghua University (CN)

Papers (1)

PASS: Path-selective State Space Model for Event-based Recognition — NeurIPS 2025 poster

Lei Zhang

2024–present: PhD student , University of California, San Diego (US)

2021–2024: MS student , Zhejiang University (CN)

Papers (1)

Autoregressive Pretraining with Mamba in Vision — ICLR 2025 Poster

Lemeng Wu

2023–present: Researcher , Facebook (US)

2018–present: PhD student , University of Texas, Austin (US)

Papers (1)

Longhorn: State Space Models are Amortized Online Learners — ICLR 2025 Poster

Leo Kozachkov

2025–present: Assistant Professor , Brown University (US)

2024–2025: Postdoc , International Business Machines (US)

2022–2024: Postdoc , Massachusetts Institute of Technology

2017–2022: PhD student , Massachusetts Institute of Technology

2016–2017: Researcher , Rutgers University, New Brunswick

Papers (1)

Predictability Enables Parallelization of Nonlinear State Space Models — NeurIPS 2025 poster

Leo Schwinn

2023–present: Postdoc , Technical University of Munich (DE)

2023–2023: Postdoc , Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)

2019–2023: PhD student , Friedrich-Alexander Universität Erlangen-Nürnberg (FAU)

Papers (1)

Efficient Time Series Processing for Transformers and State-Space Models through Token Merging — ICML 2025 poster

Leon Bergen

2017–present: Associate Professor , University of California, San Diego (US)

2022–2023: Researcher , Google

2016–2017: Postdoc , Stanford University (US)

2010–2015: PhD student , Massachusetts Institute of Technology (US)

Papers (1)

Single-Pass Document Scanning for Question Answering — COLM 2025

Leon Götz

2024–present: PhD student , Technical University of Munich (DE)

2023–present: PhD student , Volkswagen AG (DE)

2020–2023: MS student , Technische Universität Carolo-Wilhelmina zu Braunschweig (DE)

2022–2022: Researcher , Stanford University (US)

2017–2021: Undergrad student , Technische Universität Carolo-Wilhelmina zu Braunschweig (DE)

Papers (1)

Efficient Time Series Processing for Transformers and State-Space Models through Token Merging — ICML 2025 poster

Leonid Karlinsky

2022–present: Principal Researcher , International Business Machines (US)

2015–2022: Staff Research Scientist , IBM Research AI (IL)

Papers (1)

Overflow Prevention Enhances Long-Context Recurrent LLMs — COLM 2025

Leonid Sigal

2022–present: Full Professor , University of British Columbia (CA)

2017–2022: Associate Professor , University of British Columbia (CA)

2010–2017: Senior Research Scientist , Disney Research

Papers (1)

Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance? — NeurIPS 2025 poster

Lequan Yu

2021–present: Assistant Professor , The University of Hong Kong (HK)

2019–2021: Postdoc , Stanford University (US)

2015–2019: PhD student , The Chinese University of Hong Kong (HK)

2011–2014: Undergrad student , Zhejiang University

Papers (1)

From Layers to States: A State Space Model Perspective to Deep Neural Network Layer Dynamics — ICLR 2025 Poster

Lerrel Pinto

2020–present: Assistant Professor , New York University (US)

2019–2020: Postdoc , University of California Berkeley (US)

2016–2019: PhD student , School of Computer Science, Carnegie Mellon University (US)

Papers (1)

Hierarchical State Space Models for Continuous Sequence-to-Sequence Modeling — ICML 2024 Poster

Lewei Lu

2019–present: Researcher , SenseTime (CN)

2017–2019: Researcher , Microsoft Research Asia (CN)

2014–2017: MS student , South China University of Technology (CN)

Papers (1)

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures — ICLR 2025 Spotlight

Leyang Cui

2022–2024: Researcher , Tencent AI Lab

2018–2022: PhD student , Zhejiang University

Papers (1)

Gated Slot Attention for Efficient Linear-Time Sequence Modeling — NeurIPS 2024 poster

Leyla Naz Candogan

2023–2027: PhD student , EPFL - EPF Lausanne (CH)

Papers (1)

Linear Attention for Efficient Bidirectional Sequence Modeling — NeurIPS 2025 poster

Li Fei-Fei

2017–present: Full Professor , Stanford University (US)

2012–2016: Associate Professor , Stanford University (US)

2009–2012: Assistant Professor , Stanford University (US)

2007–2009: Assistant Professor , Princeton University (US)

2005–2006: Assistant Professor , University of Illinois at Urbana-Champaign (US)

2000–2005: PhD student , California Institute of Technology (US)

1995–1999: Undergrad student , Princeton University (US)

Papers (1)

Exploring Diffusion Transformer Designs via Grafting — NeurIPS 2025 oral

Li Liang

2023–2027: PhD student , University of Western Australia (AU)

Papers (1)

CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation — NeurIPS 2025 poster

Li Nanbo

2024–present: Postdoc , King Abdullah University of Science and Technology (SA)

2018–2022: PhD student , University of Edinburgh (GB)

2016–2017: MS student , University of Edinburgh (GB)

Papers (1)

FACTS: A Factored State-Space Framework for World Modelling — ICLR 2025 Poster

Li Shen

2024–present: Associate Professor , Sun Yat-Sen University (CN)

2021–2024: Researcher , JD Explore Academy (CN)

2017–2021: Researcher , Tencent AI Lab (CN)

2013–2017: PhD student , South China University of Technology

Papers (1)

Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning? — NeurIPS 2024 poster

Li Wang

2023–2024: Researcher , IntSig (CN)

2022–2023: MS student , Edinburgh University, University of Edinburgh (GB)

Papers (1)

Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences — ICML 2024 Poster

Li Yuan

2022–present: Assistant Professor , Peking University (CN)

2017–2021: PhD student , National University of Singapore (SG)

2013–2017: Undergrad student , University of Science and Technology of China (CN)

Papers (1)

Spike-driven Transformer — NeurIPS 2023 poster

Li Zhang

2024–present: Full Professor , Fudan University (CN)

2020–2024: Associate Professor , Fudan University (CN)

2018–2020: Postdoc , University of Oxford (GB)

2014–2017: PhD student , Queen Mary University London (GB)

Papers (1)

DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States — NeurIPS 2024 poster

Liang Chen

2019–2021: Associate Professor , SUN YAT-SEN UNIVERSITY

2016–2019: Researcher , SUN YAT-SEN UNIVERSITY

2015–2016: Postdoc , Royal Melbourne Institute of Technology

2009–2015: PhD student , Zhejiang University

2005–2009: Undergrad student , Zhejiang University

Papers (1)

State Space Models on Temporal Graphs: A First-Principles Study — NeurIPS 2024 poster

Lianghui Zhu

2023–present: PhD student , Huazhong University of Science and Technology (CN)

2021–2023: MS student , Huazhong University of Science and Technology (CN)

Papers (1)

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model — ICML 2024 Poster

Lianyan Xu

2022–2025: Instructor , Fudan University (CN)

Papers (1)

Dual-Res Tandem Mamba-3D: Bilateral Breast Lesion Detection and Classification on Non-contrast Chest CT — NeurIPS 2025 poster

Liao Heng

2016–2024: Principal Researcher , , Tsinghua University

Papers (1)

MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected Layers — NeurIPS 2024 poster

Lichao Sun

2021–present: Assistant Professor , Lehigh University (US)

2016–2020: PhD student , University of Illinois, Chicago (US)

Papers (1)

Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling — NeurIPS 2024 poster

Lifang He

2025–present: Associate Professor , Lehigh University (US)

2019–2025: Assistant Professor , Lehigh University (US)

2017–2019: Postdoc , University of Pennsylvania (US)

2017–2018: Postdoc , Cornell University (US)

2014–2017: Postdoc , University of Illinois at Chicago (US)

2009–2014: PhD student , South China University of Technology (CN)

Papers (1)

A Generalizable Physics-Enhanced State Space Model for Long-Term Dynamics Forecasting in Complex Environments — ICML 2025 poster

Lihua Sun

2023–2025: Lecturer , East China University of Science and Technology (CN)

Papers (1)

CSV-Occ: Fusing Multi-frame Alignment for Occupancy Prediction with Temporal Cross State Space Model and Central Voting Mechanism — ICML 2025 poster

Lili Qiu

2022–present: Principal Researcher , Microsoft (CN)

2012–present: Full Professor , University of Texas at Austin (US)

Papers (1)

SCBench: A KV Cache-Centric Analysis of Long-Context Methods — ICLR 2025 Poster

Lili Yu

2025–present: Researcher , physical intelligence (US)

2021–2025: Researcher , Facebook (US)

2017–2021: Researcher , ASAPP INC (US)

2011–2017: PhD student , Massachusetts Institute of Technology (US)

Papers (1)

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length — NeurIPS 2024 poster

Lin Jin

2024–2027: MS student , Fudan University (CN)

Papers (1)

EventMG: Efficient Multilevel Mamba-Graph Learning for Spatiotemporal Event Representation — NeurIPS 2025 poster

Lin Li

2010–2015: PhD student , Zhejiang University

Papers (1)

MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected Layers — NeurIPS 2024 poster

Lin Song

2022–present: Researcher , Tencent AI Lab (CN)

2019–2022: PhD student , Xi'an Jiaotong University (CN)

Papers (1)

MambaTree: Tree Topology is All You Need in State Space Model — NeurIPS 2024 spotlight

Lin Wang

2024–present: Assistant Professor , Nanyang Technological University (SG)

2021–2024: Assistant Professor , Hong Kong University of Science and Technology (CN)

Papers (1)

PASS: Path-selective State Space Model for Event-based Recognition — NeurIPS 2025 poster

Lin Zeng

2015–2024: Intern , SUN YAT-SEN UNIVERSITY (CN)

Papers (1)

High-Dynamic Radar Sequence Prediction for Weather Nowcasting Using Spatiotemporal Coherent Gaussian Representation — ICLR 2025 Oral

Lin Zhang

2022–present: PhD student , Fudan University (CN)

2024–2025: Intern , StepFun (CN)

2018–2022: Undergrad student , Fudan University (CN)

Papers (1)

3DET-Mamba: Causal Sequence Modelling for End-to-End 3D Object Detection — NeurIPS 2024 poster

Lingxi Xie

2018–2025: Researcher , Huawei Technologies Ltd. (CN)

2016–2018: Postdoc , Johns Hopkins University (US)

2015–2016: Postdoc , University of California, Los Angeles (US)

2010–2015: PhD student , Tsinghua University (CN)

2006–2010: Undergrad student , Tsinghua University (CN)

Papers (1)

VMamba: Visual State Space Model — NeurIPS 2024 spotlight

Lingxiang Jia

2025–present: Researcher , Zhejiang University (CN)

2020–2025: PhD student , Zhejiang University (CN)

Papers (1)

Vision Mamba Mender — NeurIPS 2024 poster

Lingyan Mao

2012–present: Lecturer , Fudan University (CN)

Papers (1)

FAPEX: Fractional Amplitude-Phase Expressor for Robust Cross-Subject Seizure Prediction — NeurIPS 2025 spotlight

Lingyi Wang

2024–2029: PhD student , Virginia Polytechnic Institute and State University (US)

2020–2024: Undergrad student , Nanjing University of Posts and Telecommunications (CN)

Papers (1)

DMWM: Dual-Mind World Model with Long-Term Imagination — NeurIPS 2025 spotlight

Lingyi Yang

2023–2025: Postdoc , University of Oxford

2022–2024: Postdoc , Alan Turing Institute

2017–2022: PhD student , University of Oxford

Papers (1)

Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models — NeurIPS 2025 spotlight

Linjie Yang

2018–present: Research Scientist , ByteDance Inc. (US)

2016–2018: Research Scientist , Snap Inc. (US)

2012–2016: PhD student , The Chinese University of Hong Kong (HK)

Papers (1)

Autoregressive Pretraining with Mamba in Vision — ICLR 2025 Poster

Linqi Zhou

2024–present: Researcher , Luma AI (US)

2020–present: PhD student , Stanford University (US)

2016–2020: Undergrad student , University of California, Los Angeles (US)

Papers (1)

Deep Latent State Space Models for Time-Series Generation — ICML 2023 Poster

LinshuangDiao

2023–present: MS student , Xinjiang University (CN)

2018–2021: Undergrad student , Xuchang University

Papers (1)

ZigzagPointMamba: Spatial-Semantic Mamba for Point Cloud Understanding — NeurIPS 2025 poster

Liqun Ma

2023–2027: PhD student , Mohamed bin Zayed University of Artificial Intelligence (AE)

2020–2023: MS student , Institute of automation, Chinese academy of science, Chinese Academy of Sciences

2014–2018: Undergrad student , Tianjin University

Papers (1)

Bi-Mamba: Towards Accurate 1-Bit State Space Model — Accepted by TMLR

Lisa Schneckenreiter

2023–present: PhD student , Institute of Machine Learning, JKU Linz (AT)

Papers (1)

Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences — ICLR 2025 Poster

Litian Liu

2022–present: Researcher , Qualcomm Inc, QualComm (US)

2017–2021: PhD student , Massachusetts Institute of Technology (US)

2016–2017: MS student , Princeton University (US)

2012–2016: Undergrad student , The Chinese University of Hong Kong (HK)

Papers (1)

Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance? — NeurIPS 2025 poster

Liuzhicheng

2019–2024: Researcher , Huawei Technologies Ltd.

Papers (1)

DiJiang: Efficient Large Language Models through Compact Kernelization — ICML 2024 Oral

Liwei Yang

2018–present: Researcher , Institute of High Performance Computing, Singapore, A*STAR (SG)

2012–2016: PhD student , Nanyang Technological University (SG)

Papers (1)

Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling — NeurIPS 2024 poster

Liyong Wang

2024–present: PhD student , University of Science and Technology Beijing (CN)

2021–2024: MS student , Dalian University (CN)

Papers (1)

MVSMamba: Multi-View Stereo with State Space Model — NeurIPS 2025 poster

Longfei Zhang

2024–present: Lecturer , National University of Defense Technology (CN)

2018–2023: PhD student , National University of Defense Technology (CN)

Papers (1)

Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning? — NeurIPS 2024 poster

Longtian Bao

2024–2026: MS student , University of California, San Diego (US)

2020–2024: Undergrad student , University of California, San Diego (US)

Papers (1)

Single-Pass Document Scanning for Question Answering — COLM 2025

Lu Chen

2020–present: Full Professor , Zhejiang University (CN)

2019–2020: Associate Professor , Aalborg University, Aalborg University (DK)

2017–2019: Assistant Professor , Aalborg University, Aalborg University (DK)

2013–2016: PhD student , Zhejiang University (CN)

Papers (1)

Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach — NeurIPS 2025 poster

Lu Tian

2022–2024: Researcher , AMD (CN)

2019–2022: Researcher , Xilinx

2017–2019: Postdoc , Tsinghua University, Tsinghua University

2011–2017: PhD student , Tsinghua University, Tsinghua University

2007–2011: Undergrad student , Tsinghua University, Tsinghua University

Papers (1)

QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion — NeurIPS 2024 poster

Luc Van Gool

2022–2027: Full Professor , Sofia Un. St. Kliment Ohridski (BG)

1998–2024: Emeritus , ETH Zurich (CH)

1982–2024: Emeritus , KU Leuven (BE)

Papers (1)

StateSpaceDiffuser: Bringing Long Context to Diffusion World Models — NeurIPS 2025 poster

Luca Zappella

2020–present: Principal Researcher , Apple (ES)

2015–2020: Researcher , Apple (US)

2011–2013: Postdoc , Johns Hopkins University

2009–2011: PhD student , University of Girona, Spain

Papers (1)

Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall Capacity — ICML 2025 poster

Lucas Pinto

2021–present: Assistant Professor , Northwestern University

Papers (1)

Modeling state-dependent communication between brain regions with switching nonlinear dynamical systems — ICLR 2024 poster

Lucine L Oganesian

2020–present: PhD student , University of Southern California (US)

2020–2024: MS student , University of Southern California (US)

2012–2016: Undergrad student , University of California, Berkeley (US)

Papers (1)

Spectral Learning of Shared Dynamics Between Generalized-Linear Processes — NeurIPS 2024 poster

Lue Fan

2024–present: Assistant Professor , Institute of automation, Chinese academy of science, Chinese Academy of Sciences (CN)

2019–2024: PhD student , Institute of automation, Chinese academy of science, Chinese Academy of Sciences (CN)

2015–2019: Undergrad student , Xi'an Jiaotong University (CN)

Papers (1)

Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection — NeurIPS 2024 spotlight

Luke Zettlemoyer

2020–present: Full Professor , University of Washington (US)

2018–present: Researcher , Facebook (US)

2018–present: Researcher , Meta (GB)

2009–2010: Postdoc , University of Edinburgh (US)

2001–2009: PhD student , Massachusetts Institute of Technology

Papers (1)

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length — NeurIPS 2024 poster

Luning Wang

2024–2026: MS student , University of Michigan - Ann Arbor (US)

2020–2024: Undergrad student , Tsinghua University (CN)

Papers (1)

Evaluating Quantized Large Language Models — ICML 2024 Poster

Luyuan Xie

2022–2026: PhD student , Peking University (CN)

2020–2022: Researcher , Lenovo Group Limited (CN)

2019–2020: Researcher , Huawei Technologies Ltd. (CN)

2016–2019: MS student , Tsinghua University, Tsinghua University (CN)

2013–2016: Undergrad student , Northeastern University (CN)

Papers (1)

Dual-Res Tandem Mamba-3D: Bilateral Breast Lesion Detection and Classification on Non-contrast Chest CT — NeurIPS 2025 poster

Lvmin Zhang

2022–present: PhD student , Stanford University (US)

Papers (1)

Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation — NeurIPS 2025 poster

Maciej Chrabaszcz

2024–present: Researcher , NASK - National Research Institute (PL)

2023–present: PhD student , Warsaw University of Technology (PL)

2021–2023: MS student , Warsaw University of Technology (PL)

Papers (1)

Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation — NeurIPS 2025 poster

Mahan Fathi

2025–present: Researcher , NVIDIA (CA)

2023–2024: Researcher , Google DeepMind (CA)

2021–2024: MS student , University of Montreal (CA)

2021–2024: MS student , Mila (CA)

2022–2023: Researcher , Google Brain (CA)

2019–2019: Researcher , Aalto University (FI)

2013–2017: Undergrad student , Sharif University of Technology

Papers (1)

Block-State Transformers — NeurIPS 2023 poster

Mahdi Karami

2024–present: Researcher , Research, Google (US)

2023–present: Researcher , University of Waterloo (CA)

2022–2023: Researcher , Amazon (CA)

2014–2020: PhD student , University of Alberta (CA)

2005–2008: MS student , The University of Tehran, University of Tehran (IR)

2001–2005: Undergrad student , Isfahan University of Technology, University of Tehran (IR)

Papers (1)

MS-SSM: A Multi-Scale State Space Model for Efficient Sequence Modeling — COLM 2025

Mahsa Shoaran

2020–present: Assistant Professor , Swiss Federal Institute of Technology Lausanne (CH)

2018–2020: Assistant Professor , Cornell University (US)

Papers (1)

Linear Attention for Efficient Bidirectional Sequence Modeling — NeurIPS 2025 poster

Malik Hassanaly

2022–present: Researcher , The National Renewable Energy Laboratory (US)

2019–2022: Postdoc , The National Renewable Energy Laboratory

2015–2019: PhD student , University of Michigan

2013–2015: MS student , University of Texas, Austin

Papers (1)

Swift Hydra: Self-Reinforcing Generative Framework for Anomaly Detection with Multiple Mamba Models — ICLR 2025 Poster

Malyaban Bal

2021–2026: PhD student , Pennsylvania State University (US)

2024–2024: Research Intern , SRI International (US)

Papers (1)

P-SPIKESSM: HARNESSING PROBABILISTIC SPIKING STATE SPACE MODELS FOR LONG-RANGE DEPENDENCY TASKS — ICLR 2025 Poster

Manabu Okumura

2024–present: Full Professor , Institute of Science Tokyo (JP)

2009–present: Full Professor , Tokyo Institute of Technology, Tokyo Institute of Technology (JP)

Papers (1)

DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs — NeurIPS 2025 poster

Manbir S Gulati

2022–2025: Researcher , Leidos Inc (US)

2018–2022: Researcher , Applied Insight LLC

2013–2018: Undergrad student , Department of Computer Science, Princeton University

Papers (1)

Mamba State-Space Models Are Lyapunov-Stable Learners — Accepted by TMLR

Maneesh Agrawala

2015–present: Full Professor , Stanford University (US)

Papers (1)

Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation — NeurIPS 2025 poster

Manish Kumar Singh

2025–present: Research Engineer , Google (US)

2021–2024: Researcher , Qualcomm AI Research (US)

2019–2021: MS student , University of California, San Diego (US)

Papers (1)

PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer — ICLR 2025 Poster

Manling Li

2024–present: Assistant Professor , Northwestern University (US)

2023–2024: Postdoc , Stanford University (US)

2019–2023: PhD student , University of Illinois, Urbana Champaign

Papers (1)

Exploring Diffusion Transformer Designs via Grafting — NeurIPS 2025 oral

Maosong Sun

2001–present: Full Professor , Tsinghua University (CN)

2000–2004: PhD student , City University of Hong Kong (HK)

1994–2001: Associate Professor , Tsinghua University (CN)

1988–1992: Lecturer , Tsinghua University (CN)

1986–1988: MS student , Tsinghua University (CN)

1981–1986: Undergrad student , Tsinghua University (CN)

Papers (1)

Stuffed Mamba: Oversized States Lead to the Inability to Forget — COLM 2025

Marc Peter Deisenroth

2025–present: Principal Researcher , Google (GB)

2019–present: Full Professor , University College London (GB)

2024–2025: Full Professor , Alan Turing Institute (GB)

2018–2019: Senior Lecturer , Imperial College London

2015–2018: Lecturer , Imperial College London

Papers (1)

Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling — NeurIPS 2024 poster

Marcel Kollovieh

2023–present: PhD student , Department of Informatics, Technische Universität München (DE)

2022–2023: Intern , Amazon (DE)

2019–2022: MS student , Department of Informatics, Technische Universität München (DE)

2016–2019: Undergrad student , Department of Informatics, Technische Universität München (DE)

Papers (1)

Efficient Time Series Processing for Transformers and State-Space Models through Token Merging — ICML 2025 poster

Marcin Chochowski

2021–present: Researcher , NVIDIA

Papers (1)

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning — NeurIPS 2025 poster

Maria Rozman

2021–present: Lecturer , Hebrew University of Jerusalem (IL)

2017–2020: Undergrad student , Hebrew University of Jerusalem

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Marin Soljacic

2010–2021: Full Professor , Massachusetts Institute of Technology

Papers (1)

L$^2$M: Mutual Information Scaling Law for Long-Context Language Modeling — NeurIPS 2025 poster

Mario Sznaier

2006–present: Full Professor , Northeastern University (US)

Papers (1)

Generalization Error Analysis for Selective State-Space Models Through the Lens of Attention — NeurIPS 2025 poster

Mark Sandler

2006–present: Research Scientist , Google

2000–2006: PhD student , Cornell University

Papers (1)

Linear Transformers are Versatile In-Context Learners — NeurIPS 2024 poster

Mark Schöne

2020–present: PhD student , Technische Universität Dresden (DE)

2024–2024: Intern , Research, Microsoft (GB)

2019–2020: MS student , University of Cambridge (GB)

2014–2018: Undergrad student , Technische Universität Dortmund (DE)

Papers (1)

Implicit Language Models are RNNs: Balancing Parallelization and Expressivity — ICML 2025 spotlightposter

Markus Spanring

2023–2024: Postdoc , Johannes Kepler Universität Linz (AT)

2021–2023: Researcher , Institute of Advanced Research in Artificial Intelligence

Papers (1)

xLSTM: Extended Long Short-Term Memory — NeurIPS 2024 spotlight

Marten Lienen

2019–2025: PhD student , Technical University Munich (DE)

Papers (1)

UnHiPPO: Uncertainty-aware Initialization for State Space Models — ICML 2025 poster

Martin B Haugh

2017–present: Associate Professor , Imperial College London, Imperial College London

2014–2017: Associate Professor , Columbia University

Papers (1)

Counterfactual Analysis in Dynamic Latent State Models — ICML 2023 Poster

Martin Takáč

2021–present: Associate Professor , Mohamed bin Zayed University of Artificial Intelligence (AE)

2020–2021: Associate Professor , Lehigh University (US)

2014–2020: Assistant Professor , Lehigh University (US)

2010–2014: PhD student , University of Edinburgh (GB)

Papers (1)

Uncovering the Spectral Bias in Diagonal State Space Models — NeurIPS 2025 poster

Maryam Fazel

2019–present: Full Professor , University of Washington, Seattle (US)

2014–2019: Associate Professor , University of Washington, Seattle (US)

2008–2014: Assistant Professor , University of Washington, Seattle (US)

2002–2007: Researcher , California Institute of Technology (US)

1995–2002: PhD student , Stanford University (US)

Papers (1)

Gating is Weighting: Understanding Gated Linear Attention through In-context Learning — COLM 2025

Maryam M. Shanechi

2023–present: Full Professor , University of Southern California (US)

Papers (1)

Spectral Learning of Shared Dynamics Between Generalized-Linear Processes — NeurIPS 2024 poster

Masakazu Yoshimura

2021–present: Researcher , Sony Group Corporation (JP)

2019–2021: MS student , Tokyo University (JP)

2014–2019: Undergrad student , Tokyo University (JP)

Papers (1)

MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba — ICLR 2025 Poster

Massoud Pedram

1991–present: Professor , University of Southern California (US)

1986–1991: Student , University of California Berkeley (US)

Papers (1)

MambaExtend: A Training-Free Approach to Improve Long Context Extension of Mamba — ICLR 2025 Poster

Matan Danos

2019–2024: Researcher , ai21 (IL)

2019–2021: MS student , Weizmann Institute of Science (IL)

2015–2019: Undergrad student , Technion - Israel Institute of Technology, Technion (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Mathias Lechner

2022–2023: Postdoc , Massachusetts Institute of Technology

2018–2022: PhD student , Institute of Science and Technology Austria

2016–2017: MS student , TU Wien Vienna University of Technology

2012–2016: Undergrad student , TU Wien Vienna University of Technology

Papers (1)

State-Free Inference of State-Space Models: The *Transfer Function* Approach — ICML 2024 Poster

Matias Altamirano

2022–present: PhD student , University College London, University of London (GB)

2020–2021: MS student , Universidad de Chile (CL)

2014–2019: Undergrad student , Universidad de Chile (CL)

Papers (1)

Outlier-robust Kalman Filtering through Generalised Bayes — ICML 2024 Poster

Matt Jones

2008–present: Full Professor , University of Colorado Boulder (US)

2022–2023: Researcher , Google Research (US)

Papers (1)

Outlier-robust Kalman Filtering through Generalised Bayes — ICML 2024 Poster

Matthew G Perich

2022–present: Assistant Professor , Université de Montréal (CA)

2020–2022: Postdoc , Icahn School of Medicine at Mount Sinai

Papers (1)

Generalizable, real-time neural decoding with hybrid state-space models — NeurIPS 2025 poster

Matthew Harper Langston

2021–present: Researcher , Qualcomm Inc, QualComm (US)

2013–2022: Lecturer , NYU, New York University (US)

2012–2021: Researcher , Reservoir Labs, Inc. (US)

2011–2012: Researcher , Perceptive Pixel / Microsoft

2002–2011: PhD student , NYU, New York University

2008–2010: Researcher , Georgia Institute of Technology

1998–2002: MS student , NYU, New York University

1997–2000: Researcher , McKinsey & Company

1993–1997: B.A. , Bowdoin College

Papers (1)

PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer — ICLR 2025 Poster

Matthijs Van keirsbilck

2017–present: Research Scientist , NVIDIA

2015–2017: MS student , KU Leuven

2015–2016: MS student , Technical University Munich

2012–2015: Undergrad student , KU Leuven

Papers (1)

Hymba: A Hybrid-head Architecture for Small Language Models — ICLR 2025 Spotlight

Max Vladymyrov

2024–present: Research Scientist , Google DeepMind (US)

2016–2024: Research Scientist , Google Research (US)

2014–2016: Research Scientist , Yahoo (US)

2009–2014: PhD student , University of California, Merced (US)

Papers (1)

Linear Transformers are Versatile In-Context Learners — NeurIPS 2024 poster

Maxence Ernoult

2025–present: Researcher , Google DeepMind (FR)

2022–2024: Researcher , Rain AI (US)

2021–2022: Researcher , International Business Machines

2017–2020: PhD student , UPSud/INRIA University Paris-Saclay

2015–2016: MS student , University of Cambridge

2012–2016: Undergrad student , Ecole polytechnique

Papers (1)

Learning long range dependencies through time reversal symmetry breaking — NeurIPS 2025 oral

Maya Okawa

2023–present: Researcher , NTT Research, Inc.

2014–2023: Researcher , NTT, The University of Tokyo

2019–2022: PhD student , Kyoto University, Tokyo Institute of Technology

2012–2014: MS student , Tokyo University, Tokyo Institute of Technology

Papers (1)

Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing — ICML 2025 poster

Md Rifat Arefin

2021–2026: PhD student , Université de Montréal

2023–2023: Intern , Recursion Pharmaceuticals (CA)

2018–2019: Research Intern , Montreal Institute for Learning Algorithms, University of Montreal, University of Montreal

2017–2019: MS student , Kyung Hee University

2013–2017: Undergrad student , University of Dhaka

Papers (1)

Layer by Layer: Uncovering Hidden Representations in Language Models — ICML 2025 oral

Mehdi Azabou

2024–present: Postdoc , Columbia University (US)

2020–2024: PhD student , Georgia Institute of Technology

2019–2020: MS student , Georgia Institute of Technology

2017–2019: MS student , Centrale-Supelec

Papers (1)

Generalizable, real-time neural decoding with hybrid state-space models — NeurIPS 2025 poster

Mehdi Rezagholizadeh

2005–present: Principal Researcher , Advanced Micro Devices (CA)

2017–2025: Principal Researcher , Huawei Technologies Ltd. (CA)

Papers (1)

Zebra-Llama: Towards Extremely Efficient Hybrid Models — NeurIPS 2025 poster

Mehrdad Noori

2022–present: PhD student , École de technologie supérieure, Université du Québec (CA)

2016–2019: MS student , Iran University of Science and Technology Tehran, University of Tehran

2012–2016: Undergrad student , Razi University

Papers (1)

TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses — NeurIPS 2025 poster

Mel White

2022–2024: Postdoc , Rice University

2014–2022: PhD student , Cornell University

2011–2014: Undergrad student , Rensselaer Polytechnic Institute

Papers (1)

WaLRUS: Wavelets for Long range Representation Using State Space Methods — NeurIPS 2025 poster

Melih Kandemir

2021–present: Associate Professor , University of Southern Denmark (DK)

2020–2021: Adjunct Professor , Istanbul Technical University

2018–2021: Research Group Leader , Bosch

2017–2018: Assistant Professor , Ozyegin University

2013–2016: Postdoc , Heidelberg University

2008–2013: PhD student , Aalto University

Papers (1)

Cheap and Deterministic Inference for Deep State-Space Models of Interacting Dynamical Systems — Accepted by TMLR

Meng Wang

2012–present: Associate Professor , Rensselaer Polytechnic Institute (US)

Papers (1)

Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis — ICLR 2025 Poster

Mengzhen Liu

2025–2027: MS student , Peking University (CN)

2021–2024: Undergrad student , Beijing Jiaotong University (CN)

Papers (1)

RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation — NeurIPS 2024 poster

Mengzhu Wang

2019–present: PhD student , National University of Defense Technology (CN)

Papers (1)

Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning? — NeurIPS 2024 poster

Miao Zhang

2022–present: Full Professor , Harbin Institute of Technology (Shenzhen) (CN)

2021–2022: Assistant Professor , Aalborg University, Aalborg University (DK)

2020–2021: Postdoc , Monash University (AU)

2018–2021: PhD student , University of Technology Sydney (AU)

Papers (1)

Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression — NeurIPS 2025 poster

Michael Gokhman

2022–present: Researcher , AI21 Labs (IL)

2003–2006: Undergrad student , Tel Aviv University (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Michael Hahn

2022–2028: Assistant Professor , Universität des Saarlandes

2016–2022: PhD student , Stanford University

2015–2016: Researcher , Edinburgh University, University of Edinburgh

2014–2015: MS student , Eberhard-Karls-Universität Tübingen

2010–2015: Undergrad student , Eberhard-Karls-Universität Tübingen

Papers (1)

The Expressive Capacity of State Space Models: A Formal Language Perspective — NeurIPS 2024 poster

Michael Hersche

2025–present: Researcher , International Business Machines (CH)

2024–2025: Postdoc , International Business Machines (CH)

2021–2023: PhD student , International Business Machines

2018–2021: PhD student , Swiss Federal Institute of Technology

Papers (1)

Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models — NeurIPS 2025 spotlight

Michael K Kopp

2024–present: Principal Researcher , Nirmata Research LLP (KY)

2019–2023: Director , Institute of Advanced Research in Artificial Intelligence (IARAI)

Papers (1)

xLSTM: Extended Long Short-Term Memory — NeurIPS 2024 spotlight

Michael M. Bronstein

2024–present: Scientific Director , Aithyra (AT)

2022–present: Professor , University of Oxford (GB)

2019–2023: Head of Graph ML , Twitter

2018–2021: Professor , Imperial College London

2012–2019: Principal Engineer , Intel

2010–2019: Professor , Università della Svizzera Italiana

2016–2018: Professor , Tel Aviv University, Technion

Papers (1)

DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Models — Accepted by TMLR

Michael Wornow

2020–present: PhD student , Stanford University

2016–2020: Undergrad student , Harvard University

Papers (1)

Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHR Data — ICLR 2025 Poster

MICHAEL YU WANG

2024–present: Full Professor , Great Bay University (CN)

2003–2022: Full Professor , The Hong Kong University of Science and Technology

Papers (1)

Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL — NeurIPS 2024 poster

Michalis Titsias

2018–present: Research Scientist , Google DeepMind

2012–2018: Assistant Professor , Athens University of Economics and Business

Papers (1)

Kalman Filter for Online Classification of Non-Stationary Data — ICLR 2024 poster

Michelangelo Conserva

2024–present: Researcher , Google (GB)

2020–2024: PhD student , Queen Mary University London (GB)

Papers (1)

Posterior Sampling for Deep Reinforcement Learning — ICML 2023 Poster

Michele Santacatterina

2021–present: Assistant Professor , New York University (US)

Papers (1)

Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models — NeurIPS 2024 poster

Miguel Angel Fuentes Hernandez

2023–2025: MS student , Stanford University (US)

2017–2021: Undergrad student , Universidad Nacional Autónoma de México (MX)

Papers (1)

Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHR Data — ICLR 2025 Poster

Miguel Sarabia

2016–present: Researcher , Apple

2010–2016: PhD student , Imperial College London, Imperial College London

Papers (1)

Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall Capacity — ICML 2025 poster

Mikail Khona

2018–2023: PhD student , Massachusetts Institute of Technology

Papers (1)

Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing — ICML 2025 poster

Min-Hung Chen

2022–present: Research Scientist , NVIDIA (TW)

2022–2022: Research Engineer , Microsoft

2020–2021: AI Engineer , MediaTek Inc.

2014–2020: PhD student , Georgia Institute of Technology

2013–2014: Research Assistant , Academia Sinica

2010–2012: MS student , National Taiwan University

2006–2010: Undergrad student , National Taiwan University

Papers (1)

Hymba: A Hybrid-head Architecture for Small Language Models — ICLR 2025 Spotlight

Minfeng Xu

2018–present: Principal Researcher , Alibaba Group (CN)

2011–2018: Researcher , Toshiba Medical System China (CN)

Papers (1)

Dual-Res Tandem Mamba-3D: Bilateral Breast Lesion Detection and Classification on Non-contrast Chest CT — NeurIPS 2025 poster

Ming Li

2024–2027: Full Professor , Guangming Laboratory (CN)

2021–2024: PhD student , National University of Singapore (SG)

2019–2021: Researcher , Worcester Polytechnic Institute (US)

2018–2019: Researcher , University of North Carolina at Chapel Hill (US)

Papers (1)

Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking — NeurIPS 2025 poster

Minghan Li

2024–present: Postdoc , Harvard University (US)

2020–2024: PhD student , The Hong Kong Polytechnic University (HK)

2016–2019: MS student , Xi'an Jiaotong University (CN)

2012–2016: Undergrad student , Xinjiang University (CN)

Papers (1)

Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion — ICLR 2025 Poster

Minghao Han

2023–2026: Postdoc , Nanyang Technological University (SG)

2021–2022: Researcher , Swiss Federal Institute of Technology, Zurich

2017–2022: PhD student , Harbin Institue of Technology

2013–2017: Undergrad student , Harbin Institue of Technology

Papers (1)

MamKO: Mamba-based Koopman operator for modeling and predictive control — ICLR 2025 Spotlight

Mingjia Shi

2025–present: PhD student , University of Virginia (US)

2025–2025: Intern , Houmo AI (CN)

2022–2025: Intern , National University of Singapore (SG)

2021–2024: MS student , Sichuan University (CN)

Papers (1)

Pruning-Robust Mamba with Asymmetric Multi-Scale Scanning Paths — NeurIPS 2025 poster

Mingjie Sun

2019–2025: PhD student , School of Computer Science, Carnegie Mellon University (US)

2015–2019: Undergrad student , Tsinghua University

Papers (1)

Bi-Mamba: Towards Accurate 1-Bit State Space Model — Accepted by TMLR

Mingli Song

2015–present: Full Professor , Zhejiang University (CN)

2009–2014: Associate Professor , Zhejiang University (CN)

2006–2008: Lecturer , Zhejiang University (CN)

2002–2006: PhD student , Zhejiang University (CN)

Papers (1)

Vision Mamba Mender — NeurIPS 2024 poster

Mingsheng Li

2025–present: Researcher , Alibaba Group (CN)

Papers (1)

3DET-Mamba: Causal Sequence Modelling for End-to-End 3D Object Detection — NeurIPS 2024 poster

Mingsheng Long

2018–present: Associate Professor , Tsinghua University (CN)

2016–2018: Assistant Professor , Tsinghua University (CN)

2014–2015: Postdoc , University of California, Berkeley (US)

Papers (1)

Mobile Attention: Mobile-Friendly Linear-Attention for Vision Transformers — ICML 2024 Poster

Mingshuo Chen

2023–present: MS student , Beijing University of Posts and Telecommunications (CN)

Papers (1)

RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing — NeurIPS 2025 poster

Mingtian Zhang

2023–2026: Researcher , University College London (GB)

2019–2023: PhD student , University College London (GB)

2017–2018: MS student , University College London (GB)

Papers (1)

Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling — NeurIPS 2024 poster

Mingyu Yang

2019–2025: PhD student , University of Michigan - Ann Arbor (US)

Papers (1)

Zebra-Llama: Towards Extremely Efficient Hybrid Models — NeurIPS 2025 poster

Minhak Song

2020–present: Undergrad student , Korea Advanced Institute of Science & Technology (KR)

2025–2025: Exchange student , Department of Computer Science, University of Washington (US)

Papers (1)

Linear attention is (maybe) all you need (to understand Transformer optimization) — ICLR 2024 poster

Minjing Dong

2024–present: Assistant Professor , City University of Hong Kong (HK)

2020–2023: PhD student , University of Sydney

2018–2019: MS student , University of Sydney

Papers (1)

Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model — NeurIPS 2024 poster

Minseon Gwak

2021–2026: PhD student , Pohang University of Science and Technology (KR)

Papers (1)

Layer-Adaptive State Pruning for Deep State Space Models — NeurIPS 2024 poster

Minseung Lee

2025–2026: Researcher , Curation Labs (US)

2022–2024: MS student , KAIST (KR)

2015–2021: Undergrad student , Sung Kyun Kwan University

Papers (1)

Slot State Space Models — NeurIPS 2024 poster

Mithun George Jacob

2018–present: Researcher , Google (US)

2014–2018: Researcher , Bosch (US)

2010–2014: PhD student , Purdue University (US)

2009–2010: Researcher , Technicolor (US)

2007–2009: MS student , University of Pennsylvania, University of Pennsylvania (US)

Papers (1)

Linear Transformer Topological Masking with Graph Random Features — ICLR 2025 Poster

Mohamad Al Ahdab

2024–2025: Postdoc , Aalborg University (DK)

2020–2023: PhD student , Aalborg University (DK)

Papers (1)

Optimal Sensor Scheduling and Selection for Continuous-Discrete Kalman Filtering with Auxiliary Dynamics — ICML 2025 poster

Mohamad Hakam Shams Eddin

2022–present: PhD student , Rheinische Friedrich-Wilhelms Universität Bonn (DE)

2017–2020: MS student , Universität Stuttgart (DE)

Papers (1)

RiverMamba: A State Space Model for Global River Discharge and Flood Forecasting — NeurIPS 2025 poster

Mohamed S. Abdelfattah

2022–present: Assistant Professor , Cornell University (US)

2019–2022: Principal Scientist , Samsung AI Center

2016–2018: Senior Member of Technical Staff , Intel

Papers (1)

Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models — ICML 2025 poster

Mohammad Erfan Sadeghi

2022–2027: PhD student , University of Southern California (US)

2022–2024: MS student , University of Southern California (US)

2017–2021: Undergrad student , Sharif University of Technology (IR)

Papers (1)

MambaExtend: A Training-Free Approach to Improve Long Context Extension of Mamba — ICLR 2025 Poster

Mohammad Reza Rezaei

—–present: Postdoc , Department of Computer Science, University of Toronto (CA)

2020–2025: PhD student , University of Toronto (CA)

Papers (1)

Alternators For Sequence Modeling — Accepted by TMLR

Mohammad Reza Samsami

2021–present: MS student , Mila

2021–present: MS student , Université de Montréal

2016–2021: Undergrad student , Sharif University of Technology

Papers (1)

Mastering Memory Tasks with World Models — ICLR 2024 oral

Mohammad Shoeybi

2019–present: Director of Applied Resesrch , NVIDIA

2017–2019: Senior Research Engineer , Google

2016–2017: Research Scientist , Baidu

Papers (1)

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning — NeurIPS 2025 poster

Mona Schirmer

2022–2026: PhD student , University of Amsterdam (NL)

2021–2021: Intern , Bosch Center for Artificial Intelligence (DE)

2019–2021: MS student , Technische Universität Berlin (DE)

Papers (1)

Temporal Test-Time Adaptation with State-Space Models — Accepted by TMLR

Mor Zusman

2020–2025: MS student , Open University of Israel (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Moritz Haas

2021–present: PhD student , Eberhard-Karls-Universität Tübingen

2021–present: PhD student , Max Planck Institute for Intelligent Systems, Max-Planck Institute

2023–2024: Intern , Amazon

2018–2020: MS student , Ruprecht-Karls-Universität Heidelberg

2014–2018: Undergrad student , Ruprecht-Karls-Universität Heidelberg

Papers (1)

On Feature Learning in Structured State Space Models — NeurIPS 2024 poster

Morris Yau

2021–present: PhD student , Massachusetts Institute of Technology

Papers (1)

Learning Linear Attention in Polynomial Time — NeurIPS 2025 oral

Moshe Eliasof

2023–present: Postdoc , University of Cambridge (GB)

2019–2023: PhD student , Ben Gurion University of the Negev (IL)

2018–2019: MS student , Ben Gurion University of the Negev (IL)

2013–2017: Undergrad student , Technion, Technion (IL)

Papers (1)

Graph Adaptive Autoregressive Moving Average Models — ICML 2025 spotlightposter

Moslem Yazdanpanah

2023–2026: PhD student , École de technologie supérieure, Université du Québec (CA)

2019–2021: MS student , University of Kurdistan (IR)

Papers (1)

TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses — NeurIPS 2025 poster

Mostofa Patwary

2019–present: Principal Researcher , NVIDIA (US)

2017–2019: Researcher , Baidu

2013–2017: Researcher , Intel

Papers (1)

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning — NeurIPS 2025 poster

Muhammad Jehanzeb Mirza

2024–present: Postdoc , Massachusetts Institute of Technology (US)

Papers (1)

Overflow Prevention Enhances Long-Context Recurrent LLMs — COLM 2025

Mustafa Bozdag

2022–2027: PhD student , Northeastern University (US)

2017–2022: Undergrad student , Bilkent University (TR)

Papers (1)

Generalization Error Analysis for Selective State-Space Models Through the Lens of Attention — NeurIPS 2025 poster

Muti Kara

2020–2025: Undergrad student , Bilkent University (TR)

2024–2024: Intern , University of Michigan - Ann Arbor (US)

Papers (1)

Theoretical Insights into In-context Learning with Unlabeled Data — NeurIPS 2025 poster

Mutian He

2022–present: PhD student , EPFL - EPF Lausanne

2022–present: PhD student , Idiap Research Institute

2019–2022: MPhil student , The Hong Kong University of Science and Technology

2020–2021: Intern , Microsoft

2015–2019: Undergrad student , Beihang University

Papers (1)

Joint Fine-tuning and Conversion of Pretrained Speech and Language Models towards Linear Complexity — ICLR 2025 Poster

My T. Thai

2006–present: Full Professor , University of Florida (US)

Papers (1)

Swift Hydra: Self-Reinforcing Generative Framework for Anomaly Detection with Multiple Mamba Models — ICLR 2025 Poster

Myeongjae Jeon

2024–2024: Associate Professor , Pohang University of Science and Technology (KR)

2020–2024: Associate Professor , Ulsan National Institute of Science and Technology (KR)

2022–2022: Visiting Professor , Microsoft (US)

2018–2020: Assistant Professor , Ulsan National Institute of Science and Technology (KR)

2015–2018: Senior Research Engineer , Microsoft Research (US)

2014–2015: Senior Design Engineer , ARM Research (US)

2009–2014: PhD student , Rice University (US)

Papers (1)

Training Free Exponential Context Extension via Cascading KV Cache — ICLR 2025 Poster

Mónika Farsang

2022–present: PhD student , Technische Universität Wien (AT)

2019–2021: MS student , Technical University of Budapest (HU)

2015–2019: Undergrad student , Technical University of Budapest (HU)

Papers (1)

Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence Modeling — NeurIPS 2025 poster

N M Anoop Krishnan

2022–present: Associate Professor , Indian Institute of Technology Delhi

2017–2022: Assistant Professor , Indian Institute of Technology Delhi

Papers (1)

Latent Mamba Operator for Partial Differential Equations — ICML 2025 poster

Naama Gidron

2022–present: language data analyst , AI21 Labs (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Naiqi Li

2018–present: PhD student , Tsinghua University, Tsinghua University (CN)

Papers (1)

LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling — NeurIPS 2024 poster

Nan Jiang

2025–present: PhD student , University of Chicago (US)

2024–2025: Intern , Cornell University (US)

2019–2024: Undergrad student , University of California, San Diego (US)

2021–2022: Undergrad student , Peking University (CN)

Papers (1)

Is attention required for ICL? Exploring the Relationship Between Model Architecture and In-Context Learning Ability — ICLR 2024 poster

Nan Song

2023–present: PhD student , Fudan University (CN)

2022–2023: Intern , Megvii Technology Inc. (CN)

2019–2022: MS student , Wuhan University (CN)

Papers (1)

DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States — NeurIPS 2024 poster

Nan Zhang

2015–2025: Principal Researcher , Fujitsu Research and Development Center Co. Ltm. (CN)

2012–2015: MS student , East China University of Science and Technology (CN)

Papers (1)

Mamba Only Glances Once (MOGO): A Lightweight Framework for Efficient Video Action Detection — NeurIPS 2025 poster

Nanda H Krishna

2021–present: PhD student , Université de Montréal (CA)

2021–present: PhD student , Mila – Quebec AI Institute (CA)

2017–2021: Undergrad student , Sri Sivasubramaniya Nadar College of Engineering (IN)

Papers (1)

Generalizable, real-time neural decoding with hybrid state-space models — NeurIPS 2025 poster

Naren Ramakrishnan

1998–present: Full Professor , Virginia Tech (US)

Papers (1)

DMWM: Dual-Mind World Model with Long-Term Imagination — NeurIPS 2025 spotlight

Naser Kazemi

2024–present: Intern , INSAIT (BG)

2020–present: Undergrad student , Sharif University of Technology (IR)

Papers (1)

StateSpaceDiffuser: Bringing Long Context to Diffusion World Models — NeurIPS 2025 poster

Nathan Wilce

2023–present: Researcher , Recursal AI

2018–2021: Undergrad student , University of Essex

Papers (1)

RWKV-7 "Goose" with Expressive Dynamic State Evolution — COLM 2025

NAVEED AKHTAR

2023–present: Associate Professor , University of Melbourne (AU)

2019–2023: Assistant Professor , University of Western Australia (AU)

Papers (1)

CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation — NeurIPS 2025 poster

Nayoung Lee

2020–present: PhD student , University of Wisconsin - Madison (US)

2018–2020: MS student , Seoul National University (KR)

2014–2018: Undergrad student , Seoul National University (KR)

Papers (1)

Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks — ICML 2024 Poster

Nedko Savov

2023–present: Researcher , INSAIT (BG)

2016–2018: MS student , University of Amsterdam

Papers (1)

StateSpaceDiffuser: Bringing Long Context to Diffusion World Models — NeurIPS 2025 poster

Nguyen Hoang Khoi Do

2024–2028: PhD student , University of Florida (US)

Papers (1)

Swift Hydra: Self-Reinforcing Generative Framework for Anomaly Detection with Multiple Mamba Models — ICLR 2025 Poster

Ni Xu

2023–2026: MS student , Zhejiang University of Technology

Papers (1)

Alias-Free Mamba Neural Operator — NeurIPS 2024 poster

Nicholas Krämer

2023–present: Postdoc , Technical University of Denmark (DK)

2019–2024: PhD student , University of Tuebingen (DE)

2016–2019: MS student , University of Bonn (DE)

Papers (1)

Numerically Robust Fixed-Point Smoothing Without State Augmentation — Accepted by TMLR

Nicholas Roberts

2021–present: PhD student , University of Wisconsin-Madison (US)

2024–2025: Intern , Facebook (GB)

2024–2024: Intern , Together AI (US)

2023–2023: Intern , Microsoft (US)

2019–2021: MS student , Carnegie Mellon University (US)

2019–2019: Intern , Amazon (US)

2019–2019: Intern , UnifyID (US)

2015–2019: Undergrad student , University of California, San Diego (US)

Papers (1)

Pretrained Hybrids with MAD Skills — COLM 2025

Nicolas Menet

2024–2028: PhD student , ETHZ - ETH Zurich (CH)

2022–2024: MS student , ETHZ - ETH Zurich (CH)

2023–2023: MS student , Massachusetts Institute of Technology (US)

2018–2022: Undergrad student , ETHZ - ETH Zurich (CH)

Papers (1)

Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models — NeurIPS 2025 spotlight

Nicolas Zucchet

2021–present: PhD student , ETHZ - ETH Zurich (CH)

2021–2021: MS student , Institute für Psychologie, Universität Bern

2019–2021: MS student , ETHZ - ETH Zurich

2018–2019: MS student , Ecole polytechnique

2016–2018: Undergrad student , Ecole polytechnique

Papers (1)

Recurrent neural networks: vanishing and exploding gradients are not the end of the story — NeurIPS 2024 poster

Nigam Shah

2020–present: Full Professor , Stanford University (US)

Papers (1)

Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHR Data — ICLR 2025 Poster

Niket Patel

2025–2030: PhD student , New York University (US)

2021–2025: Undergrad student , University of California, Los Angeles (US)

2023–2023: Intern , ETHZ - ETH Zurich (CH)

Papers (1)

Layer by Layer: Uncovering Hidden Representations in Language Models — ICML 2025 oral

Niklas Schmidinger

2022–2025: PhD student , Johannes Kepler Universität Linz (AT)

2019–2021: MS student , Johannes Kepler University Linz

Papers (1)

Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences — ICLR 2025 Poster

Nikola Zubic

2022–present: PhD student , Department of Informatics, University of Zurich and ETH Zurich (CH)

2020–2021: MS student , University of Novi Sad (RS)

2016–2020: Undergrad student , University of Novi Sad (RS)

Papers (1)

Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theory — ICLR 2025 Poster

Niladri Dutta

2023–2025: MS student , Indian Institute of Science, Indian institute of science, Bangalore (IN)

Papers (1)

Latent Mamba Operator for Partial Differential Equations — ICML 2025 poster

Nils Strodthoff

2021–present: Associate Professor , Carl von Ossietzky Universität Oldenburg (DE)

2017–2021: Principal Researcher , Fraunhofer HHI (DE)

Papers (1)

Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models — Accepted by TMLR

Nima Tajbakhsh

2015–2016: Postdoc , Illinois Institute of Technology

2010–2015: PhD student , Arizona State University

Papers (1)

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning — NeurIPS 2025 poster

Nimrod Berman

2025–2025: Intern , Amazon (IL)

2023–2025: Intern , Bosch (IL)

2022–2025: PhD student , Ben Gurion University of the Negev (IL)

2021–2022: MS student , Ben-Gurion University of the Negev (IL)

Papers (1)

Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series — NeurIPS 2024 poster

Ning Ding

2020–present: PhD student , Peking University (CN)

2016–2020: Undergrad student , Shandong University (CN)

Papers (1)

MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected Layers — NeurIPS 2024 poster

Ning Liu

2025–present: Applied Scientist , Amazon (US)

2018–2025: Principal Machine Learning Scientist , Global Engineering and Materials, Inc. (US)

2014–2018: PhD student , University of Michigan - Ann Arbor

Papers (1)

Neural Interpretable PDEs: Harmonizing Fourier Insights with Attention for Scalable and Interpretable Physics Discovery — ICML 2025 poster

Ningyuan Huang

2024–present: Postdoc , Flatiron Institute (US)

2023–2024: Intern , Apple (US)

2020–2024: PhD student , Johns Hopkins University (US)

Papers (1)

Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall Capacity — ICML 2025 poster

Nir Ratner

2019–2020: MS student , University of Oxford (GB)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Noam Gat

2024–present: Researcher , AI21 Labs (IL)

2018–2020: MS student , Tel Aviv University (IL)

2008–2011: Undergrad student , Hebrew University of Jerusalem (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Noam Razin

2024–present: Postdoc , Princeton University (US)

2019–2024: PhD student , Tel Aviv University (IL)

2015–2018: Undergrad student , Hebrew University of Jerusalem (IL)

Papers (1)

The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels — NeurIPS 2025 spotlight

Noam Rozen

2020–2022: MS student , Weizmann Institute, Technion

2017–2019: Undergrad student , Hebrew University of Jerusalem, Technion

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Noga Mudrik

2021–present: PhD student , Johns Hopkins University (US)

2020–2023: MS student , Tel Aviv University (IL)

2016–2020: Undergrad student , Tel Aviv University (IL)

Papers (1)

Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics — NeurIPS 2024 poster

Octavia Camps

—–present: Professor , Northeastern University (US)

—–present: Full Professor , Northeastern University (US)

Papers (1)

Generalization Error Analysis for Selective State-Space Models Through the Lens of Attention — NeurIPS 2025 poster

Oded Fried

2022–present: Researcher , AI21 Labs (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Ohad Leshno

2024–present: MS student , Tel Aviv University (IL)

2016–2021: Undergrad student , Open University of Israel (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Oleksandra Prudnikova

2023–present: PhD student , Johannes Kepler Universität Linz (AT)

Papers (1)

xLSTM: Extended Long Short-Term Memory — NeurIPS 2024 spotlight

Oliver Eberle

2022–present: Postdoc , Technische Universität Berlin (DE)

2018–2022: PhD student , Technische Universität Berlin

Papers (1)

MambaLRP: Explaining Selective State Space Sequence Models — NeurIPS 2024 poster

Oluwatobi Olabiyi

2021–present: Director of Engineering , NVIDIA (US)

2017–2020: Senior Research Scientist Manager , Capital One Bank (US)

2015–2017: Senior Research Scientist , Toyota Research (US)

2014–2015: Principal Engineer , DCT Technology (US)

2011–2013: PhD student , Prairie View A&M University (US)

2010–2011: MS student , Prairie View A&M University (NG)

2006–2010: System Engineer and Manager , Nokia networks Nigeria (NG)

Papers (1)

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning — NeurIPS 2025 poster

Omer Antverg

—–present: MS student , Technion, Technion

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Omer Levy

2018–present: Research Scientist , Facebook

2020–2024: Senior Lecturer , Tel Aviv University

2016–2018: Postdoc , University of Washington

2012–2016: PhD student , Bar-Ilan University

Papers (1)

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length — NeurIPS 2024 poster

Omid G. Sani

2020–present: Researcher , University of Southern California

2015–2020: PhD student , University of Southern California

2013–2015: MS student , Sharif University of Technology, Sharif University of Technology

2009–2013: Undergrad student , Sharif University of Technology, Sharif University of Technology

Papers (1)

Spectral Learning of Shared Dynamics Between Generalized-Linear Processes — NeurIPS 2024 poster

Omri Abend

2020–present: Associate Professor , Hebrew University of Jerusalem

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Omri Azencot

2020–2025: Assistant Professor , Ben-Gurion University of the Negev (IL)

2017–2020: Adjunct Assistant Professor , University of California, Los Angeles

2011–2017: PhD student , Technion, Technion

Papers (1)

Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series — NeurIPS 2024 poster

Opher Lieber

2020–present: Principal Researcher , AI21 Labs (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Or Dagan

2018–present: Full Professor , AI21 (IL)

2015–2019: Undergrad student , Hebrew University of Jerusalem

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Orhan Firat

2017–present: Research Scientist , Google

2011–2017: PhD student , METU

Papers (1)

Block-State Transformers — NeurIPS 2023 poster

Oriol Mayné i Comas

2024–present: Undergraduate researcher , Massachusetts Institute of Technology (US)

2020–present: Undergrad student , Universitat Politècnica de Catalunya (ES)

Papers (1)

L$^2$M: Mutual Information Scaling Law for Long-Context Language Modeling — NeurIPS 2025 poster

Orit Cohavi

2022–present: Algorithm Developer , AI21 Labs (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Orr Krupnik

2025–present: Researcher , Tzafon (US)

2017–2025: PhD student , Technion - Israel Institute of Technology, Technion - Israel Institute of Technology (IL)

2022–2022: Intern , Bosch (IL)

2019–2019: Intern , Osaro Inc. (US)

2013–2017: Undergrad student , Technion - Israel Institute of Technology, Technion - Israel Institute of Technology (IL)

Papers (1)

MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning — ICLR 2024 poster

Orren Karniol-Tambour

2018–present: PhD student , Princeton University

2013–2015: MS student , Stanford University

Papers (1)

Modeling state-dependent communication between brain regions with switching nonlinear dynamical systems — ICLR 2024 poster

Osafumi Nakayama

1998–present: Researcher , Fujitsu Limited (JP)

1994–1997: PhD student , Osaka University, Graduate School of Enginerring (JP)

1990–1992: MS student , Osaka University, Graduate School of Enginerring (JP)

1986–1990: Undergrad student , Osaka University (JP)

Papers (1)

Mamba Only Glances Once (MOGO): A Lightweight Framework for Efficient Video Action Detection — NeurIPS 2025 poster

Oscar Skean

2021–present: PhD student , University of Kentucky (US)

Papers (1)

Layer by Layer: Uncovering Hidden Representations in Language Models — ICML 2025 oral

Oubo Ma

2022–2026: PhD student , Zhejiang University (CN)

Papers (1)

Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning? — NeurIPS 2024 poster

Owen M Dugan

2024–present: PhD student , Stanford University (US)

2021–2024: Undergrad student , Massachusetts Institute of Technology

Papers (1)

Towards Learning High-Precision Least Squares Algorithms with Sequence Models — ICLR 2025 Poster

Padhraic Smyth

2004–present: Full Professor , University of California, Irvine (US)

1998–2004: Associate Professor , University of California, Irvine

1996–1998: Assistant Professor , University of California, Irvine

1988–1996: Member of Technical Staff , Jet Propulsion Laboratory

1985–1988: PhD student , California Institute of Technology

1984–1985: MS student , California Institute of Technology

1980–1984: Undergrad student , National University of Ireland, Galway

Papers (1)

Deep Continuous-Time State-Space Models for Marked Event Sequences — NeurIPS 2025 spotlight

Pan Li

2023–present: Assistant Professor , Georgia Institute of Technology

2020–present: Assistant Professor , Purdue University

2019–2020: Postdoc , Computer Science Department, Stanford University

2015–2019: PhD student , University of Illinois, Urbana Champaign

Papers (1)

Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing — ICLR 2025 Poster

Pan Zhou

2024–present: Assistant Professor , Singapore Management University (SG)

2021–2023: senior research scientist , Sea Group (SG)

2019–2021: research scientist , SalesForce.com (SG)

2020–2020: Intern , Princeton University (US)

2020–2020: Intern , Carnegie Mellon University (US)

2016–2019: PhD student , national university of singaore, National University of Singapore (SG)

2018–2018: Intern , Harbin Institute of Technology (CN)

2013–2016: MS student , Peking University (CN)

Papers (1)

MVGamba: Unify 3D Content Generation as State Space Sequence Modeling — NeurIPS 2024 poster

Panpan Zhang

2021–present: PhD student , National University of Singapore (SG)

2018–2021: MS student , Fudan University

2014–2018: Undergrad student , East China University of Science and Technology

Papers (1)

Pruning-Robust Mamba with Asymmetric Multi-Scale Scanning Paths — NeurIPS 2025 poster

Parminder Bhatia

2023–present: Principal Researcher , GEHC (US)

2018–2023: Principal Researcher , Amazon

Papers (1)

Deep Continuous-Time State-Space Models for Marked Event Sequences — NeurIPS 2025 spotlight

Patrick Forré

2024–present: Associate Professor , University of Amsterdam (NL)

2019–2024: Assistant Professor , University of Amsterdam (NL)

2016–2019: Postdoc , University of Amsterdam (NL)

2008–2016: PhD/Postdoc , University of Regensburg (DE)

2012–2013: Postdoc , Tokyo University (JP)

Papers (1)

Deep Gaussian Markov Random Fields for Graph-Structured Dynamical Systems — NeurIPS 2023 poster

Patrick M Blies

2024–present: Researcher , NXAI GmbH (AT)

2018–2024: Research Engineer , EnliteAI GmbH (AT)

2017–2018: Postdoc , Institute of Science and Technology Austria

2012–2017: PhD student , University of Vienna

2010–2012: MS student , Ruhr-Universtät Bochum

Papers (1)

xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference — ICML 2025 poster

Patrick Podest

2025–present: PhD student , Johannes Kepler Universität Linz (AT)

2021–2024: MS student , Johannes Kepler Universität Linz (AT)

2015–2020: Undergrad student , Technische Universität Wien (AT)

Papers (1)

TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning — NeurIPS 2025 poster

Patrik Reizinger

2021–present: PhD student , Eberhard-Karls-Universität Tübingen (DE)

2019–2021: MS student , Technical University of Budapest

2015–2019: Undergrad student , Technical University of Budapest

Papers (1)

Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD Prompts — NeurIPS 2024 spotlight

Pau Rodriguez

2022–present: Researcher , Apple (ES)

2022–2022: Researcher , ServiceNow Research

2019–2022: Researcher , Element AI

2015–2019: PhD student , Computer Vision Center, Universitat Autònoma de Barcelona

2015–2019: PhD student , Universitat Autonoma de Barcelona

Papers (1)

Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall Capacity — ICML 2025 poster

Paul F Roysdon

2020–2025: Principal Researcher , Leidos (US)

2015–2020: Principal Researcher , US Department of Defense

2013–2017: PhD student , University of California, Riverside

2005–2015: Principal Researcher , Composite Engineering Inc

2013–2014: MS student , University of California, Riverside

2010–2011: MS student , University of California, Davis

2009–2010: MS student , Von Karman Institute of Fluid Dynamics

1999–2004: Undergrad student , University of California, Davis

Papers (1)

Mamba State-Space Models Are Lyapunov-Stable Learners — Accepted by TMLR

Paul Schwerdtner

2023–2025: Postdoc , New York University (US)

2018–2023: PhD student , Technische Universität Berlin (DE)

Papers (1)

Hankel Singular Value Regularization for Highly Compressible State Space Models — NeurIPS 2025 poster

Paulo Rauber

2020–present: Lecturer , Queen Mary University London

2017–2020: Postdoc , IDSIA

Papers (1)

Posterior Sampling for Deep Reinforcement Learning — ICML 2023 Poster

Peer Nagy

2021–2025: PhD student , University of Oxford, University of Oxford (GB)

2021–2021: Intern , Man Group (AHL)

2018–2020: MS student , University of Oxford

Papers (1)

LOB-Bench: Benchmarking Generative AI for Finance - an Application to Limit Order Book Data — ICML 2025 poster

Peihao Wang

2021–2026: PhD student , University of Texas, Austin (US)

2017–2021: Undergrad student , ShanghaiTech University (CN)

Papers (1)

Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing — ICLR 2025 Poster

Peilin Zhong

2025–present: Researcher , Meta (US)

2021–2025: Researcher , Google (US)

2016–2021: PhD student , Columbia University (US)

Papers (1)

MS-SSM: A Multi-Scale State Space Model for Efficient Sequence Modeling — COLM 2025

Pekka Marttinen

2018–present: Associate Professor , Aalto University (FI)

2004–2008: PhD student , University of Helsinki (FI)

Papers (1)

Identifying latent state transitions in non-linear dynamical systems — ICLR 2025 Poster

Peng Lu

2020–2025: PhD student , University of Montreal (CA)

2016–2019: MS student , University of Montreal

Papers (1)

Mamba Modulation: On the Length Generalization of Mamba Models — NeurIPS 2025 poster

Peng Mi

2020–2023: MS student , Xiamen University

Papers (1)

State space models can express $n$-gram languages — Accepted by TMLR

Peng Wang

2019–present: Research Scientist , Bytedance US AILab (US)

2017–2019: Research Scientist , Baidu

2013–2017: PhD student , University of California, Los Angeles

2010–2013: MS student , Peking University

2006–2010: Undergrad student , Peking University

Papers (1)

Autoregressive Pretraining with Mamba in Vision — ICLR 2025 Poster

Peng Ye

2024–present: Postdoc , The Chinese University of Hong Kong (HK)

2020–2024: PhD student , Fudan University (CN)

Papers (1)

Revisiting Convolution Architecture in the Realm of DNA Foundation Models — ICLR 2025 Poster

Peng Zhou

2023–present: CTO , LuxiTech Co., Ltd (CN)

2017–2022: PhD student , University of California, Santa Cruz (US)

2012–2016: Undergrad student , Huazhong University of Science and Technology (CN)

Papers (1)

Gated Slot Attention for Efficient Linear-Time Sequence Modeling — NeurIPS 2024 poster

Pengfei Li

2025–2028: PhD student , Harbin Institute of Technology (CN)

2025–2025: Intern , Shanghai Artificial Intelligence Laboratory (CN)

2023–2025: MS student , Harbin Institute of Technology (CN)

Papers (1)

Exploring Adversarial Robustness of Deep State Space Models — NeurIPS 2024 poster

Pengju An

2023–2026: MS student , Peking University (CN)

2019–2023: Undergrad student , Southeast University (CN)

Papers (1)

RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation — NeurIPS 2024 poster

Pengxiao Lin

—–present: PhD student , Shanghai Jiaotong University

Papers (1)

Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data — NeurIPS 2025 spotlight

Peter Clark

2014–present: Senior Research Director , Allen Institute for Artificial Intelligence (US)

Papers (1)

Language Modeling by Language Models — NeurIPS 2025 spotlight

Peter E. Latham

2004–2021: Full Professor , University College London

Papers (1)

Training Dynamics of In-Context Learning in Linear Attention — ICML 2025 spotlightposter

Peter Stone

2019–present: Principal Researcher , Sony AI (US)

2012–present: Full Professor , University of Texas, Austin (US)

Papers (1)

Longhorn: State Space Models are Amortized Online Learners — ICLR 2025 Poster

Philip N. Garner

2007–present: Senior Researcher , Idiap Research Institute

Papers (1)

Joint Fine-tuning and Conversion of Pretrained Speech and Language Models towards Linear Complexity — ICLR 2025 Poster

Philip Torr

2013–present: Full Professor , University of Oxford (GB)

Papers (1)

Universal In-Context Approximation By Prompting Fully Recurrent Models — NeurIPS 2024 poster

Philipp Becker

2020–present: PhD student , Karlsruhe Institute of Technology (DE)

2024–2025: Intern , Samsung (GB)

2023–2024: Researcher , FZI Forschungszentrum Informatik (DE)

2019–2019: PhD student , Bosch (DE)

2016–2019: MS student , TU Darmstadt (DE)

2012–2016: Undergrad student , TU Darmstadt (DE)

Papers (1)

On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning — Accepted by TMLR

Philipp Froehlich

2021–present: PhD student , Technische Universität Darmstadt (DE)

Papers (1)

Graph Structure Inference with BAM: Neural Dependency Processing via Bilinear Attention — NeurIPS 2024 poster

Philipp Hennig

2018–present: Full Professor , University of Tübingen (DE)

2016–2022: Adjunct Professor , Max Planck Institute for Intelligent Systems, Max-Planck Institute (DE)

2011–2018: Associate Professor , Max Planck Institute for Intelligent Systems, Max-Planck Institute (DE)

2011–2016: Associate Professor , Max Planck Institute for Intelligent Systems

2007–2011: PhD student , University of Cambridge (GB)

2001–2007: MS student , University of Heidelberg (DE)

Papers (1)

The Rank-Reduced Kalman Filter: Approximate Dynamical-Low-Rank Filtering In High Dimensions — NeurIPS 2023 poster

Philipp Seidl

2019–present: PhD student , Johannes Kepler University Linz

Papers (1)

Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences — ICLR 2025 Poster

Philippe Langlais

2009–present: Full Professor , Université de Montréal (CA)

Papers (1)

Mamba Modulation: On the Length Generalization of Mamba Models — NeurIPS 2025 poster

Pierre-David Letourneau

2021–present: Researcher , Qualcomm Inc, QualComm

Papers (1)

PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer — ICLR 2025 Poster

Pierre-Luc Bacon

2020–present: Assistant Professor , University of Montreal

2018–2019: Postdoc , Stanford University

2013–2018: PhD student , McGill University

2011–2013: MS student , McGill University

2008–2011: Undergrad student , McGill University

Papers (1)

Block-State Transformers — NeurIPS 2023 poster

Pieter-Jan Hoedt

2024–2030: Postdoc , Johannes Kepler University (AT)

2018–2024: PhD student , Johannes Kepler University (AT)

2018–2021: Instructor , Medical University of Vienna (AT)

Papers (1)

Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences — ICLR 2025 Poster

Pin-Yu Chen

2022–present: Principal Researcher , International Business Machines (US)

2016–2022: Research Staff Member , International Business Machines (US)

2012–2016: PhD student , University of Michigan (US)

2009–2011: MS student , National Taiwan University (TW)

2005–2009: Undergrad student , National Chiao Tung University (TW)

Papers (1)

Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis — ICLR 2025 Poster

Pingfan Su

2022–2026: PhD student , London School of Economics and Political Science, University of London (GB)

Papers (1)

AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees — NeurIPS 2025 poster

Pingzhao Hu

2023–present: Associate Professor , University of Toronto (CA)

2022–present: Associate Professor , University of Western Ontario (CA)

2013–2023: Assistant Professor , University of Toronto (CA)

2020–2022: Associate Professor , University of Manitoba (CA)

2014–2020: Assistant Professor , University of Manitoba (CA)

2004–2014: Manager , The Hospital for Sick Children (SickKids) (CA)

2005–2012: PhD student , York University (CA)

Papers (1)

Structure-Aware Fusion with Progressive Injection for Multimodal Molecular Representation Learning — NeurIPS 2025 poster

Pol Puigdemont

2025–2029: PhD student , EPFL (CH)

2023–2024: Undergrad student , EPFL - EPF Lausanne (CH)

2023–2024: Intern , Universidad Politécnica de Cataluna (ES)

2020–2024: Undergrad student , Universidad Politécnica de Cataluna (ES)

Papers (1)

Linear Attention for Efficient Bidirectional Sequence Modeling — NeurIPS 2025 poster

PooGyeon Park

1996–2030: Full Professor , Pohang University of Science and Technology (KR)

Papers (1)

Layer-Adaptive State Pruning for Deep State Space Models — NeurIPS 2024 poster

Pragaash Ponnusamy

2023–present: Principal Researcher , Together AI (US)

2017–2023: Researcher , Amazon (US)

Papers (1)

Mechanistic Design and Scaling of Hybrid Architectures — ICML 2024 Poster

Pragya Srivastava

2024–present: Researcher , Google DeepMind (IN)

Papers (1)

Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing — ICLR 2025 Poster

Prasanna Mayilvahanan

2022–2025: PhD student , Eberhard-Karls-Universität Tübingen (DE)

2022–2025: PhD student , Max Planck Institute for Intelligent Systems, Max-Planck Institute (DE)

2024–2024: Intern , Apple (FR)

2021–2021: MS student , ETHZ - ETH Zurich (CH)

2019–2021: MS student , Universita della Svizzera Italiana (CH)

2011–2015: Undergrad student , Indian Institute of Technology, Guwahati

Papers (1)

LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws — ICML 2025 poster

Prathosh AP

2021–present: Assistant Professor , Indian Institute of Science, Indian institute of science, Bangalore (IN)

2017–2021: Assistant Professor , Indian Institute of Technology, Delhi

Papers (1)

Latent Mamba Operator for Partial Differential Equations — ICML 2025 poster

Prayag Tiwari

2024–present: Associate Professor , Halmstad University (SE)

2022–2024: Assistant Professor , Halmstad University (SE)

2021–2022: Postdoc , Aalto University (FI)

2017–2020: PhD student , University of Padua (IT)

Papers (1)

DyPolySeg: Taylor Series-Inspired Dynamic Polynomial Fitting Network for Few-shot Point Cloud Semantic Segmentation — ICML 2025 poster

Qi An

2022–present: Associate Professor , Tokyo University (JP)

Papers (1)

State-Free Inference of State-Space Models: The *Transfer Function* Approach — ICML 2024 Poster

Qi Bi

2025–present: Postdoc , Utrecht University (NL)

2024–2025: Lecturer , University of Amsterdam (NL)

2020–2024: PhD student , University of Amsterdam (NL)

2017–2020: MS student , Wuhan University (CN)

2013–2017: Undergrad student , Wuhan University (CN)

Papers (1)

Samba: Severity-aware Recurrent Modeling for Cross-domain Medical Image Grading — NeurIPS 2024 poster

Qi Lv

2023–present: PhD student , Harbin Institute of Technology (CN)

2020–2023: MS student , Soochow University (CN)

Papers (1)

Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL — NeurIPS 2024 poster

Qi Xie

2023–present: Associate Professor , Xi'an Jiaotong University (CN)

2020–2023: Assistant Professor , Xi'an Jiaotong University (CN)

2015–2020: PhD student , Xi'an Jiaotong University (CN)

2013–2015: MS student , Xi'an Jiaotong University (CN)

2009–2013: Undergrad student , Xi'an Jiaotong University (CN)

Papers (1)

Polyline Path Masked Attention for Vision Transformer — NeurIPS 2025 spotlight

Qi Zhu

2020–present: PhD student , University of Science and Technology of China (CN)

Papers (1)

FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining — ICML 2025 poster

Qian Liu

2024–present: Researcher , TikTok (SG)

2022–2023: Researcher , Sea AI Lab (SG)

2017–2022: PhD student , Beihang University (CN)

Papers (1)

ZeCO: Zero-Communication Overhead Sequence Parallelism for Linear Attention — NeurIPS 2025 poster

Qian Zhang

2017–present: Researcher , Horizon Robotics (CN)

2016–2017: Researcher , Alibaba Group (CN)

2014–2016: Researcher , Samsung (CN)

2011–2014: PhD student , Institute of Automation, Chinese Academy of Sciences (CN)

2008–2011: MS student , Central South University (CN)

2004–2008: Undergrad student , Central South University (CN)

Papers (1)

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model — ICML 2024 Poster

qiang liu

2018–2025: Assistant Professor , University of Texas, Austin (US)

2015–2018: Assistant Professor , Dartmouth College

2014–2015: Postdoc , Massachusetts Institute of Technology

2008–2014: PhD student , University of California, Irvine

Papers (1)

Longhorn: State Space Models are Amortized Online Learners — ICLR 2025 Poster

Qiang Qu

2021–present: PhD student , The University of Sydney (AU)

2016–2020: Undergrad student , The University of Sydney (AU)

Papers (1)

State space models can express $n$-gram languages — Accepted by TMLR

Qianhui Wu

2021–present: Researcher , Microsoft (US)

2016–2021: PhD student , Tsinghua University, Tsinghua University (CN)

2012–2016: Undergrad student , Tsinghua University, Tsinghua University (CN)

Papers (1)

SCBench: A KV Cache-Centric Analysis of Long-Context Methods — ICLR 2025 Poster

Qiankun Liu

2024–present: Assistant Professor , University of Science and Technology Beijing (CN)

2022–2024: Postdoc , Beijing Institute of Technology (CN)

2017–2022: PhD student , University of Science and Technology of China

Papers (1)

MVSMamba: Multi-View Stereo with State Space Model — NeurIPS 2025 poster

Qianxiong Xu

2024–2025: Postdoc , Nanyang Technological University (SG)

2020–2024: PhD student , Nanyang Technological University (SG)

2016–2020: Undergrad student , Nanjing University of Information Science and Technology (CN)

Papers (1)

Hybrid Mamba for Few-Shot Segmentation — NeurIPS 2024 poster

Qihao Duan

2024–present: PhD student , Charité - Universitätsmedizin Berlin (DE)

Papers (1)

JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation Model — NeurIPS 2025 poster

Qihao Xu

2025–present: PhD student , Harbin Institute of Technology (CN)

2022–2025: MS student , Harbin Institute of Technology (CN)

Papers (1)

Hierarchical Information Aggregation for Incomplete Multimodal Alzheimer's Disease Diagnosis — NeurIPS 2025 poster

Qiming Hu

2022–2026: PhD student , Tianjin University (CN)

Papers (1)

MODEM: A Morton-Order Degradation Estimation Mechanism for Adverse Weather Image Recovery — NeurIPS 2025 poster

Qing Ye

2015–2025: Lecturer , Sichuan University (CN)

Papers (1)

Pruning-Robust Mamba with Asymmetric Multi-Scale Scanning Paths — NeurIPS 2025 poster

Qingdong He

2021–present: Researcher , Tencent Youtu Lab (CN)

Papers (1)

MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection — NeurIPS 2024 poster

Qinghao Hu

2024–present: Postdoc , Massachusetts Institute of Technology (US)

2020–2023: PhD student , Nanyang Technological University

2019–2020: MS student , National University of Singapore

2014–2018: Undergrad student , Zhejiang University

Papers (1)

Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search — NeurIPS 2025 poster

Qingming Huang

2003–present: Full Professor , University of Chinese Academy of Sciences (CN)

Papers (1)

Modeling Language Tokens as Functionals of Semantic Fields — ICML 2024 Poster

Qingshan Xu

2022–2025: Research Fellow , Nanyang Technological University (SG)

2020–2021: Visiting PhD student , Department of Computer Science, ETHZ - ETH Zurich (CH)

2016–2021: PhD student , Huazhong University of Science and Technology (CN)

Papers (1)

MVGamba: Unify 3D Content Generation as State Space Sequence Modeling — NeurIPS 2024 poster

Qingxiao Zheng

2024–present: Postdoc , State University of New York at Buffalo (US)

2019–2024: PhD student , University of Illinois at Urbana-Champaign (US)

Papers (1)

Sub-Sequential Physics-Informed Learning with State Space Model — ICML 2025 poster

Qingzhu Zhang

2024–2027: MS student , Southern University of Science and Technology (CN)

2020–2024: Undergrad student , Shanghai University (CN)

Papers (1)

Multi-dataset Joint Pre-training of Emotional EEG Enables Generalizable Affective Computing — NeurIPS 2025 poster

Qinshuo Liu

2021–2025: PhD student , University of Hong Kong (HK)

Papers (1)

From Layers to States: A State Space Model Perspective to Deep Neural Network Layer Dynamics — ICLR 2025 Poster

Qiong Tang

2022–2025: MS student , Fudan University (CN)

2018–2022: Undergrad student , East China Normal University (CN)

Papers (1)

Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures — ICLR 2025 Poster

Qirui Zheng

2022–2026: Undergrad student , University of California, San Diego (US)

Papers (1)

Single-Pass Document Scanning for Question Answering — COLM 2025

QIUHAO Zeng

2022–2026: PhD student , University of Western Ontario (CA)

2022–2025: PhD student , University of Western Ontario (CA)

2018–2021: Researcher , Nanyang Technological University

2017–2018: MS student , National University of Singapore

Papers (1)

Mamba Modulation: On the Length Generalization of Mamba Models — NeurIPS 2025 poster

Qiuhong Shen

2023–2027: PhD student , National University of Singapore (SG)

2022–2023: Researcher , Tencent Group

2022–2023: Intern , Shanghai AI Laboratory

2019–2022: MS student , Harbin Institute of Technology

Papers (1)

MVGamba: Unify 3D Content Generation as State Space Sequence Modeling — NeurIPS 2024 poster

Qixiang Ye

2016–present: Full Professor , University of Chinese Academy of Sciences (CN)

Papers (1)

VMamba: Visual State Space Model — NeurIPS 2024 spotlight

Quan Dao

2024–2029: PhD student , Rutgers University (US)

2022–2024: Intern , VinAI Research (VN)

2018–2021: Undergrad student , Monash University (AU)

Papers (1)

DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation — NeurIPS 2024 poster

Quanquan Gu

2023–present: Research Scientist , ByteDance Seed (US)

2022–present: Associate Professor , University of California, Los Angeles (US)

2018–2022: Assistant Professor , University of California, Los Angeles (US)

2015–2018: Assistant Professor , University of Virginia (US)

2014–2015: Postdoc , Princeton University (US)

2010–2014: PhD student , University of Illinois, Urbana Champaign

Papers (1)

How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression? — ICLR 2024 spotlight

Quanying Liu

2025–present: Associate Professor , Southern University of Science and Technology (CN)

2019–2025: Assistant Professor , Southern University of Science and Technology (CN)

Papers (1)

Multi-dataset Joint Pre-training of Emotional EEG Enables Generalizable Affective Computing — NeurIPS 2025 poster

Quinn McIntyre

2022–2026: Undergrad student , Stanford University

Papers (1)

Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions — NeurIPS 2023 poster

Radu Grosu

2012–present: Full Professor , TU Wien Vienna University of Technology (AT)

Papers (1)

Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence Modeling — NeurIPS 2025 poster

Raed Alharbi

2023–present: Assistant Professor , Saudi Electroic University (SA)

Papers (1)

Swift Hydra: Self-Reinforcing Generative Framework for Anomaly Detection with Multiple Mamba Models — ICLR 2025 Poster

Rafal Wisniewski

—–present: Full Professor , Aalborg University

Papers (1)

PAC-Bayesian Error Bound, via Rényi Divergence, for a Class of Linear Time-Invariant State-Space Models — ICML 2024 Poster

Raghav Singal

2025–present: Associate Professor , Dartmouth College (US)

2021–2025: Assistant Professor , Dartmouth College (US)

2015–2020: PhD student , Columbia University (US)

2010–2015: Undergrad student , University of Toronto (CA)

Papers (1)

Counterfactual Analysis in Dynamic Latent State Models — ICML 2023 Poster

Rahul Chalamala

2023–present: Researcher , Together AI (US)

2022–present: Undergrad student , California Institute of Technology (US)

2021–2022: Intern , Air Force Research Laboratory (US)

Papers (1)

LoLCATs: On Low-Rank Linearizing of Large Language Models — ICLR 2025 Poster

Rahul Ramesh

2019–2025: PhD student , University of Pennsylvania (US)

2014–2019: Undergrad student , Indian Institute of Technology Madras (IN)

Papers (1)

Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing — ICML 2025 poster

Ramamohan Paturi

1986–present: Full Professor , University of California, San Diego (US)

Papers (1)

Single-Pass Document Scanning for Question Answering — COLM 2025

Rameswar Panda

2018–present: Research Scientist , MIT-IBM Watson AI Lab

2014–2018: PhD student , University of California, Riverside

2011–2013: MS student , Jadavpur University, Kolkata

Papers (1)

Gated Linear Attention Transformers with Hardware-Efficient Training — ICML 2024 Poster

Ramin Hasani

2021–present: Researcher , Massachusetts Institute of Technology (US)

2020–2021: Postdoc , Massachusetts Institute of Technology

2020–2020: Postdoc , TU Wien

Papers (1)

State-Free Inference of State-Space Models: The *Transfer Function* Approach — ICML 2024 Poster

Ramin Zabih

2016–present: Research scientist , Google (US)

1994–present: Professor , Cornell (US)

Papers (1)

Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models — NeurIPS 2024 poster

Ramy Mounir

2020–present: PhD student , University of South Florida

Papers (1)

Predictive Attractor Models — NeurIPS 2024 poster

Rashed Shelim

2024–present: Postdoc , Virginia Tech (US)

Papers (1)

DMWM: Dual-Mind World Model with Long-Term Imagination — NeurIPS 2025 spotlight

Raunaq Bhirangi

2024–present: Postdoc , New York University (US)

2020–2024: PhD student , Carnegie Mellon University (US)

2018–2020: MS student , Carnegie Mellon University (US)

2014–2018: Undergrad student , Indian Institute of Technology Bombay, Dhirubhai Ambani Institute Of Information and Communication Technology (IN)

Papers (1)

Hierarchical State Space Models for Continuous Sequence-to-Sequence Modeling — ICML 2024 Poster

Ravid Shwartz-Ziv

2021–2025: Postdoc , New York University (US)

Papers (1)

Layer by Layer: Uncovering Hidden Representations in Language Models — ICML 2025 oral

Raviraj Bhuminand Joshi

2023–present: Researcher , NVIDIA (IN)

2016–2018: MS student , Department of Computer Science, Indian Institute of Technology, Madras, Indian Institute of Technology, Madras (IN)

Papers (1)

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning — NeurIPS 2025 poster

Raz Alon

2008–present: PhD student , Weizmann Institute of Science (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Rei Higuchi

2024–2026: MS student , the University of Tokyo (JP)

2020–2024: Undergrad student , the University of Tokyo (JP)

Papers (1)

Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency — NeurIPS 2025 poster

Remo Sasso

2021–2025: PhD student , Queen Mary, University of London

2018–2021: MS student , University of Groningen

2015–2018: Undergrad student , University of Groningen

Papers (1)

Posterior Sampling for Deep Reinforcement Learning — ICML 2023 Poster

Renhe Jiang

2023–present: Lecturer , The University of Tokyo (JP)

2019–2023: Assistant Professor , The University of Tokyo (JP)

2016–2019: PhD student , The University of Tokyo (JP)

Papers (1)

DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs — NeurIPS 2025 poster

Renrui Zhang

2021–2025: PhD student , MMLab of CUHK & Shanghai AI Laboratory (HK)

2017–2021: Undergrad student , Peking University

Papers (1)

RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation — NeurIPS 2024 poster

René Wagner

2019–present: Researcher , Google (DE)

2013–2021: PhD student , Universität Bremen (DE)

2012–2019: Researcher , German Aerospace Center (DLR) (DE)

2012–2012: Researcher , Universität Bremen (DE)

2010–2011: Researcher , German Research Center for AI (DE)

2003–2010: Undergrad student , Universität Bremen (DE)

Papers (1)

Linear Transformer Topological Masking with Graph Random Features — ICLR 2025 Poster

Reza Ebrahimi

2024–present: Researcher , Qualcomm Inc, QualComm (CA)

2018–2024: PhD student , University of Toronto (CA)

2023–2023: Intern , Qualcomm Inc, QualComm (CA)

2014–2017: MS student , University of Tehran, University of Tehran (IR)

2010–2014: Undergrad student , University of Tehran, University of Tehran (IR)

Papers (1)

Revisiting Bi-Linear State Transitions in Recurrent Neural Networks — NeurIPS 2025 poster

Reza Pourreza

2017–present: Researcher , Qualcomm AI Research (US)

2016–2017: Researcher , National Institutes of Health (US)

2012–2016: PhD student , University of Texas, Dallas (US)

Papers (1)

Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance? — NeurIPS 2025 poster

Riashat Islam

2025–present: Senior Researcher , Microsoft Research (US)

2023–2025: Researcher , Saudi Data and AI Authority, Saudi Data and AI Authority (SA)

2022–2023: Researcher , DreamFold AI (CA)

2017–2022: PhD student , Mila - Quebec AI Institute (CA)

2015–2017: MS student , University of Cambridge (GB)

2011–2015: Undergrad student , University College London, University of London (GB)

Papers (1)

Learning Latent Dynamic Robust Representations for World Models — ICML 2024 Poster

Richard E Turner

2024–present: Researcher , Alan Turing Institute (GB)

2012–present: Professor , University of Cambridge (GB)

2023–2024: Researcher , Research, Microsoft (GB)

Papers (1)

Linear Transformer Topological Masking with Graph Random Features — ICLR 2025 Poster

Richard Freinschlag

2023–present: PhD student , Johannes Kepler Universität Linz

Papers (1)

pLSTM: parallelizable Linear Source Transition Mark networks — NeurIPS 2025 poster

Richard Kurle

2025–present: Researcher , Emmi AI GmbH (AT)

2024–2025: Researcher , NXAI GmbH (AT)

2023–2024: Researcher , Hasso Plattner Institute (DE)

2021–2022: Applied Scientist , Amazon AWS AI

2017–2021: PhD student , Department of Informatics, Technical University Munich

2017–2021: PhD student , Volkswagen Group

2017–2021: PHD student , Volkswagen Group, Machine Learning Research Lab (MLRL)

Papers (1)

xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference — ICML 2025 poster

Rikuto Kotoge

2024–present: PhD student , Osaka University (JP)

2022–2024: MS student , Osaka University (JP)

2018–2022: Undergrad student , Osaka University (JP)

Papers (1)

EvoBrain: Dynamic Multi-Channel EEG Graph Modeling for Time-Evolving Brain Networks — NeurIPS 2025 spotlight

Ro'i Belson

2023–present: Language Data Analyst , AI21labs (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Roger P. Levy

2021–present: Full Professor , Massachusetts Institute of Technology (US)

2016–2021: Associate Professor , Massachusetts Institute of Technology (US)

2012–2016: Associate Professor , University of California, San Diego (US)

2006–2012: Assistant Professor , University of California, San Diego (US)

2005–2006: Postdoc , University of Edinburgh (GB)

1998–2005: PhD student , Stanford University (US)

Papers (1)

Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale — NeurIPS 2025 poster

Roi Cohen

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Roland Eils

2004–present: Full Professor , Charité Universitaetsmedizin Berlin

Papers (1)

JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation Model — NeurIPS 2025 poster

Rom Gilad

2023–present: Researcher , AI21 labs (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Roman Glozman

2023–present: Researcher , AI21Labs (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Rong Ge

2022–present: Associate Professor , Duke University (US)

2023–2023: Researcher , Google (visiting)

2015–2022: Assistant Professor , Duke University

2013–2015: Postdoc , Microsoft

2008–2013: PhD student , Princeton University

Papers (1)

Linear Transformers are Versatile In-Context Learners — NeurIPS 2024 poster

Ronghui Li

2022–present: PhD student , Tsinghua University, Tsinghua University (CN)

2019–2022: MS student , Northeastern University (CN)

Papers (1)

MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models — NeurIPS 2024 poster

Rongrong Ji

2013–2025: Full Professor , Xiamen University (CN)

2010–2013: Researcher , Columbia University

Papers (1)

DAMamba: Vision State Space Model with Dynamic Adaptive Scan — NeurIPS 2025 poster

Rongyu Zhang

2023–2027: PhD student , Nanjing University (CN)

2023–2027: PhD student , Hong Kong Polytechnic University (CN)

2021–2023: MS student , The Chinese University of Hong Kong, Shenzhen (CN)

2017–2021: Undergrad student , Beijing University of Posts and Telecommunications (CN)

Papers (1)

Orochi: Versatile Biomedical Image Processor — NeurIPS 2025 spotlight

Ross Goroshin

2017–present: Research Scientist , Google (CA)

2016–2017: Research Scientist , Google (GB)

2010–2015: PhD student , New York University (US)

2006–2008: MS student , Georgia Institute of Technology (US)

Papers (1)

Block-State Transformers — NeurIPS 2023 poster

Ruben Solozabal

2021–present: Postdoc , Mohamed bin Zayed University of Artificial Intelligence

Papers (1)

Uncovering the Spectral Bias in Diagonal State Space Models — NeurIPS 2025 poster

Rui Men

2020–present: Engineer , Alibaba Group (CN)

2017–2020: MS student , Peking University

2013–2017: Undergrad student , Peking University

Papers (1)

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free — NeurIPS 2025 oral

Rui Sun

2025–present: Postdoc , Tsinghua University (CN)

2021–2024: PhD student , University of Science and Technology of China (CN)

Papers (1)

BeyondMix: Leveraging Structural Priors and Long-Range Dependencies for Domain-Invariant LiDAR Segmentation — NeurIPS 2025 poster

Rui Wang

2021–present: Researcher , Helixon

2017–2020: Undergrad student , Purdue University

Papers (1)

Longhorn: State Space Models are Amortized Online Learners — ICLR 2025 Poster

Rui Zhang

2020–2025: PhD student , University of Science and Technology of China (CN)

Papers (1)

RFMamba: Frequency-Aware State Space Model for RF-Based Human-Centric Perception — ICLR 2025 Poster

Rui Zhao

2015–present: Researcher , SenseTime Research (CN)

2010–2015: PhD student , The Chinese University of Hong Kong

Papers (1)

Hybrid Mamba for Few-Shot Segmentation — NeurIPS 2024 poster

Ruichong Zhang

2024–2029: PhD student , Tsinghua University (CN)

2020–2024: Undergrad student , Tsinghua University, Tsinghua University (CN)

Papers (1)

RWKV-7 "Goose" with Expressive Dynamic State Evolution — COLM 2025

Ruimao Zhang

2024–present: Associate Professor , SUN YAT-SEN UNIVERSITY (CN)

2021–2024: Assistant Professor , The Chinese University of Hong Kong (Shenzhen) (CN)

2017–2019: Postdoc , The Chinese University of Hong Kong

2011–2016: PhD student , SUN YAT-SEN UNIVERSITY

Papers (1)

High-Dynamic Radar Sequence Prediction for Weather Nowcasting Using Spatiotemporal Coherent Gaussian Representation — ICLR 2025 Oral

Ruiping Wang

2017–present: Full Professor , Institute of Computing Technology, Chinese Academy of Sciences (CN)

2012–2017: Associate Professor , Institute of Computing Technology, Chinese Academy of Sciences (CN)

2010–2012: Postdoc , Tsinghua University, Tsinghua University (CN)

2010–2011: Postdoc , University of Maryland, College Park (US)

Papers (1)

EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment — ICLR 2025 Poster

Ruiqi Zhang

2022–2027: PhD student , University of California, Berkeley (US)

2018–2022: Undergrad student , Peking University (CN)

Papers (1)

In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization — NeurIPS 2024 poster

Ruisi Cai

2022–present: PhD student , University of Texas at Austin (US)

2018–2022: Undergrad student , University of Science and Technology of China

Papers (1)

Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing — ICLR 2025 Poster

Ruixiang Sun

2024–present: MS student , Beijing Institute of Technology (CN)

2020–2024: Undergrad student , Beijing Institute of Technology (CN)

Papers (1)

Learning Latent Dynamic Robust Representations for World Models — ICML 2024 Poster

Ruixu Geng

2022–present: PhD student , University of Science and Technology of China (CN)

2019–2022: MS student , University of Electronic Science and Technology of China (CN)

2015–2019: Undergrad student , University of Electronic Science and Technology of China (CN)

Papers (1)

RFMamba: Frequency-Aware State Space Model for RF-Based Human-Centric Perception — ICLR 2025 Poster

Ruiyang Qin

2022–2025: PhD student , University of Notre Dame (US)

2020–2021: MS student , Georgia Institute of Technology

2017–2020: Undergrad student , Georgia Institute of Technology

Papers (1)

Sub-Sequential Physics-Informed Learning with State Space Model — ICML 2025 poster

Ruiyuan Song

2020–2026: PhD student , University of Science and Technology of China

Papers (1)

RFMamba: Frequency-Aware State Space Model for RF-Based Human-Centric Perception — ICLR 2025 Poster

Ruizhe Chen

2023–present: PhD student , Xiamen University (CN)

2020–2023: MS student , Xiamen University (CN)

Papers (1)

FRN: Fractal-Based Recursive Spectral Reconstruction Network — NeurIPS 2025 poster

Ruizhe Zheng

2023–2026: MS student , Fudan University (CN)

Papers (1)

FAPEX: Fractional Amplitude-Phase Expressor for Robust Cross-Subject Seizure Prediction — NeurIPS 2025 spotlight

Runqing Wang

2024–2027: MS student , Beijing Institute of Technology (CN)

Papers (1)

DyMoDreamer: World Modeling with Dynamic Modulation — NeurIPS 2025 poster

Ruofan Wu

2024–present: Researcher , Coupang (CN)

2019–2024: Researcher , Ant Group (CN)

2017–2019: Researcher , International Business Machines

2012–2017: PhD student , Fudan University

Papers (1)

State Space Models on Temporal Graphs: A First-Principles Study — NeurIPS 2024 poster

S. T. John

2023–present: Research Fellow , Aalto University (FI)

2021–2023: Postdoc , Aalto University (FI)

2017–2021: Senior Machine Learning Researcher , Prowler.io (GB)

2011–2016: PhD student , University of Cambridge (GB)

Papers (1)

Identifying latent state transitions in non-linear dynamical systems — ICLR 2025 Poster

Sabri Eyuboglu

2020–2025: PhD student , Stanford University

2018–2019: MS student , Stanford University

2014–2019: Undergrad student , Stanford University

Papers (1)

Simple linear attention language models balance the recall-throughput tradeoff — ICML 2024 Spotlight

Sahar Dastani

2023–2027: PhD student , École de technologie supérieure, Université du Québec (CA)

2020–2022: MS student , Amirkabir University of Technology (IR)

2016–2020: Undergrad student , Amirkabir University of Technology (IR)

Papers (1)

TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses — NeurIPS 2025 poster

Saibal Mukhopadhyay

2007–present: Full Professor , Georgia Institute of Technology (US)

2006–2007: Researcher , IBM, International Business Machines (US)

2001–2006: PhD student , Purdue University (US)

1996–2000: Undergrad student , Jadavpur University (IN)

Papers (1)

FLAME: Fast Long-context Adaptive Memory for Event-based Vision — NeurIPS 2025 poster

Saiteja Utpala

2023–present: Researcher , Microsoft (IN)

2022–2022: Researcher , University of California, Santa Barbara

2018–2020: MS student , IIT Kanpur

Papers (1)

RWKV-7 "Goose" with Expressive Dynamic State Evolution — COLM 2025

Sajad Movahedi

2024–present: PhD student , ELLIS Institute Tübingen, Max Planck Institute for Intelligent Systems, Tübingen AI Center (DE)

2019–2022: MS student , University of Tehran, University of Tehran (IR)

Papers (1)

Fixed-Point RNNs: Interpolating from Diagonal to Dense — NeurIPS 2025 spotlight

Samuel Barbeau

2020–2025: Undergrad student , École de technologie supérieure, Université du Québec (CA)

Papers (1)

TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses — NeurIPS 2025 poster

Samuel Guo

2023–present: PhD student , University of Wisconsin - Madison (US)

Papers (1)

Pretrained Hybrids with MAD Skills — COLM 2025

Samy Jelassi

2023–2025: Postdoc , Harvard University

2017–2023: PhD student , Princeton University

Papers (1)

Repeat After Me: Transformers are Better than State Space Models at Copying — ICML 2024 Poster

Sangwoo Mo

2025–present: Assistant Professor , Pohang University of Science and Technology (KR)

2023–2025: Postdoc , University of Michigan - Ann Arbor (US)

2018–2023: PhD student , KAIST (KR)

Papers (1)

Sparsified State-Space Models are Efficient Highway Networks — Accepted by TMLR

Sanjay Haresh

2023–present: Researcher , Qualcomm, Inc. (CA)

2021–2023: MS student , Simon Fraser University

2019–2021: Researcher , Retrocausal, Inc.

2015–2019: Undergrad student , FAST (National University of Computer and Emerging Sciences)

Papers (1)

Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance? — NeurIPS 2025 poster

Sankaraleengam Alagapan

2022–present: Researcher , Georgia Institute of Technology (US)

2018–2022: Postdoc , Georgia Institute of Technology (US)

2014–2018: Postdoc , University of North Carolina at Chapel Hill (US)

2009–2014: PhD student , University of Florida (US)

Papers (1)

Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics — NeurIPS 2024 poster

Sarath Chandar

2024–present: Associate Professor , École Polytechnique de Montréal (CA)

2020–2024: Assistant Professor , École Polytechnique de Montréal (CA)

2015–2019: PhD student , University of Montreal (CA)

Papers (1)

Mastering Memory Tasks with World Models — ICLR 2024 oral

Sascha Yves Frey

2021–2025: PhD student , University of Oxford (GB)

2018–2020: MS student , EPFL - EPF Lausanne (CH)

2014–2018: Undergrad student , EPFL - EPF Lausanne (CH)

Papers (1)

LOB-Bench: Benchmarking Generative AI for Finance - an Application to Limit Order Book Data — ICML 2025 poster

Satinder Singh

—–present: Full Professor , University of Michigan

—–present: Research Scientist , DeepMind

Papers (1)

Structured State Space Models for In-Context Reinforcement Learning — NeurIPS 2023 poster

Satya Sai Srinath Namburi GNVV

2024–present: Researcher , GE HealthCare (US)

2021–2024: MS student , University of Wisconsin - Madison (US)

2015–2019: Undergrad student , National Institute of Technology Calicut

Papers (1)

Pretrained Hybrids with MAD Skills — COLM 2025

Saurav Muralidharan

2016–present: Researcher , NVIDIA (US)

2010–2016: PhD student , University of Utah

Papers (1)

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning — NeurIPS 2025 poster

Sayak Mallick

2024–2025: MS student , Max Planck Institute for Intelligent Systems, Max-Planck Institute (DE)

2021–2025: MS student , Eberhard-Karls-Universität Tübingen (DE)

2023–2024: Intern , Robert Bosch GmbH, Bosch (DE)

2018–2021: Undergrad student , St. Xaviers College Mumbai

Papers (1)

LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws — ICML 2025 poster

Scott A Sisson

2003–present: Full Professor , University of New South Wales (AU)

Papers (1)

Free-Form Variational Inference for Gaussian Process State-Space Models — ICML 2023 Poster

Sedrick Keh

2023–present: Research Engineer , Toyota Research Institute

2023–2023: AI Resident , Toyota Research Institute

2021–2022: MS student , Carnegie Mellon University

2017–2021: Undergrad student , Hong Kong University of Science and Technology

Papers (1)

Linearizing Large Language Models — COLM

Senqiao Yang

2024–present: PhD student , The Chinese University of Hong Kong (HK)

Papers (1)

RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation — NeurIPS 2024 poster

Sensen Song

2023–present: Associate Professor , Xinjiang University (CN)

Papers (1)

ZigzagPointMamba: Spatial-Semantic Mamba for Point Cloud Understanding — NeurIPS 2025 poster

Senyan Xu

2025–present: PhD student , University of Science and Technology of China (CN)

2023–2024: MS student , University of Science and Technology of China (CN)

2019–2023: Undergrad student , Xidian University (CN)

Papers (1)

FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining — ICML 2025 poster

Seokin Seo

2019–present: PhD student , Korea Advanced Institute of Science and Technology (KR)

2017–2019: MS student , Korea Advanced Institute of Science and Technology (KR)

Papers (1)

Information-Theoretic State Space Model for Multi-View Reinforcement Learning — ICML 2023 OralPoster

Seongrok Moon

2022–2024: MS student , Pohang University of Science and Technology

2018–2022: Undergrad student , Pohang University of Science and Technology

Papers (1)

Layer-Adaptive State Pruning for Deep State Space Models — NeurIPS 2024 poster

Seunghoon Hong

2024–present: Associate Professor , Korea Advanced Institute of Science and Technology (KR)

2017–2019: Postdoc , University of Michigan (US)

2011–2016: PhD student , POSTECH (KR)

Papers (1)

Information-Theoretic State Space Model for Multi-View Reinforcement Learning — ICML 2023 OralPoster

Seunghyuk Oh

2025–present: Researcher , FuriosaAI (KR)

2023–2025: MS student , KAIST (KR)

2017–2023: Undergrad student , KAIST

Papers (1)

Sparsified State-Space Models are Efficient Highway Networks — Accepted by TMLR

Seyedarmin Azizi

2022–present: PhD student , University of Southern California (US)

Papers (1)

MambaExtend: A Training-Free Approach to Improve Long Context Extension of Mamba — ICLR 2025 Poster

Shady Abu-Hussein

2025–present: Postdoc , Tel Aviv University (IL)

2019–2024: PhD student , Tel Aviv University (IL)

Papers (1)

DeciMamba: Exploring the Length Extrapolation Potential of Mamba — ICLR 2025 Poster

Shahar Lev

—–present: Msc , School of Computer Science, Tel Aviv University (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Shai Shalev-Shwartz

—–present: Full Professor , Hebrew University of Jerusalem

2009–present: Full Professor , Hebrew University, Hebrew University of Jerusalem

2007–2009: Postdoc , Toyota Technological Institute at Chicago

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Shaked Haim Meirom

2018–2022: MS student , Technion - Israel Institute of Technology, Technion

2015–2018: Undergrad student , Technion - Israel Institute of Technology, Technion

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Shakeel A O B Gavioli-Akilagun

2025–present: Researcher , City University (HK)

2023–2025: Researcher , London School of Economics and Political Science, University of London (GB)

2019–2023: PhD student , London School of Economics and Political Science, University of London (GB)

Papers (1)

AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees — NeurIPS 2025 poster

Shalini De Mello

2011–present: Principal Researcher , NVIDIA (US)

2008–2010: Imaging Scientist , Texas Instruments (US)

2004–2008: PhD student , University of Texas at Austin (US)

2002–2004: MS student , University of Texas at Austin (US)

Papers (1)

Convolutional State Space Models for Long-Range Spatiotemporal Modeling — NeurIPS 2023 poster

Sham M. Kakade

2022–present: Full Professor , Harvard University (US)

Papers (1)

Repeat After Me: Transformers are Better than State Space Models at Copying — ICML 2024 Poster

Shang Yang

2023–present: PhD student , Massachusetts Institute of Technology (US)

2022–2023: Intern , Massachusetts Institute of Technology (US)

2019–2023: Undergrad student , Tsinghua University, Tsinghua University (CN)

Papers (1)

Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search — NeurIPS 2025 poster

Shaoli Huang

2021–present: Researcher , Tencent AI Lab (CN)

2017–2021: Postdoc , University of Sydney (AU)

2013–2017: PhD student , University of Technology Sydney (AU)

Papers (1)

MambaTree: Tree Topology is All You Need in State Space Model — NeurIPS 2024 spotlight

Shaowei Zhang

2024–present: PhD student , Nanjing University (CN)

2021–2024: MS student , Nanjing University

2017–2021: Undergrad student , Northeastern University

Papers (1)

Leveraging Conditional Dependence for Efficient World Model Denoising — NeurIPS 2025 poster

Sharath Turuvekere Sreenivas

2018–present: Deep Learning Engineer , NVIDIA

2016–2018: MS student , University of California, Santa Cruz

Papers (1)

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning — NeurIPS 2025 poster

Sheng Wu

—–present: PhD student , Fudan University (CN)

Papers (1)

EventMG: Efficient Multilevel Mamba-Graph Learning for Spatiotemporal Event Representation — NeurIPS 2025 poster

Shengchao Hu

2022–2027: PhD student , Shanghai Jiao Tong University (CN)

2018–2022: Undergrad student , Shanghai Jiao Tong University (CN)

Papers (1)

Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning? — NeurIPS 2024 poster

Shengding Hu

2020–2025: PhD student , Tsinghua University, Tsinghua University (CN)

2016–2020: Undergrad student , Tsinghua University, Tsinghua University (CN)

Papers (1)

Stuffed Mamba: Oversized States Lead to the Inability to Forget — COLM 2025

Shengen Yan

2024–present: Associate Professor , Tsinghua University (CN)

2022–2023: Associate Professor , Peking University (CN)

2017–2022: Principal Researcher , SenseTime (HK)

2015–2017: Postdoc , Chinese University of Hong Kong (HK)

2009–2014: PhD student , Chinese Academy of Sciences (CN)

Papers (1)

Evaluating Quantized Large Language Models — ICML 2024 Poster

Shengfeng He

2023–present: Associate Professor , Singapore Management University (SG)

2016–2022: Associate Professor , South China University of Technology (CN)

2015–2016: Researcher , City University of Hong Kong (HK)

2012–2015: PhD student , City University of Hong Kong (HK)

Papers (1)

Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking — NeurIPS 2025 poster

Shenghua Wan

2021–present: PhD student , Nanjing University (CN)

2017–2021: Undergrad student , Nanjing University (CN)

Papers (1)

Leveraging Conditional Dependence for Efficient World Model Denoising — NeurIPS 2025 poster

Shengkun Tang

2024–present: PhD student , Mohamed bin Zayed University of Artificial Intelligence (AE)

2018–2022: Undergrad student , Wuhan University

Papers (1)

Bi-Mamba: Towards Accurate 1-Bit State Space Model — Accepted by TMLR

Shengnan Guo

2024–present: Associate Professor , Beijing Jiaotong University

2021–2023: Lecturer , Beijing Jiaotong University

2019–2020: PhD student , National Technological University

Papers (1)

TrajMamba: An Efficient and Semantic-rich Vehicle Trajectory Pre-training Model — NeurIPS 2025 spotlight

Shengxuming Zhang

2020–present: PhD student , Zhejiang University (CN)

2016–2020: Undergrad student , Central South University (CN)

Papers (1)

Vision Mamba Mender — NeurIPS 2024 poster

Shida Sun

2023–2026: MS student , University of Science and Technology of China (CN)

2019–2023: Undergrad student , Nanchang University (CN)

Papers (1)

Toward Dynamic Non-Line-of-Sight Imaging with Mamba Enforced Temporal Consistency — NeurIPS 2024 poster

Shih-Yang Liu

2021–2026: PhD student , Department of Computer Science and Engineering, Hong Kong University of Science and Technology (HK)

2023–2025: Intern , NVIDIA (TW)

2016–2021: Undergrad student , Hong Kong University of Science and Technology (HK)

Papers (1)

Hymba: A Hybrid-head Architecture for Small Language Models — ICLR 2025 Spotlight

Shihao Yang

2023–present: PhD student , Stevens Institute of Technology (US)

2018–2020: MS student , University of Southern California (US)

2014–2018: Undergrad student , Nankai University (CN)

Papers (1)

Inference of Whole Brain Electrophysiological Networks Through Multimodal Integration of Simultaneous Scalp and Intracranial EEG — NeurIPS 2025 poster

Shin-ichi Maeda

2017–present: Senior Researcher , Preferred Networks, Inc. (JP)

2008–2017: Assistant Professor , Kyoto University, Japan (JP)

2004–2008: Assistant Professor , Nara Institute of Science and Technology, Japan (JP)

2001–2004: PhD student , Nara Institute of Science and Technology, Japan (JP)

Papers (1)

Deep Bayesian Filter for Bayes-Faithful Data Assimilation — ICML 2025 poster

Shiyao Li

2023–present: Intern , Infinigence (CN)

2020–2025: PhD student , Tsinghua University, Tsinghua University (CN)

2016–2020: Undergrad student , Tsinghua University, Tsinghua University (CN)

Papers (1)

Evaluating Quantized Large Language Models — ICML 2024 Poster

Shiyin Tan

2024–2026: PhD student , Institute of Science Tokyo (JP)

2023–2024: PhD student , Tokyo Institute of Technology (JP)

Papers (1)

DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs — NeurIPS 2025 poster

Shizhan Liu

2025–present: Researcher , Zhipu AI (CN)

2024–2025: Researcher , Ant Group (CN)

2021–2024: MS student , Shanghai Jiao Tong University (CN)

2017–2021: Undergrad student , Shanghai Jiao Tong University (CN)

Papers (1)

Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions — ICLR 2025 Poster

Shizhong Han

2019–present: Researcher , QualComm (US)

2017–2019: Researcher , 12sigma (US)

2011–2017: PhD student , University of South Carolina (US)

Papers (1)

PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer — ICLR 2025 Poster

Shouling Ji

2016–present: Full Professor , Zhejiang University (CN)

2013–2015: PhD student , Georgia Institute of Technology

Papers (1)

Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning? — NeurIPS 2024 poster

Shu-Tao Xia

2007–present: Full Professor , Shenzhen International Graduate School, Tsinghua University (CN)

1992–1997: PhD student , Nankai University (CN)

1988–1992: Undergrad student , Nankai University (CN)

Papers (1)

LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling — NeurIPS 2024 poster

Shuai Xiao

2019–present: Researcher , Huawei Technologies Ltd. (CN)

2016–2019: MS student , Tsinghua University (CN)

Papers (1)

TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-state — ICML 2025 poster

Shuhui Wang

2020–present: Full Professor , Institute of Computing Technology, Chinese Academy of Sciences (CN)

2012–2015: Assistant Professor , Institute of Computing Technology, Chinese Academy of Sciences (CN)

2006–2012: PhD student , Institute of Computing Technology, Chinese Academy of Sciences (CN)

2002–2006: Undergrad student , Tsinghua University, Tsinghua University (CN)

Papers (1)

Modeling Language Tokens as Functionals of Semantic Fields — ICML 2024 Poster

Shuicheng YAN

2025–present: Full Professor , National University of Singapore (SG)

2021–2024: Researcher , sea Group (SG)

2019–2020: Principal Researcher , YITU Technology, China

2015–2019: Principal Researcher , Qihoo 360

2013–2019: Associate Professor , National University of Singapore

2007–2012: Assistant Professor , national university of singaore, National University of Singapore

1999–2004: PhD student , Peking University

Papers (1)

MVGamba: Unify 3D Content Generation as State Space Sequence Modeling — NeurIPS 2024 poster

Shuo Wang

2023–2027: Postdoc , Tsinghua University, Tsinghua University (CN)

2018–2023: PhD student , Tsinghua University, Tsinghua University (CN)

2014–2018: Undergrad student , Tsinghua University, Tsinghua University (CN)

Papers (1)

RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing — NeurIPS 2025 poster

Shuo Yang

2024–2029: PhD student , University of California, Berkeley (US)

2020–2024: Undergrad student , Shanghai Jiaotong University (CN)

Papers (1)

Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation — NeurIPS 2025 poster

Si Chen

2023–2026: MS student , University of Science and Technology of China (CN)

2019–2023: Undergrad student , University of Science and Technology of China (CN)

Papers (1)

BeyondMix: Leveraging Structural Priors and Long-Range Dependencies for Domain-Invariant LiDAR Segmentation — NeurIPS 2025 poster

Sicheng Yang

2024–2025: Researcher , Huawei Technologies Ltd. (GB)

2021–2024: MS student , Tsinghua University, Tsinghua University (CN)

2017–2021: Undergrad student , Beijing Institute of Technology (CN)

Papers (1)

MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models — NeurIPS 2024 poster

Siddhartha Somani

2023–2027: Undergrad student , Georgia Institute of Technology (US)

Papers (1)

ZeroS: Zero‑Sum Linear Attention for Efficient Transformers — NeurIPS 2025 spotlight

Sifan Zhou

2023–2025: visiting student , Carnegie Mellon University (US)

2021–2025: PhD student , Southeast University (CN)

2020–2021: Intern , Fudan University (CN)

2018–2021: MS student , Northeastern University (CN)

Papers (1)

MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods — ICLR 2025 Poster

Sijin Chen

2025–2029: PhD student , University of Hong Kong (CN)

2024–2025: Researcher , ByteDance Inc. (CN)

2021–2024: MS student , Fudan University (CN)

2017–2021: Undergrad student , Fudan University (CN)

Papers (1)

3DET-Mamba: Causal Sequence Modelling for End-to-End 3D Object Detection — NeurIPS 2024 poster

Silas Alberti

2022–present: PhD student , Stanford University (US)

2019–2022: Undergrad student , Ludwig-Maximilians-Universität München

Papers (1)

Simple linear attention language models balance the recall-throughput tradeoff — ICML 2024 Spotlight

Sili Huang

2025–present: Lecturer , Minzu University of China (CN)

2021–2025: PhD student , Jilin University (CN)

Papers (1)

Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling — NeurIPS 2024 poster

Simiao Zuo

2023–present: Researcher , Microsoft

2019–2023: PhD student , Georgia Institute of Technology

Papers (1)

Efficient Hybrid Long Sequence Modeling with State Space Augmented Transformers — COLM

Sina Alemohammad

2025–present: Postdoc , University of Texas at Austin (US)

2019–2025: PhD student , Rice University (US)

2014–2019: Undergrad student , Sharif University of Technology

Papers (1)

WaLRUS: Wavelets for Long range Representation Using State Space Methods — NeurIPS 2025 poster

Siyu Song

2022–2026: Undergrad student , South China Normal University (CN)

Papers (1)

MambaTree: Tree Topology is All You Need in State Space Model — NeurIPS 2024 spotlight

Siyuan Li

2021–2026: PhD student , Westlake University & Zhejiang University (CN)

2024–2025: Intern , BioMap Research (CN)

2023–2024: Intern , Alibaba Group (CN)

2017–2021: Undergrad student , Nanjing University (CN)

Papers (1)

Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences — ICML 2024 Poster

Sohvi Luukkonen

2023–present: Postdoc , Johannes Kepler Universität Linz (AT)

2021–2023: Postdoc , Leiden University (NL)

2017–2020: PhD student , CEA (FR)

Papers (1)

Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences — ICLR 2025 Poster

Songhua Liu

2025–2025: Assistant Professor , Shanghai Jiaotong University (CN)

2021–2025: PhD student , national university of singaore, National University of Singapore (SG)

2017–2021: Undergrad student , Nanjing University (CN)

Papers (1)

CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up — NeurIPS 2025 poster

Songtao Lu

2025–present: Assistant Professor , Department of Computer Science and Engineering, The Chinese University of Hong Kong (HK)

2022–2024: Senior Research Scientist , MIT-IBM Watson AI Lab

2022–2024: Researcher , IBM Thomas J. Watson Research Center

2020–2022: Research Scientist , IBM Thomas J. Watson Research Center

2019–2020: AI Resident , IBM Thomas J. Watson Research Center

2018–2019: Postdoc , University of Minnesota Twin Cities

2012–2018: PhD student , Iowa State University

Papers (1)

Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis — ICLR 2025 Poster

Sonia Cromp

2021–present: PhD student , Department of Computer Science, University of Wisconsin - Madison (US)

2024–2025: Intern , NASA (US)

2017–2021: Undergrad student , , University of Pittsburgh (US)

2020–2020: Intern , , Lehigh University (US)

Papers (1)

Pretrained Hybrids with MAD Skills — COLM 2025

Soon Hoe Lim

2024–present: Assistant Professor , KTH Royal Institute of Technology (SE)

2022–2024: Assistant Professor , Nordic Institute for Theoretical Physics (SE)

2018–2022: Postdoc , Nordic Institute for Theoretical Physics (SE)

Papers (1)

Tuning Frequency Bias of State Space Models — ICLR 2025 Spotlight

Stan Z. Li

2019–present: Chair Professor , Westlake University (CN)

2004–2019: Professor , Institute of automation, Chinese academy of sciences (CN)

2000–2004: Researcher , Microsoft Research Asia (CN)

Papers (1)

Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences — ICML 2024 Poster

Stefan Kollet

2012–present: Full Professor , Forschungszentrum Juelich GmbH (DE)

Papers (1)

RiverMamba: A State Space Model for Global River Discharge and Flood Forecasting — NeurIPS 2025 poster

Stefan Zohren

2018–present: Associate Professor , University of Oxford (GB)

Papers (1)

LOB-Bench: Benchmarking Generative AI for Finance - an Application to Limit Order Book Data — ICML 2025 poster

Stefanie Jegelka

2023–present: Full Professor , Technische Universität München (DE)

2019–present: Associate Professor , Massachusetts Institute of Technology (US)

2015–2019: Assistant Professor , Massachusetts Institute of Technology (US)

2012–2014: Postdoc , University of California, Berkeley (US)

2008–2012: PhD student , Max Planck Institute for Intelligent Systems, Max-Planck Institute (DE)

Papers (1)

Learning Linear Attention in Polynomial Time — NeurIPS 2025 oral

Stephan Allenspach

2023–present: Postdoc , University of California, Berkeley (US)

2022–2023: Postdoc , ETHZ - ETH Zurich (CH)

2017–2021: PhD student , University of Geneva

Papers (1)

Unlocking Guidance for Discrete State-Space Diffusion and Flow Models — ICLR 2025 Poster

Stephen Baccus

2020–2023: Full Professor , Stanford University

2012–2020: Associate Professor , Stanford University

2004–2012: Assistant Professor , Stanford University

Papers (1)

Hyena Hierarchy: Towards Larger Convolutional Language Models — ICML 2023 OralPoster

Stratis Ioannidis

2023–present: Full Professor , Northeastern University (US)

2022–present: Researcher , Meta, Inc. (US)

2020–2023: Associate Professor , Northeastern University (US)

2021–2021: Researcher , University of Cambridge (GB)

2015–2020: Assistant Professor , Northeastern University (US)

2014–2015: Researcher , Yahoo Research (US)

2010–2014: Researcher , Technicolor (US)

2009–2010: Postdoc , Technicolor (FR)

2004–2009: PhD student , University of Toronto (CA)

2002–2004: MS student , University of Toronto

1997–2002: Undergrad student , National Technical University of Athens (GR)

Papers (1)

Exploring Token Pruning in Vision State Space Models — NeurIPS 2024 poster

Sucheng Ren

2023–present: PhD student , Johns Hopkins University (US)

2020–2022: MS student , South China University of Technology, Tsinghua University (CN)

2016–2020: Undergrad student , South China University of Technology, Tsinghua University (CN)

Papers (1)

Autoregressive Pretraining with Mamba in Vision — ICLR 2025 Poster

Sudeep Sarkar

1993–present: Professor , University of South Florida (US)

Papers (1)

Predictive Attractor Models — NeurIPS 2024 poster

Sugitha Janarthanan

2023–2027: PhD student , Western University (CA)

2019–2023: Undergrad student , Western University (CA)

Papers (1)

Structure-Aware Fusion with Progressive Injection for Multimodal Molecular Representation Learning — NeurIPS 2025 poster

Suhana Bedi

2023–2029: PhD student , Stanford University (US)

Papers (1)

Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHR Data — ICLR 2025 Poster

Sukjun Hwang

2023–present: PhD student , Carnegie Mellon University (US)

2022–2022: Intern , Adobe Research

2020–2022: MS student , Yonsei University

2019–2020: Intern , Qualcomm Inc, QualComm

Papers (1)

Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers — NeurIPS 2024 poster

Sungjin Ahn

2021–present: Associate Professor , KAIST (US)

2018–2021: Assistant Professor , Rutgers University (CA)

2017–2018: Research Scientist , Element AI (CA)

2015–2017: Postdoc , University of Montreal (US)

2010–2015: PhD student , University of California, Irvine

Papers (1)

Slot State Space Models — NeurIPS 2024 poster

Sungyoon Kim

2021–2023: MS student , Korea Advanced Institute of Science & Technology

Papers (1)

Information-Theoretic State Space Model for Multi-View Reinforcement Learning — ICML 2023 OralPoster

Sungyoon Lee

2023–present: Assistant Professor , Hanyang University (KR)

2021–2023: Researcher , Korea Institute for Advanced Study (KR)

2016–2021: PhD student , Seoul National University (KR)

2010–2016: Undergrad student , Seoul National University (KR)

Papers (1)

Prior Forgetting and In-Context Overfitting — NeurIPS 2025 poster

Sunny Panchal

2021–present: Researcher , Qualcomm Inc, QualComm (CA)

2018–2019: MS student , University of Edinburgh, University of Edinburgh (GB)

Papers (1)

Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance? — NeurIPS 2025 poster

Suozhi Huang

2025–2030: PhD student , Princeton University (US)

2020–2025: Undergrad student , Tsinghua University, Tsinghua University (CN)

Papers (1)

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free — NeurIPS 2025 oral

Surin Ahn

2023–present: Researcher , Microsoft (US)

2018–2023: PhD student , Stanford University (US)

2021–2022: Intern , Microsoft (US)

2014–2018: Undergrad student , Princeton University

Papers (1)

SCBench: A KV Cache-Centric Analysis of Long-Context Methods — ICLR 2025 Poster

Suvrit Sra

2023–present: Full Professor , Technische Universität München (DE)

2019–present: Associate Professor , Massachusetts Institute of Technology (US)

2015–2018: Other , Massachusetts Institute of Technology (US)

Papers (1)

Linear attention is (maybe) all you need (to understand Transformer optimization) — ICLR 2024 poster

Svitlana Vyetrenko

—–present: AI Research Director , J.P. Morgan Chase (US)

Papers (1)

LOB-Bench: Benchmarking Generative AI for Finance - an Application to Limit Order Book Data — ICML 2025 poster

Szilvia Ujváry

2023–present: PhD student , University of Cambridge

2022–2023: MS student , University of Cambridge

2019–2022: Undergrad student , Imperial College London

Papers (1)

Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD Prompts — NeurIPS 2024 spotlight

Szymon Plotka

2025–present: Assistant Professor , Jagiellonian University (PL)

2024–2025: Postdoc , University of Warsaw (PL)

2022–2024: PhD student , University of Amsterdam (NL)

2022–2024: Researcher , Amsterdam UMC (NL)

Papers (1)

Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation — NeurIPS 2025 poster

T. Anderson Keller

2023–present: Postdoc , Harvard University (US)

2018–2023: PhD student , University of Amsterdam (NL)

Papers (1)

Bridging Expressivity and Scalability with Adaptive Unitary SSMs — NeurIPS 2025 poster

T. Konstantin Rusch

2025–2031: Assistant Professor , Max Planck Institute for Intelligent Systems, Max-Planck Institute (DE)

2025–2031: Principal Researcher , ELLIS Institute Tübingen (DE)

2024–2025: Postdoc , Massachusetts Institute of Technology (US)

2019–2023: PhD student , Swiss Federal Institute of Technology

Papers (1)

Oscillatory State-Space Models — ICLR 2025 Oral

Taha Kass-Hout

2023–present: Global Chief Science and Technology Officer , GE HealthCare (US)

2016–2023: VP Machine Learning/Distinguished Engineer , Amazon (US)

1998–2002: MS student , University of Texas at Houston (US)

1993–1996: Medical Student , UT Health Houston (US)

Papers (1)

Deep Continuous-Time State-Space Models for Marked Event Sequences — NeurIPS 2025 spotlight

Tai Nakamaki

2024–2026: MS student , The University of Tokyo

2020–2024: Undergrad student , The University of Tokyo (JP)

Papers (1)

Transformers are Minimax Optimal Nonparametric In-Context Learners — NeurIPS 2024 poster

Taisong Jin

2021–present: Associate Professor , Xiamen University (CN)

2007–2021: Assistant Professor , Xiamen University (CN)

Papers (1)

DAMamba: Vision State Space Model with Dynamic Adaptive Scan — NeurIPS 2025 poster

Takufumi Yanagisawa

2018–present: Full Professor , Osaka University, Tokyo Institute of Technology (JP)

2016–2018: Associate Professor , Osaka University, Tokyo Institute of Technology (JP)

2012–2016: Assistant Professor , Osaka University, Tokyo Institute of Technology (JP)

Papers (1)

EvoBrain: Dynamic Multi-Channel EEG Graph Modeling for Time-Evolving Brain Networks — NeurIPS 2025 spotlight

Takuma Yamamoto

2017–present: Researcher , Fujitsu Research, Fujitsu Limited (JP)

Papers (1)

Mamba Only Glances Once (MOGO): A Lightweight Framework for Efficient Video Action Detection — NeurIPS 2025 poster

Tal Delbari

—–present: Undergrad student , Reichman University (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Tal Ness

2023–present: Language Data Scientist , AI21 Labs (IL)

2021–2023: Postdoc , University of Maryland, College Park

2017–2021: PhD student , Tel Aviv University

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Tam Minh Nguyen

2023–present: PhD student , Rice University (US)

2021–2023: FPT AI Residency , FPT Software

2020–2021: Researcher , Sun Asterisk

Papers (1)

PIDformer: Transformer Meets Control Theory — ICML 2024 Poster

Tangyu Jiang

2024–present: Postdoc , Tsinghua University, Tsinghua University (CN)

2021–2024: PhD student , Beijing Normal University (CN)

2018–2021: MS student , Beijing Normal University (CN)

2014–2018: Undergrad student , Dalian University of Technology (CN)

Papers (1)

Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking — NeurIPS 2025 poster

Tanzhe Li

2022–present: MS student , Xiamen University (CN)

2018–2022: Undergrad student , Xiangtan University (CN)

Papers (1)

DAMamba: Vision State Space Model with Dynamic Adaptive Scan — NeurIPS 2025 poster

Tao Chen

2019–present: Full Professor , Fudan University (CN)

2017–2019: Senior scientist , Huawei Technologies Ltd. (SG)

2013–2017: Scientist , , A*STAR (SG)

Papers (1)

3DET-Mamba: Causal Sequence Modelling for End-to-End 3D Object Detection — NeurIPS 2024 poster

Tao Dai

2021–present: Assistant Professor , Department of Software Engineering, Shenzhen University (CN)

2019–2021: Postdoc , Tsinghua University (CN)

2014–2019: PhD student , Tsinghua University, Tsinghua University (CN)

Papers (1)

LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling — NeurIPS 2024 poster

Tao Luo

2017–present: Researcher , A*STAR (SG)

2013–2017: PhD student , Nanyang Technological University (SG)

Papers (1)

Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling — NeurIPS 2024 poster

Tasuku Kimura

2020–present: Specially Appointed Assistant Professor , The University of Osaka (JP)

Papers (1)

EvoBrain: Dynamic Multi-Channel EEG Graph Modeling for Time-Evolving Brain Networks — NeurIPS 2025 spotlight

Tatsunori Hashimoto

2019–present: Assistant Professor , Stanford University

2016–2019: Postdoc , Stanford University

2011–2016: PhD student , Massachusetts Institute of Technology

2007–2011: Undergrad student , Harvard University

Papers (1)

Learning to (Learn at Test Time): RNNs with Expressive Hidden States — ICML 2025 spotlightposter

Tengxuan Liu

2025–present: PhD student , Tsinghua University (CN)

2021–2025: Undergrad student , Tsinghua University (CN)

Papers (1)

Evaluating Quantized Large Language Models — ICML 2024 Poster

Terence O'kane

2009–2026: Principal Researcher , CSIRO (AU)

Papers (1)

Free-Form Variational Inference for Gaussian Process State-Space Models — ICML 2023 Poster

Terrence Sejnowski

1988–present: Full Professor , Salk Institute

Papers (1)

Bridging Expressivity and Scalability with Adaptive Unitary SSMs — NeurIPS 2025 poster

Teruaki Hayashi

2025–present: Researcher , Sony Interactive Entertainment (JP)

2021–2025: Researcher , Sony (JP)

Papers (1)

MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba — ICLR 2025 Poster

Tess Hellebrekers

2020–2024: Researcher , Meta

Papers (1)

Hierarchical State Space Models for Continuous Sequence-to-Sequence Modeling — ICML 2024 Poster

Thaddäus Wiedemer

2022–2025: PhD student , Eberhard-Karls-Universität Tübingen (DE)

2022–2025: PhD student , Max Planck Institute for Intelligent Systems (DE)

2018–2021: MS student , Karlsruher Institut für Technologie (DE)

2018–2021: MS student , Tsinghua University, Tsinghua University (CN)

2015–2018: Undergrad student , Karlsruher Institut für Technologie (DE)

Papers (1)

LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws — ICML 2025 poster

Thieu Vo

2024–2025: Postdoc , National University of Singapore (SG)

2017–2025: Lecturer , Ton Duc Thang University (VN)

2013–2016: PhD student , Johannes Kepler Universität Linz (AT)

2011–2013: MS student , University of Bordeaux (FR)

Papers (1)

Demystifying the Token Dynamics of Deep Selective State Space Models — ICLR 2025 Spotlight

Thomas Adler

2024–present: Postdoc , Johannes Kepler Universität Linz (AT)

2017–2024: PhD student , Johannes Kepler University Linz (AT)

Papers (1)

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks — ICML 2025 poster

Thomas Kollar

2024–present: Principal Researcher , Wayve (US)

2018–2024: Principal Researcher , Toyota Research Institute (US)

2015–2018: Principal Researcher , Amazon

2013–2015: Researcher , Apple

2011–2013: Postdoc , Carnegie Mellon University

2004–2011: PhD student , Massachusetts Institute of Technology

Papers (1)

Linearizing Large Language Models — COLM

Tian Luo

2025–2025: Lecturer , Fudan University (CN)

Papers (1)

FAPEX: Fractional Amplitude-Phase Expressor for Robust Cross-Subject Seizure Prediction — NeurIPS 2025 spotlight

Tian Yu Liu

2022–2025: PhD student , University of California, Los Angeles (US)

2018–2021: Undergrad student , University of California, Los Angeles (US)

Papers (1)

PICASO: Permutation-Invariant Context Composition with State Space Models — ICLR 2025 Poster

Tianjian Li

2024–present: Researcher , ByteDance Inc. (CN)

2013–2018: PhD student , Shanghai Jiaotong University (CN)

Papers (1)

ZeCO: Zero-Communication Overhead Sequence Parallelism for Linear Attention — NeurIPS 2025 poster

Tianle Cai

2025–present: Researcher , ByteDance Inc. (CN)

2021–2025: PhD student , Princeton University (US)

2016–2020: Undergrad student , Peking University (CN)

Papers (1)

Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation — NeurIPS 2025 poster

Tianyi Chen

2024–2028: PhD student , Shanghai Jiaotong University (CN)

Papers (1)

Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data — NeurIPS 2025 spotlight

Tianyi Wu

2022–present: PhD student , Beijing Normal University (CN)

Papers (1)

RWKV-7 "Goose" with Expressive Dynamic State Evolution — COLM 2025

Tianyu Liu

2022–present: PhD student , Tsinghua University, Tsinghua University (CN)

2019–2022: MS student , Tsinghua University, Tsinghua University

2015–2019: Undergrad student , Beijing Forestry University (CN)

Papers (1)

Slimming the Fat-Tail: Morphing-Flow for Adaptive Time Series Modeling — ICML 2025 poster

Tiejun Huang

2009–present: Full Professor , Peking University (CN)

2007–2009: Associate Professor , Peking University (CN)

2003–2007: Associate Professor , Graduted University of CAS (CN)

1999–2002: Postdoc , , Chinese Academy of Sciences

1995–1998: PhD student , Huazhong University of Science and Technology (CN)

Papers (1)

Orochi: Versatile Biomedical Image Processor — NeurIPS 2025 spotlight

Tiexin Qin

2021–2025: PhD student , City University of Hong Kong (HK)

2018–2021: MS student , Nanjing University (CN)

2014–2018: Undergrad student , China University of Mining and Technology (CN)

Papers (1)

Log Neural Controlled Differential Equations: The Lie Brackets Make A Difference — ICML 2024 Poster

Tijin Yan

2019–present: PhD student , Beijing Institute of Technology

2015–2019: Undergrad student , Beijing Institute of Technology

Papers (1)

Probabilistic Time Series Modeling with Decomposable Denoising Diffusion Model — ICML 2024 Poster

Timur Carstensen

2024–present: PhD student , Albert-Ludwigs-Universität Freiburg (DE)

2024–present: PhD student , ELLIS Institute Tübingen (DE)

2021–2024: MS student , Universität Mannheim (DE)

Papers (1)

DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products — NeurIPS 2025 poster

Tingyu Du

2022–2026: Undergrad student , Beijing Jiaotong University (CN)

Papers (1)

A Multimodal BiMamba Network with Test-Time Adaptation for Emotion Recognition Based on Physiological Signals — NeurIPS 2025 poster

Tom A. Lamb

2023–2027: PhD student , University of Oxford (GB)

2022–2023: MS student , University of Edinburgh (GB)

2016–2020: Undergrad student , University of Durham (GB)

Papers (1)

Universal In-Context Approximation By Prompting Fully Recurrent Models — NeurIPS 2024 poster

Tom Ben Gal

2024–present: Researcher , AI21 Labs (IL)

2014–2018: Undergrad student , Ben Gurion University of the Negev (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Tom Braude

2018–2021: MS student , IDC

2013–2017: Undergrad student , Ben Gurion University of the Negev

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Tom Jurgenson

2018–present: PhD student , Technion

2014–2018: MS student , Tel Aviv University

2010–2013: Undergrad student , Tel Aviv University

Papers (1)

MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning — ICLR 2024 poster

Tomer Asida

2025–present: Researcher , NVIDIA (IL)

2019–2024: Researcher , AI21 Labs (IL)

2014–2018: MS student , Hebrew University of Jerusalem (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Tong Lu

—–present: Full Professor , Nanjing University (CN)

—–present: Associate Professor , Nanjing University (CN)

—–present: Assistant Professor , Nanjing University (CN)

—–present: PhD student , Nanjing University (CN)

—–present: Undergrad student , Nanjing University (CN)

Papers (1)

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures — ICLR 2025 Spotlight

Tongliang Liu

2023–present: Associate Professor , University of Sydney (AU)

2020–present: Visiting Scientist , RIKEN (JP)

2022–2025: Affiliated Associate Professor , Mohamed bin Zayed University of Artificial Intelligence (AE)

2017–2023: Lecturer , University of Sydney

2016–2017: Lecturer , University of Technology Sydney

2012–2016: PhD , University of Technology Sydney

Papers (1)

State space models can express $n$-gram languages — Accepted by TMLR

Tongxin Bai

2022–present: Researcher , Beijing Institute of Artificial Intelligence (CN)

2019–2021: Research Scientist , Siemens Corporate Technology (CN)

2014–2019: Associate Professor , Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Chinese Academy of Sciences (CN)

2005–2011: PhD student , Department of Computer Science, University of Rochester (US)

2008–2008: Intern , Google (US)

2005–2005: Intern , Intel (CN)

2001–2004: MS student , Institute of Computing Technology, Chinese Academy of Sciences (CN)

1996–2000: Undergrad student , Fudan University (CN)

Papers (1)

MVA: Linear Attention with High-order Query-Keys Integration and Multi-level Vocabulary Decomposition — ICML 2025 poster

Truc Nguyen

2023–present: Postdoc , The National Renewable Energy Laboratory (US)

2018–2023: PhD student , University of Florida

Papers (1)

Swift Hydra: Self-Reinforcing Generative Framework for Anomaly Detection with Multiple Mamba Models — ICLR 2025 Poster

Trung Tuan Dao

2024–present: Researcher , Qualcomm Inc, QualComm (VN)

2020–2024: Researcher , VinAI Research (VN)

2016–2020: Undergrad student , Thang Long University (VN)

Papers (1)

DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation — NeurIPS 2024 poster

Tuan Dinh

2023–2025: Postdoc , University of California San Francisco (US)

2016–2023: Graduate student , Department of Computer Science, University of Wisconsin, Madison

Papers (1)

TabFlex: Scaling Tabular Learning to Millions with Linear Attention — ICML 2025 spotlightposter

Tuo Zhao

2017–present: Associate Professor , Georgia Institute of Technology (US)

2011–2016: PhD student , Johns Hopkins University

Papers (1)

Efficient Hybrid Long Sequence Modeling with State Space Augmented Transformers — COLM

Tushaar Gangavarapu

2025–present: PhD student , University of Texas at Austin (US)

2022–2024: MS student , Cornell University (US)

Papers (1)

MambaByte: Token-free Selective State Space Model — COLM

Uriya Pumerantz

2024–present: Researcher , Ai21 (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Vahab Mirrokni

2008–present: VP, Google Fellow , Google Research (US)

Papers (1)

MS-SSM: A Multi-Scale State Space Model for Efficient Sequence Modeling — COLM 2025

Vaishnavh Nagarajan

2021–present: Researcher , Google (US)

2015–2021: PhD student , School of Computer Science, Carnegie Mellon University (US)

2011–2015: Undergrad student , Indian Institute of Technology Madras (IN)

Papers (1)

The Pitfalls of Next-Token Prediction — ICML 2024 Poster

Velibor Bojkovic

2025–present: Assistant Professor , Mohamed bin Zayed University of Artificial Intelligence (AE)

2022–2025: Postdoc , Mohamed bin Zayed University of Artificial Intelligence (AE)

2019–2022: Postdoc , Université de Caen Basse Normandie (FR)

Papers (1)

Uncovering the Spectral Bias in Diagonal State Space Models — NeurIPS 2025 poster

Venkatesh Pattabiraman

2022–2024: MS student , New York University (US)

2018–2022: Undergrad student , Indian Institute of Technology, Indore (IN)

Papers (1)

Hierarchical State Space Models for Continuous Sequence-to-Sequence Modeling — ICML 2024 Poster

Viet Cuong Ta

2010–present: Lecturer , VNU University of Engineering and Technology (VN)

Papers (1)

Pseudo-Riemannian Graph Transformer — NeurIPS 2025 poster

Vihang Prakash Patil

2019–present: PhD student , Johannes Kepler University Linz

2017–2019: MS student , Università della Svizzera Italiana

2011–2015: Undergrad student , University of Mumbai

Papers (1)

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks — ICML 2025 poster

Vikram Appia

2024–present: Researcher , Advanced Micro Devices (US)

2017–2024: Researcher , Rivian (US)

2006–2012: PhD student , Georgia Institute of Technology (US)

Papers (1)

Zebra-Llama: Towards Extremely Efficient Hybrid Models — NeurIPS 2025 poster

Vinny Cahill

—–present: Full Professor , University of Dublin, Trinity College (IE)

Papers (1)

Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient — ICLR 2025 Poster

Vinoth Nandakumar

2024–present: Data scientist , Westpac (AU)

2021–present: Researcher , University of Sydney (AU)

2022–2022: Intern , Amazon (AU)

2019–2020: Postdoc , Max Planck Institute of Mathematics, Bonn (DE)

2016–2019: Postdoc , University of Sydney (AU)

Papers (1)

State space models can express $n$-gram languages — Accepted by TMLR

Viresh Pati

2023–present: Undergrad student , Georgia Institute of Technology (US)

Papers (1)

ZeroS: Zero‑Sum Linear Attention for Efficient Transformers — NeurIPS 2025 spotlight

Vladimir Braverman

2024–present: Full Professor , UT Health (US)

2022–present: Full Professor , Rice University (US)

2020–present: Researcher , Google (US)

2011–present: Full Professor , Department of Computer Science, Whiting School of Engineering (US)

Papers (1)

How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression? — ICLR 2024 spotlight

Volker Tresp

2011–present: Associate Professor , Ludwig Maximilian University of Munich (DE)

1990–present: Principal Researcher , Siemens Corporate Research (DE)

1984–1989: PhD student , Yale University (US)

Papers (1)

DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Models — Accepted by TMLR

Volodymyr Kuleshov

2020–present: Assistant Professor , Cornell University (US)

2017–2018: Postdoc , Stanford University

2011–2017: PhD student , Stanford University

Papers (1)

Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling — ICML 2024 Poster

Walid Saad

—–present: Full Professor , Virginia Tech (US)

2011–2014: Assistant Professor , University of Miami (US)

2011–2011: Postdoc , Princeton University (US)

2007–2010: PhD student , University of Oslo (NO)

Papers (1)

DMWM: Dual-Mind World Model with Long-Term Imagination — NeurIPS 2025 spotlight

Wan Choi

2020–present: Full Professor , Seoul National University (KR)

2017–2020: Full Professor , Korea Advanced Institute of Science & Technology (KR)

2011–2014: Associate Professor , Korea Advanced Institute of Science & Technology (KR)

2007–2014: Assistant Professor , Korea Advanced Institute of Science & Technology (KR)

Papers (1)

Gated Inference Network: Inference and Learning State-Space Models — NeurIPS 2024 poster

wang ning

2023–present: PhD student , Institute of automation, Chinese academy of science, Chinese Academy of Sciences (CN)

Papers (1)

MVA: Linear Attention with High-order Query-Keys Integration and Multi-level Vocabulary Decomposition — ICML 2025 poster

Wangbo Zhao

2022–present: PhD student , National University of Singapore (SG)

2022–2023: Intern , Shanghai AI Lab

2019–2022: MS student , Northwest Polytechnical University Xi'an

2015–2019: Undergrad student , Northwest Polytechnical University Xi'an

Papers (1)

Pruning-Robust Mamba with Asymmetric Multi-Scale Scanning Paths — NeurIPS 2025 poster

Wangkai Li

2025–2027: PhD student , University of Science and Technology of China (CN)

2022–2025: MS student , University of Science and Technology of China (CN)

2018–2022: Undergrad student , University of Science and Technology of China (CN)

Papers (1)

BeyondMix: Leveraging Structural Priors and Long-Range Dependencies for Domain-Invariant LiDAR Segmentation — NeurIPS 2025 poster

Wanrong Huang

2024–2025: Associate Professor , National University of Defense Technology (CN)

2023–2024: Assistant Research Fellow , National University of Defense Technology (CN)

2019–2022: Assistant Research Fellow , National Innovation Institute of Defense Technology (CN)

2015–2018: PhD student , National University of Defense Technology (CN)

Papers (1)

Effective and Efficient Time-Varying Counterfactual Prediction with State-Space Models — ICLR 2025 Poster

Wei Bi

2024–2025: Principal Researcher , Independent Researcher (CN)

2017–2024: Principal Researcher , Tencent AI Lab (CN)

2010–2015: PhD student , The Hong Kong University of Science and Technology (HK)

Papers (1)

Gated Slot Attention for Efficient Linear-Time Sequence Modeling — NeurIPS 2024 poster

Wei Chen

2023–present: PhD student , The Hong Kong University of Science and Technology, Guangzhou (CN)

2025–2025: Researcher , Ant Research (CN)

2024–2025: Researcher , Huawei 2012 Research (CN)

2022–2024: Researcher , Microsoft Research (CN)

2022–2022: Researcher , IFLYTEK Research (CN)

Papers (1)

Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective — NeurIPS 2024 poster

Wei Dong

2024–present: PhD student , McMaster University (CA)

2016–2019: MS student , Beijing University of Aeronautics and Astronautics (CN)

Papers (1)

ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correction — NeurIPS 2024 poster

Wei Fang

2022–present: Researcher , Alibaba Group (CN)

2017–2022: PhD student , Tsinghua University (CN)

2013–2017: Undergrad student , Tsinghua University (CN)

Papers (1)

Dual-Res Tandem Mamba-3D: Bilateral Breast Lesion Detection and Classification on Non-contrast Chest CT — NeurIPS 2025 poster

Wei Huang

2024–2029: Research Scientist , RIKEN AIP (JP)

2022–2023: Postdoc , RIKEN AIP

2017–2021: PhD student , University of Technology Sydney

2014–2017: MS student , University of Science and Technology of China

2010–2014: Undergrad student , University of Science and Technology of China

Papers (1)

Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression — NeurIPS 2025 poster

Wei Huang

2025–present: Intern , NVIDIA (US)

2023–present: PhD student , University of Hong Kong (HK)

2019–2023: Undergrad student , Beijing University of Aeronautics and Astronautics (CN)

Papers (1)

From Layers to States: A State Space Model Perspective to Deep Neural Network Layer Dynamics — ICLR 2025 Poster

Wei Ji

2024–present: Postdoc , Yale University (US)

2020–2024: PhD student , University of Alberta (CA)

2022–2023: Visiting PhD student , Johns Hopkins University (US)

Papers (1)

Samba: Severity-aware Recurrent Modeling for Cross-domain Medical Image Grading — NeurIPS 2024 poster

Wei Li

2025–2028: PhD student , Zhejiang University of Technology (CN)

2023–2025: MS student , Zhejiang University of Technology (CN)

2019–2023: Undergrad student , Zhejiang University of Technology (CN)

Papers (1)

Alias-Free Mamba Neural Operator — NeurIPS 2024 poster

Wei Lin

2023–2025: Researcher , Johannes Kepler Universität Linz (AT)

2019–2023: PhD student , Technische Universität Graz (AT)

Papers (1)

pLSTM: parallelizable Linear Source Transition Mark networks — NeurIPS 2025 poster

Wei Shao

2022–present: Assistant Professor , University of Florida (US)

2019–2022: Postdoc , Stanford University (US)

2014–2019: PhD student , University of Iowa (US)

Papers (1)

Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More — ICML 2025 poster

Wei Wu

2023–present: Researcher , Ant Research (CN)

2020–2022: Researcher , Meituan (CN)

2012–2020: Researcher , Microsoft Research (CN)

Papers (1)

Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access — NeurIPS 2025 poster

Wei Xiao

2022–2026: PhD student , Beijing Institute of Technology

Papers (1)

DyMoDreamer: World Modeling with Dynamic Modulation — NeurIPS 2025 poster

Wei Xu

2023–2027: PhD student , Huazhong University of Science and Technology (CN)

2020–2023: MS student , Beijing University of Posts and Telecommunications

Papers (1)

PointMamba: A Simple State Space Model for Point Cloud Analysis — NeurIPS 2024 poster

Wei Yang

2021–present: Associate Professor , Huazhong University of Science and Technology (CN)

2020–2021: Researcher , Google (US)

2018–2020: Research Scientist , DGene inc (US)

2013–2017: PhD student , University of Delaware (US)

2015–2015: Intern , Adobe Systems (US)

2011–2013: Researcher , Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Chinese Academy of Sciences (CN)

2007–2009: MS student , Harbin Institute of Technology (CN)

2003–2007: Undergrad student , Huazhong University of Science and Technology (CN)

Papers (1)

Coupled Mamba: Enhanced Multimodal Fusion with Coupled State Space Model — NeurIPS 2024 poster

Wei-Fang Sun

2023–2025: Researcher , NVIDIA AI Technology Center (TW)

2021–2023: MS student , Department of Computer Science, National Tsing Hua University, National Tsing Hua University (TW)

2017–2021: Undergrad student , Department of Computer Science, National Tsing Hua University, National Tsing Hua University (TW)

Papers (1)

EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling — NeurIPS 2025 spotlight

Weian Mao

2020–2025: PhD student , University of Adelaide (AU)

Papers (1)

Revisiting Convolution Architecture in the Realm of DNA Foundation Models — ICLR 2025 Poster

Weihan Li

2023–present: PhD student , Georgia Institute of Technology (US)

2020–2023: MS student , Zhejiang University

2016–2020: Undergrad student , Zhejiang University

Papers (1)

Learning Time-Varying Multi-Region Brain Communications via Scalable Markovian Gaussian Processes — ICML 2025 oral

Weijia Zhang

2024–2025: Researcher , Shanghai Jiao Tong University (CN)

2021–2025: Researcher , University of Sydney, University of Sydney (AU)

2018–2019: MS student , Imperial College London (GB)

2015–2018: Undergrad student , Imperial College London (GB)

Papers (1)

QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model — NeurIPS 2024 poster

Weikang Meng

2023–2028: PhD student , Harbin Institute of Technology, Shenzhen (CN)

2019–2023: Undergrad student , Harbin Institute of Technology (CN)

Papers (1)

PolaFormer: Polarity-aware Linear Attention for Vision Transformers — ICLR 2025 Poster

Weili Cao

2023–2025: MS student , University of California, San Diego (US)

2019–2023: Undergrad student , University of California, San Diego (US)

Papers (1)

Single-Pass Document Scanning for Question Answering — COLM 2025

Weipu Zhang

2025–2029: PhD student , Beijing Institute of Technology (CN)

2023–2024: MS student , University of Edinburgh (GB)

2019–2023: Undergrad student , Beijing Institute of Technology

2021–2022: Intern , Research, Baidu

Papers (1)

DyMoDreamer: World Modeling with Dynamic Modulation — NeurIPS 2025 poster

Weiqiang Bai

2022–present: MS student , Dalian University of Technology (CN)

Papers (1)

Revisiting Convolution Architecture in the Realm of DNA Foundation Models — ICLR 2025 Poster

Weiqiang Wang

2015–present: Researcher , Ant Group (CN)

2008–2011: Researcher , University of Southern California (US)

2002–2008: PhD student , University of Southern California (US)

Papers (1)

Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training — ICML 2025 poster

Weiqin Zhao

2021–2025: PhD student , University of Hong Kong (HK)

2017–2021: Undergrad student , Beihang University (CN)

Papers (1)

From Layers to States: A State Space Model Perspective to Deep Neural Network Layer Dynamics — ICLR 2025 Poster

Weiyao Lin

2018–present: Full Professor , Shanghai Jiao Tong University (CN)

2013–2017: Associate Professor , Shanghai Jiao Tong University (CN)

2010–2012: Assistant Professor , Shanghai Jiao Tong University (CN)

2005–2010: PhD student , University of Washington (US)

Papers (1)

Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions — ICLR 2025 Poster

Weiyun Wang

2022–present: PhD student , Fudan University (CN)

2018–2022: Undergrad student , Harbin Institute of Technology (CN)

Papers (1)

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures — ICLR 2025 Spotlight

Wenbing Li

2023–2029: PhD student , Huazhong University of Science and Technology (CN)

Papers (1)

Coupled Mamba: Enhanced Multimodal Fusion with Coupled State Space Model — NeurIPS 2024 poster

Wenbo Gou

2024–2025: Research Assistant , CMU, Carnegie Mellon University (US)

2023–2024: MS student , Carnegie Mellon University (US)

2022–2023: Intern , The Chinese University of Hong Kong,ShenZhen (CN)

2018–2022: Undergrad student , Huazhong University of Science and Technology (CN)

Papers (1)

Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba — NeurIPS 2024 poster

Wenfei Yang

2024–present: Assistant Professor , University of Science and Technology of China (CN)

2022–2024: Postdoc , University of Science and Technology of China (CN)

2017–2022: PhD student , University of Science and Technology of China (CN)

2013–2017: Undergrad student , University of Science and Technology of China (CN)

Papers (1)

State Space Model Meets Transformer: A New Paradigm for 3D Object Detection — ICLR 2025 Poster

Wenhai Wang

2023–present: Postdoc , The Chinese University of Hong Kong (HK)

2021–2023: Researcher , Shanghai AI Laboratory (CN)

2016–2021: PhD student , Nanjing University (CN)

Papers (1)

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures — ICLR 2025 Spotlight

Wenhan Xiong

2021–present: Researcher , Facebook

2016–2021: PhD student , , UC Santa Barbara

Papers (1)

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length — NeurIPS 2024 poster

Wenjie Du

2024–2027: Assistant Professor , University of Science and Technology of China (CN)

2021–2023: PhD student , University of Science and Technology of China (CN)

Papers (1)

Enhancing the Maximum Effective Window for Long-Term Time Series Forecasting — NeurIPS 2025 poster

Wenjun Huang

2022–present: PhD student , SUN YAT-SEN UNIVERSITY (CN)

2017–2020: MS student , Central South University (CN)

2013–2017: Undergrad student , Guilin University of Electronic Technology (CN)

Papers (1)

EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment — ICLR 2025 Poster

Wenlong Wang

2025–present: Researcher , Intercom (IE)

2023–2025: Postdoc , University of Dublin, Trinity College (IE)

2019–2023: PhD student , Massey University (NZ)

Papers (1)

Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient — ICLR 2025 Poster

Wentao Shu

2024–present: MS student , Fudan University (CN)

2020–2024: Undergrad student , Fudan University (CN)

Papers (1)

Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures — ICLR 2025 Poster

Wenyi Wang

2022–present: PhD student , King Abdullah University of Science and Technology (SA)

2021–2022: Intern , Borealis AI (CA)

2015–2019: MS student , University of British Columbia (CA)

2018–2018: Intern , Amazon (DE)

2012–2015: Undergrad student , University of Utah (US)

Papers (1)

FACTS: A Factored State-Space Framework for World Modelling — ICLR 2025 Poster

Wenyu Liu

2001–present: Full Professor , Huazhong University of Science and Technology (CN)

1997–2000: PhD student , Huazhong University of Science and Technology (CN)

Papers (1)

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model — ICML 2024 Poster

William F Whitney

2021–present: Researcher , DeepMind

2016–2021: PhD student , New York University

Papers (1)

Linear Transformer Topological Masking with Graph Random Features — ICLR 2025 Poster

Winnie Xu

2017–2022: Undergrad student , University of Toronto

Papers (1)

Deep Latent State Space Models for Time-Series Generation — ICML 2023 Poster

Woomin Song

2023–present: PhD student , KAIST (KR)

2022–2023: MS student , KAIST

2018–2022: Undergrad student , KAIST

Papers (1)

Sparsified State-Space Models are Efficient Highway Networks — Accepted by TMLR

Xi Wang

2022–present: Postdoc , ETHZ - ETH Zurich (CH)

2014–2021: PhD student , Technische Universität Berlin (DE)

Papers (1)

StateSpaceDiffuser: Bringing Long Context to Diffusion World Models — NeurIPS 2025 poster

Xiang Cheng

2020–2023: Postdoc , Massachusetts Institute of Technology

2014–2020: PhD student , University of California Berkeley

Papers (1)

Linear attention is (maybe) all you need (to understand Transformer optimization) — ICLR 2024 poster

Xiang Deng

2024–2025: Full Professor , Harbin Institute of Technology (CN)

2024–2025: Full Professor , Harbin Institute of Technology (Shenzhen)) (CN)

2018–2022: PhD student , State University of New York, Binghamton (US)

Papers (1)

Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL — NeurIPS 2024 poster

Xiang Fang

2022–present: PhD student , Nanyang Technological University (SG)

2020–2022: Researcher , Huazhong University of Science and Technology (CN)

2018–2020: MS student , Huazhong University of Science and Technology (CN)

Papers (1)

DyPolySeg: Taylor Series-Inspired Dynamic Polynomial Fitting Network for Few-shot Point Cloud Semantic Segmentation — ICML 2025 poster

Xiang Hu

2017–present: Researcher , Alibaba Group (CN)

2011–2013: MS student , Shanghai Jiaotong University

2007–2011: Undergrad student , Shanghai Jiaotong University

Papers (1)

Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access — NeurIPS 2025 poster

Xiang Liu

2020–present: Full Professor , Dongguan University of Technology (CN)

2019–2021: Postdoc , University of Science and Technology of China (CN)

2014–2019: PhD student , Beijing Institute of Technology (CN)

Papers (1)

State Space Model Meets Transformer: A New Paradigm for 3D Object Detection — ICLR 2025 Poster

Xiangchi Yuan

2024–2029: PhD student , Georgia Institute of Technology (US)

2025–2025: Intern , Adobe Systems (US)

2022–2024: MS student , Brandeis University (US)

2018–2022: Undergrad student , University of Electronic Science and Technology of China (US)

Papers (1)

LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement — ICLR 2025 Poster

Xiangsheng Shi

2020–2023: MS student , Tsinghua University, Tsinghua University

Papers (1)

Evaluating Quantized Large Language Models — ICML 2024 Poster

Xiangtai Li

2024–present: Researcher , ByteDance Inc. (SG)

2022–2024: Postdoc , Nanyang Technological University (SG)

2021–2022: Intern , SenseTime (CN)

2021–2022: Intern , JD Explore Academy (CN)

2017–2022: PhD student , Peking University (CN)

2020–2021: Intern , Microsoft (CN)

2013–2017: Undergrad student , Beijing University of Post and Telecommunication (CN)

Papers (1)

MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection — NeurIPS 2024 poster

Xiangyu Chang

2021–present: PhD student , University of California, Riverside (US)

2019–2020: MS student , University of California, Riverside (US)

2015–2019: Undergrad student , Huazhong University of Science and Technology (CN)

Papers (1)

Theoretical Insights into In-context Learning with Unlabeled Data — NeurIPS 2025 poster

Xiangyu Yin

2022–2025: PhD student , University of Liverpool (GB)

2021–2022: PhD student , University of Exeter (GB)

2015–2020: Undergrad student , Beijing University of Posts and Telecommunications (CN)

2019–2019: Intern , University of Maryland, College Park (US)

Papers (1)

Toward Linearly Regularizing the Geometric Bottleneck of Linear Generalized Attention — Accepted by TMLR

Xiangyuan Lan

2022–present: Researcher , Pengcheng Laboratory (CN)

2018–2021: Research Assistant Professor , Hong Kong Baptist University (HK)

2012–2016: PhD student , Hong Kong Baptist University (HK)

Papers (1)

EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment — ICLR 2025 Poster

Xianhang Li

2021–2026: PhD student , University of California, Santa Cruz (US)

2019–2021: MS student , University of Central Florida (US)

2014–2018: Undergrad student , Beijing University of Post and Telecommunication (CN)

Papers (1)

Autoregressive Pretraining with Mamba in Vision — ICLR 2025 Poster

Xiao Sheng

2012–2015: MS student , Tsinghua University, Tsinghua University

2008–2012: Undergrad student , Tsinghua University, Tsinghua University

Papers (1)

QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion — NeurIPS 2024 poster

Xiao Tan

2016–present: Researcher , Baidu (CN)

2015–2016: research fellow , The University of Hong Kong (HK)

2010–2014: PhD student , University of New South Wales (AU)

Papers (1)

PointMamba: A Simple State Space Model for Point Cloud Analysis — NeurIPS 2024 poster

Xiaodong Cui

—–present: Principal Research Staff Member , IBM T. J. Watson Research Center (US)

Papers (1)

Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis — ICLR 2025 Poster

Xiaodong Liu

2015–present: Researcher , Microsoft Research (US)

2011–2015: PhD student , Nara Institute of Science and Technology, Japan

Papers (1)

Efficient Hybrid Long Sequence Modeling with State Space Augmented Transformers — COLM

Xiaofei Cao

2023–present: Principal Researcher , Toyota Motor Corporation (US)

2016–2021: PhD student , Missouri University of Science and Technology (US)

Papers (1)

MamBEV: Enabling State Space Models to Learn Birds-Eye-View Representations — ICLR 2025 Poster

Xiaofeng Ling

2021–present: Associate Professor , East China University of Science and Technology (CN)

2018–2021: Lecturer , East China University of Science and Technology (CN)

2016–2018: Postdoc , East China University of Science and Technology (CN)

Papers (1)

CSV-Occ: Fusing Multi-frame Alignment for Occupancy Prediction with Temporal Cross State Space Model and Central Voting Mechanism — ICML 2025 poster

Xiaofeng Liu

2024–2026: Postdoc , University of Michigan - Ann Arbor (US)

Papers (1)

Theoretical Insights into In-context Learning with Unlabeled Data — NeurIPS 2025 poster

Xiaohong Liu

2025–present: Associate Professor , Shanghai Jiaotong University (CN)

2022–2024: Assistant Professor , Shanghai Jiao Tong University (CN)

2018–2021: PhD student , McMaster University (CA)

2014–2016: MS student , University of Ottawa (CA)

2010–2014: Undergrad student , Southwest Jiaotong University (CN)

Papers (1)

ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correction — NeurIPS 2024 poster

Xiaojiang Peng

2024–present: Full Professor , Shenzhen Technology University (CN)

2020–2023: Associate Professor , Shenzhen Technology University (CN)

2017–2020: Associate Professor , Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Chinese Academy of Sciences (CN)

2016–2017: Postdoc , Idiap Research Institute (CH)

2015–2016: Postdoc , INRIA (FR)

Papers (1)

Pruning-Robust Mamba with Asymmetric Multi-Scale Scanning Paths — NeurIPS 2025 poster

Xiaojie Guo

2024–present: Full Professor , Tianjin University (CN)

Papers (1)

MODEM: A Morton-Order Degradation Estimation Mechanism for Adverse Weather Image Recovery — NeurIPS 2025 poster

Xiaoling Luo

2023–present: Assistant Professor , Shenzhen University (CN)

2017–2023: PhD student , Harbin Institute of Technology (CN)

Papers (1)

Hierarchical Information Aggregation for Incomplete Multimodal Alzheimer's Disease Diagnosis — NeurIPS 2025 poster

Xiaolong Wang

2020–present: Assistant Professor , University of California, San Diego (US)

2019–2020: Postdoc , University of California Berkeley (US)

2014–2019: PhD student , Carnegie Mellon University (US)

Papers (1)

Learning to (Learn at Test Time): RNNs with Expressive Hidden States — ICML 2025 spotlightposter

Xiaomeng Yang

2024–present: Research Engineer , Google DeepMind (US)

2023–2024: Member of Technical Staff , Moonshot AI (US)

2017–2023: Software Engineer , Meta (US)

2016–2017: Software Engineer , Google (US)

2014–2016: Software Engineer , Google (CN)

2012–2014: PhD student (dropped out) , Tsinghua University, Tsinghua University (CN)

2008–2012: Undergrad student , Beijing Institute of Technology (CN)

Papers (1)

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length — NeurIPS 2024 poster

Xiaoqi Li

2023–2027: PhD student , Peking University (CN)

2020–2022: MS student , Columbia University (US)

Papers (1)

RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation — NeurIPS 2024 poster

Xiaoqin Zhang

2023–present: Full Professor , Zhejiang University of Technology (CN)

2016–2023: Full Professor , Wenzhou University

2012–2016: Associate Professor , Wenzhou University

2010–2012: Assistant Professor , Wenzhou University

2005–2010: PhD student , Institute of automation, Chinese academy of science, Chinese Academy of Sciences

Papers (1)

Alias-Free Mamba Neural Operator — NeurIPS 2024 poster

Xiaotong Zhao

2020–present: Researcher , Tencent PCG (CN)

2015–2020: PhD student , Beijing University of Posts and Telecommunications (CN)

Papers (1)

VFIMamba: Video Frame Interpolation with State Space Models — NeurIPS 2024 poster

Xiaowei Huang

—–present: Full Professor , University of Liverpool (GB)

Papers (1)

Toward Linearly Regularizing the Geometric Bottleneck of Linear Generalized Attention — Accepted by TMLR

Xiaowen Ma

2023–present: Researcher , Huawei Technologies Ltd. (CN)

2021–2024: MS student , Zhejiang University (CN)

2017–2021: Undergrad student , Zhejiang University (CN)

Papers (1)

TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-state — ICML 2025 poster

XiaoxuLin

2023–2026: MS student , Zhejiang University of Technology (CN)

Papers (1)

Alias-Free Mamba Neural Operator — NeurIPS 2024 poster

Xiaqiang Tang

2024–2027: PhD student , Hong Kong University of Science and Technology(GZ) (CN)

Papers (1)

Improving Bilinear RNN with Closed-loop Control — NeurIPS 2025 spotlight

Ximeng Mao

2020–present: PhD student , University of Montreal (CA)

2018–2020: MS student , McGill University, McGill University (CA)

Papers (1)

Generalizable, real-time neural decoding with hybrid state-space models — NeurIPS 2025 poster

Xin Chen

2024–present: Researcher , ByteDance Inc. (US)

2022–2024: Researcher , Tencent (CN)

2018–2022: PhD student , ShanghaiTech University (CN)

Papers (1)

3DET-Mamba: Causal Sequence Modelling for End-to-End 3D Object Detection — NeurIPS 2024 poster

Xin Du

2023–present: Assistant Professor , Waseda University (JP)

2020–2023: PhD student , The University of Tokyo

2018–2020: MS student , The University of Tokyo

2012–2017: Undergrad student , Tongji University

Papers (1)

Correlation Dimension of Autoregressive Large Language Models — NeurIPS 2025 poster

Xin Li

2022–present: Researcher , Pengcheng Laboratory (CN)

2020–2022: Postdoc , Pengcheng Laboratory (CN)

2014–2020: PhD student , Harbin Institute of Technology (CN)

Papers (1)

PolaFormer: Polarity-aware Linear Attention for Vision Transformers — ICLR 2025 Poster

Xin Li

2024–2026: Postdoc , University of Science and Technology of China (CN)

2023–2024: PhD student , National University of Singapore (SG)

2019–2024: PhD student , University of Science and Technology of China (CN)

2021–2022: Intern , Microsoft

2015–2019: Undergrad student , University of Science and Technology of China (CN)

Papers (1)

QMamba: On First Exploration of Vision Mamba for Image Quality Assessment — ICML 2025 poster

Xin Li

2016–present: Associate Professor , Beijing Institute of Technology (CN)

2010–2016: Assistant Professor , Beijing Institute of Technology (CN)

2004–2009: PhD student , Hong Kong Baptist University (CN)

Papers (1)

Learning Latent Dynamic Robust Representations for World Models — ICML 2024 Poster

Xin T. Tong

2022–present: Associate Professor , National University of Singapore (SG)

2016–present: Assistant Professor , National University of Singapore

2016–2022: Assistant Professor , National University of Singapore (SG)

2013–2016: Postdoc , NYU, New York University (US)

2009–2013: PhD student , Princeton University (US)

Papers (1)

Demystifying the Token Dynamics of Deep Selective State Space Models — ICLR 2025 Spotlight

Xin Zhou

2025–2030: PhD student , Huazhong University of Science and Technology (CN)

Papers (1)

PointMamba: A Simple State Space Model for Point Cloud Analysis — NeurIPS 2024 poster

Xing Hu

2023–present: Researcher , houmo.ai (CN)

2020–2023: MS student , Hohai University (CN)

Papers (1)

MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods — ICLR 2025 Poster

Xinggang Wang

2021–present: Full Professor , Huazhong University of Science and Technology (CN)

2017–2021: Associate Professor , Huazhong University of Science and Technology (CN)

Papers (1)

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model — ICML 2024 Poster

Xinghao Ding

2003–present: Full Professor , Xiamen University (CN)

Papers (1)

FRN: Fractal-Based Recursive Spectral Reconstruction Network — NeurIPS 2025 poster

Xingjian Du

2024–2029: PhD student , University of Rochester (CN)

2018–2024: Researcher , ByteDance AI Lab

Papers (1)

RWKV-7 "Goose" with Expressive Dynamic State Evolution — COLM 2025

Xingkui Zhu

2022–2026: PhD student , Huazhong University of Science and Technology (CN)

Papers (1)

PointMamba: A Simple State Space Model for Point Cloud Analysis — NeurIPS 2024 poster

Xingxing Liang

2022–2025: Lecturer , National University of Defense Technology (CN)

2017–2021: PhD student , National University of Defense Technology (CN)

Papers (1)

Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning? — NeurIPS 2024 poster

Xingyang Li

2025–2026: Intern , Massachusetts Institute of Technology (US)

2022–2026: Undergrad student , Shanghai Jiaotong University (CN)

Papers (1)

Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation — NeurIPS 2025 poster

Xinhao Li

2024–present: PhD student , University of California, San Diego (US)

2022–2024: MS student , University of California, San Diego (US)

2018–2022: Undergrad student , University of Electronic Science and Technology of China (CN)

Papers (1)

Learning to (Learn at Test Time): RNNs with Expressive Hidden States — ICML 2025 spotlightposter

Xinke Shen

2023–2025: Postdoc , Southern University of Science and Technology (CN)

2017–2023: PhD student , Tsinghua University, Tsinghua University (CN)

2013–2017: Undergrad student , Beijing University of Aeronautics and Astronautics (CN)

Papers (1)

Multi-dataset Joint Pre-training of Emotional EEG Enables Generalizable Affective Computing — NeurIPS 2025 poster

Xinlei Chen

2018–present: Researcher , Meta (US)

2012–2018: PhD student , School of Computer Science, Carnegie Mellon University (US)

2008–2012: Undergraduate , Zhejiang University (CN)

Papers (1)

Learning to (Learn at Test Time): RNNs with Expressive Hidden States — ICML 2025 spotlightposter

Xinlong Wang

2022–present: Researcher , Beijing Academy of Artificial Intelligence (CN)

2020–2022: PhD student , The University of Adelaide (AU)

2014–2018: Undergrad student , Tongji University (CN)

Papers (1)

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model — ICML 2024 Poster

Xinping Yi

2023–2050: Full Professor , Southeast University (CN)

2017–2023: Assistant Professor , University of Liverpool

Papers (1)

Toward Linearly Regularizing the Geometric Bottleneck of Linear Generalized Attention — Accepted by TMLR

Xinrong Zhang

2025–present: Researcher , ByteDance Inc. (CN)

2019–2024: PhD student , Tsinghua University (CN)

Papers (1)

Stuffed Mamba: Oversized States Lead to the Inability to Forget — COLM 2025

Xinyi Wan

2025–present: PhD student , national university of singaore, National University of Singapore (SG)

2021–present: Researcher , Sea AI Lab (SG)

2013–2016: MS student , Zhejiang University

Papers (1)

ZeCO: Zero-Communication Overhead Sequence Parallelism for Linear Attention — NeurIPS 2025 poster

Xinyu Wang

2022–2025: MS student , Huazhong University of Science and Technology

2018–2022: Undergrad student , Huazhong University of Science and Technology

Papers (1)

LION: Linear Group RNN for 3D Object Detection in Point Clouds — NeurIPS 2024 poster

Xinyu Wang

2025–2029: PhD student , University of Western Australia (AU)

Papers (1)

CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation — NeurIPS 2025 poster

Xinyu Wang

2025–present: PhD student , McGill University, McGill University (CA)

2023–2024: MS student , McGill University, McGill University (CA)

2019–2022: Undergrad student , McGill University, McGill University (CA)

Papers (1)

Mamba Modulation: On the Length Generalization of Mamba Models — NeurIPS 2025 poster

Xinzhou Jin

2022–2025: MS student , SUN YAT-SEN UNIVERSITY (CN)

2018–2022: Undergrad student , South China University of Technology (CN)

Papers (1)

State Space Models on Temporal Graphs: A First-Principles Study — NeurIPS 2024 poster

Xinzhu Ma

2025–present: Associate Professor , Beihang University (CN)

2024–2025: Postdoc , The Chinese University of Hong Kong (CN)

2020–2023: PhD student , University of Sydney (AU)

2017–2019: MS student , Dalian University of Technology (CN)

Papers (1)

Revisiting Convolution Architecture in the Realm of DNA Foundation Models — ICLR 2025 Poster

Xipeng Qiu

2024–present: Full Professor , Shanghai Innovation Institution (CN)

2006–present: Full Professor , Fudan University (CN)

Papers (1)

Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures — ICLR 2025 Poster

Xizhou Zhu

2023–present: Researcher , Shanghai AI Laboratory (CN)

2023–present: Postdoc , Tsinghua University (CN)

2020–2023: Researcher , SenseTime (CN)

2015–2020: PhD student , University of Science and Technology of China (CN)

2015–2020: Intern , Microsoft Research Asia (CN)

Papers (1)

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures — ICLR 2025 Spotlight

Xu Han

2024–present: Assistant Professor , Tsinghua University, Tsinghua University (CN)

2022–2024: Postdoc , Tsinghua University, Tsinghua University (CN)

2017–2022: PhD student , Tsinghua University, Tsinghua University (CN)

2013–2017: Undergrad student , Tsinghua University, Tsinghua University (CN)

Papers (1)

Stuffed Mamba: Oversized States Lead to the Inability to Forget — COLM 2025

Xu Owen He

2025–present: CTO , MakerMaker AI (US)

2020–2024: Research Scientist , Google DeepMind (CA)

2019–2020: PhD student , University of Groningen (NL)

2016–2019: PhD student , Jacobs University Bremen (DE)

Papers (1)

Forgetting Transformer: Softmax Attention with a Forget Gate — ICLR 2025 Poster

Xu Zou

2024–present: Assistant Professor , Huazhong University of Science and Technology (CN)

Papers (1)

State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding — NeurIPS 2025 poster

Xuanyi Liu

2024–present: PhD student , Peking University (CN)

2023–2024: Researcher , Nanyang Technological University (SG)

2021–2023: MS student , Nanyang Technological University

2019–2020: Intern , Megvii Technology Inc.

2015–2019: Undergrad student , Wuhan University

Papers (1)

Hybrid Mamba for Few-Shot Segmentation — NeurIPS 2024 poster

Xuanyu Yi

2021–2025: PhD student , Nanyang Technological University (SG)

2017–2021: Undergrad student , Tsinghua University (CN)

Papers (1)

MVGamba: Unify 3D Content Generation as State Space Sequence Modeling — NeurIPS 2024 poster

Xue Lin

2023–present: Associate Professor , Northeastern University (US)

2017–2023: Assistant Professor , Northeastern University (US)

Papers (1)

Sparse Learning for State Space Models on Mobile — ICLR 2025 Poster

Xuefei Ning

2024–present: Research Assistant Professor , Tsinghua University (CN)

2022–2023: Postdoc , Tsinghua University (CN)

2022–2023: Postdoc , Huawei Technologies Ltd. (CN)

2016–2021: PhD student , Tsinghua University (CN)

2012–2016: Undergrad student , Tsinghua University (CN)

Papers (1)

Evaluating Quantized Large Language Models — ICML 2024 Poster

Xuerui Qiu

2024–present: PhD student , Institute of automation, Chinese Academy of Sciences (CN)

2020–2024: Undergrad student , University of Electronic Science and Technology of China (CN)

Papers (1)

Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking — NeurIPS 2025 poster

Xueyang Fu

2025–present: Full Professor , University of Science and Technology of China (CN)

2023–2024: Associate Professor , University of Science and Technology of China (CN)

2018–2023: Researcher , University of Science and Technology of China (CN)

Papers (1)

FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining — ICML 2025 poster

Xuezhe Ma

2020–present: Assistant Professor , USC/ISI (US)

2014–2020: PhD student , School of Computer Science, Carnegie Mellon University (US)

2010–2013: MS student , School of Computer Science, Shanghai Jiao Tong University (CN)

Papers (1)

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length — NeurIPS 2024 poster

Xufang Luo

2020–present: Researcher , Microsoft Research (CN)

2015–2020: PhD student , Beihang University (CN)

Papers (1)

SCBench: A KV Cache-Centric Analysis of Long-Context Methods — ICLR 2025 Poster

Xuhui Fan

2023–present: Lecturer , Macquarie University (AU)

2022–2023: Lecturer , University of Newcastle

2017–2022: Postdoc , University of New South Wales

Papers (1)

Free-Form Variational Inference for Gaussian Process State-Space Models — ICML 2023 Poster

XulongTang

2025–present: PhD student , State University of New York at Albany (US)

2024–present: Researcher , Malou Tech Inc (US)

2018–2022: Undergrad student , Xi'an University of Electronic Science and Technology (CN)

Papers (1)

MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation — NeurIPS 2025 poster

Xunlan Zhou

2023–2027: Undergrad student , Nanjing University (CN)

2025–2026: Intern , University of California, Berkeley (US)

Papers (1)

Leveraging Conditional Dependence for Efficient World Model Denoising — NeurIPS 2025 poster

Xunyuan Yin

2021–present: Assistant Professor , Nanyang Technological University (SG)

Papers (1)

MamKO: Mamba-based Koopman operator for modeling and predictive control — ICLR 2025 Spotlight

Xuran Pan

2018–2024: PhD student , Tsinghua University, Tsinghua University

2014–2018: Undergrad student , Tsinghua University, Tsinghua University

Papers (1)

Bridging the Divide: Reconsidering Softmax and Linear Attention — NeurIPS 2024 poster

Xutao Wang

2021–2022: Researcher , Huawei Technologies Ltd.

2019–2021: MS student , School of mathematical Science, Peking University, Peking University

2015–2019: Undergrad student , School of mathematical Science, Peking University, Peking University

Papers (1)

DiJiang: Efficient Large Language Models through Compact Kernelization — ICML 2024 Oral

Xuyang Ge

2024–2027: MS student , Fudan University (CN)

2020–2024: Undergrad student , Fudan University (CN)

Papers (1)

Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures — ICLR 2025 Poster

Yabo Liu

2025–present: Lecturer , Ocean University of China (CN)

2021–2025: PhD student , Harbin Institute of Technology (CN)

Papers (1)

Hierarchical Information Aggregation for Incomplete Multimodal Alzheimer's Disease Diagnosis — NeurIPS 2025 poster

Yachao Zhang

2024–2027: Assistant Professor , Xiamen University (CN)

2022–2024: Postdoc , Tsinghua University (CN)

2018–2022: PhD student , Xiamen University,

Papers (1)

MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models — NeurIPS 2024 poster

Yadan Luo

2024–present: Associate Professor , The University of Queensland (AU)

2022–2024: Assistant Professor , The University of Queensland (AU)

2021–2022: Postdoc , University of Queensland (AU)

Papers (1)

PolaFormer: Polarity-aware Linear Attention for Vision Transformers — ICLR 2025 Poster

Yadong Li

2024–2029: PhD student , University of Washington (US)

Papers (1)

RFMamba: Frequency-Aware State Space Model for RF-Based Human-Centric Perception — ICLR 2025 Poster

Yadong Lu

2021–present: Researcher , Microsoft (US)

2016–2021: PhD student , University of California, Irvine

Papers (1)

Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling — ICLR 2025 Poster

Yair Schiff

2022–2028: PhD student , Department of Computer Science, Cornell University (US)

2017–2019: MS student , New York University (US)

2010–2014: Undergrad student , University of Pennsylvania (US)

Papers (1)

Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling — ICML 2024 Poster

Yan Chen

2020–present: Full Professor , University of Science and Technology of China (CN)

Papers (1)

RFMamba: Frequency-Aware State Space Model for RF-Based Human-Centric Perception — ICLR 2025 Poster

Yan Lin

2024–present: Postdoc , Aalborg University, Aalborg University (DK)

2019–2024: PhD student , Beijing Jiaotong University (CN)

2022–2023: PhD student , Aalborg University (DK)

2015–2019: Undergrad student , Beijing Jiaotong University (CN)

Papers (1)

TrajMamba: An Efficient and Semantic-rich Vehicle Trajectory Pre-training Model — NeurIPS 2025 spotlight

Yan Ru Pei

2025–present: Engineer , NVIDIA (US)

2021–2025: Researcher , Brainchip Inc (US)

2017–2021: PhD student , University of California, San Diego (US)

2016–2017: Researcher , Massachusetts Institute of Technology (US)

2014–2016: Undergrad student , University of California, Los Angeles (US)

Papers (1)

Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions — ICLR 2025 Spotlight

Yan Sun

2025–present: Postdoc , Western University (CA)

2020–2025: PhD student , University of Manitoba (CA)

Papers (1)

Structure-Aware Fusion with Progressive Injection for Multimodal Molecular Representation Learning — NeurIPS 2025 poster

Yan Yi Li

2023–present: MS student , University of Toronto (CA)

2018–2023: Undergrad student , University of Waterloo (CA)

Papers (1)

Structure-Aware Fusion with Progressive Injection for Multimodal Molecular Representation Learning — NeurIPS 2025 poster

Yana Veitsman

2023–2025: MS student , Universität des Saarlandes (DE)

2019–2022: Undergrad student , American University in Bulgaria (BG)

Papers (1)

The Expressive Capacity of State Space Models: A Formal Language Perspective — NeurIPS 2024 poster

Yandong Guo

2023–present: Chief Scientist , AI^2 Robotics (CN)

2020–2022: Chief Scientist , OPPO Research Institute (CN)

Papers (1)

RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation — NeurIPS 2024 poster

Yanfeng Zhou

2020–2025: PhD student , University of Chinese Academy of Sciences (CN)

2020–2025: PhD student , Institute of automation, Chinese academy of science (CN)

2016–2020: Undergrad student , Northeastern University (CN)

Papers (1)

Dual-Res Tandem Mamba-3D: Bilateral Breast Lesion Detection and Classification on Non-contrast Chest CT — NeurIPS 2025 poster

Yang Dai

2024–2028: PhD student , National University of Defense Technology (CN)

Papers (1)

Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning? — NeurIPS 2024 poster

Yang Gao

2024–present: Full Professor , Nanjing University (CN)

2008–2024: Full Professor , Nanjing University (CN)

2003–2008: Associate Professor , Nanjing University (CN)

2000–2003: Lecturer , Nanjing University (CN)

1997–2000: PhD student , Nanjing University (CN)

Papers (1)

START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation — NeurIPS 2024 poster

Yang Hu

2020–present: Associate Professor , University of Science and Technology of China (CN)

Papers (1)

RFMamba: Frequency-Aware State Space Model for RF-Based Human-Centric Perception — ICLR 2025 Poster

Yang Wang

2025–present: Full Professor , University of Science and Technology of China (CN)

2017–2024: Associate Professor , University of Science and Technology of China (CN)

2002–2007: PhD student , University of Science and Technology of China (CN)

1998–2002: Undergrad student , University of Science and Technology of China (CN)

Papers (1)

Enhancing the Maximum Effective Window for Long-Term Time Series Forecasting — NeurIPS 2025 poster

Yangang Sun

2024–2026: Assistant Professor , Tsinghua University (CN)

2019–2024: PhD student , University of the Chinese Academy of Sciences (CN)

Papers (1)

RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing — NeurIPS 2025 poster

Yangchao Wu

2022–present: PhD student , University of California, Los Angeles (US)

2018–2022: Undergrad student , University of California, Los Angeles (US)

Papers (1)

STree: Speculative Tree Decoding for Hybrid State Space Models — NeurIPS 2025 poster

Yann Dubois

2024–present: Researcher , OpenAI (US)

2021–present: PhD student , Stanford University (US)

2020–2021: Intern , Vector Institute (CA)

2019–2020: AI Resident , Facebook (US)

2018–2019: MS student , University of Cambridge (GB)

2014–2017: Undergrad student , Swiss Federal Institute of Technology Lausanne (CH)

Papers (1)

Learning to (Learn at Test Time): RNNs with Expressive Hidden States — ICML 2025 spotlightposter

Yann LeCun

2013–present: Chief AI Scientist , Meta (US)

2003–present: Full Professor , New York University (US)

1988–2002: Researcher , AT&T (US)

1987–1988: Post Doc , University of Toronto (CA)

1983–1987: Graduate Student , Sorbonne Université - Faculté des Sciences (Paris VI) (FR)

1978–1983: Undergraduate , Ecole Supérieure d'Ingénieurs en Electronique et Electrotechnique (FR)

Papers (1)

Layer by Layer: Uncovering Hidden Representations in Language Models — ICML 2025 oral

Yannick Schroecker

2020–present: Research Scientist , DeepMind

2014–2020: PhD student , Georgia Institute of Technology

2011–2014: Undergrad student , TU Darmstadt

Papers (1)

Structured State Space Models for In-Context Reinforcement Learning — NeurIPS 2023 poster

Yantao Shen

2021–present: Applied Scientist , Amazon (US)

2020–2021: Researcher , Tencent ARC

2019–2020: Research Intern , Amazon

2015–2020: PhD student , The Chinese University of Hong Kong

2011–2015: Undergrad student , Northeastern University (China)

Papers (1)

B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory — NeurIPS 2024 poster

Yanwen Fang

2023–2026: Researcher , University of Hong Kong (HK)

2018–2023: PhD student , The University of Hong Kong (HK)

Papers (1)

From Layers to States: A State Space Model Perspective to Deep Neural Network Layer Dynamics — ICLR 2025 Poster

Yanzi Wang

2024–2027: MS student , Tsinghua University, Tsinghua University (CN)

2020–2024: Undergrad student , Beijing University of Posts and Telecommunications (CN)

Papers (1)

LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling — NeurIPS 2024 poster

Yao Lu

2025–present: Principal Researcher , Physical Intelligence (US)

2023–2025: Principal Researcher , NVIDIA (US)

2018–2023: Researcher , Google (US)

2012–2016: PhD student , University of California, San Diego (US)

Papers (1)

SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers — ICLR 2025 Oral

Yaodong Yu

2024–present: Researcher , OpenAI (US)

2019–2024: PhD student , Electrical Engineering & Computer Science Department, University of California Berkeley (US)

2017–2019: MS student , Department of Computer Science, University of Virginia (US)

2011–2015: Undergrad student , Department of Mathematics , Nanjing University (CN)

Papers (1)

Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More — ICML 2025 poster

Yaohua Zha

2024–2027: PhD student , Tsinghua University, Tsinghua University (CN)

2021–2024: MS student , Computer Science, Tsinghua University, Tsinghua University (CN)

2014–2018: Undergrad student , University of Electronic Science and Technology of China (CN)

Papers (1)

LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling — NeurIPS 2024 poster

Yash Sarrof

2025–present: PhD student , Universität des Saarlandes (DE)

2023–2025: MS student , Universität des Saarlandes (DE)

2020–2023: Researcher , Glib.ai (IN)

2020–2020: Intern , Samsung (IN)

2016–2020: Undergrad student , Manipal University (IN)

2018–2019: Intern , Novartis Institutes for BioMedical Research (IN)

Papers (1)

The Expressive Capacity of State Space Models: A Formal Language Perspective — NeurIPS 2024 poster

Yashaswi Karnati

2022–present: Researcher , NVIDIA (US)

Papers (1)

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning — NeurIPS 2025 poster

Yasuko Matsubara

2025–present: Full Professor , Osaka University (JP)

2019–2025: Associate Professor , Osaka University (JP)

Papers (1)

EvoBrain: Dynamic Multi-Channel EEG Graph Modeling for Time-Evolving Brain Networks — NeurIPS 2025 spotlight

Yasushi Sakurai

2019–present: Full Professor , Osaka University (JP)

Papers (1)

EvoBrain: Dynamic Multi-Channel EEG Graph Modeling for Time-Evolving Brain Networks — NeurIPS 2025 spotlight

Yawen Huang

2021–present: Researcher , Tencent (CN)

2015–2018: PhD student , University of Sheffield (GB)

Papers (1)

Samba: Severity-aware Recurrent Modeling for Cross-domain Medical Image Grading — NeurIPS 2024 poster

Yazid Janati

2025–present: Researcher , Institute of Foundation Models, MBZUAI (FR)

2023–2026: Postdoc , École Polytechnique (FR)

2020–2023: PhD student , Telecom SudParis (FR)

Papers (1)

State and parameter learning with PARIS particle Gibbs — ICML 2023 Poster

Yedi Zhang

2022–present: PhD student , University College London (GB)

Papers (1)

Training Dynamics of In-Context Learning in Linear Attention — ICML 2025 spotlightposter

Yee Whye Teh

2016–present: Researcher , Google DeepMind (GB)

2012–present: Full Professor , University of Oxford (GB)

2007–2012: Associate Professor , University College London

Papers (1)

Kalman Filter for Online Classification of Non-Stationary Data — ICLR 2024 poster

Yefeng Zheng

2024–present: Full Professor , Westlake University (CN)

2018–2024: Director , Tencent Jarvis Lab (CN)

2006–2017: Principal Key Expert , Siemens Corporate Research (US)

2001–2005: PhD student , University of Maryland, College Park (US)

Papers (1)

Samba: Severity-aware Recurrent Modeling for Cross-domain Medical Image Grading — NeurIPS 2024 poster

Yenho Chen

2021–2026: PhD student , Georgia Institute of Technology (US)

Papers (1)

Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics — NeurIPS 2024 poster

Yeonju Ro

2021–present: PhD student , University of Texas at Austin (US)

2025–2025: Research Intern , Microsoft (US)

2023–2023: Research Intern , Facebook

2022–2023: Research Intern , HP Labs

2018–2021: Researcher , Samsung Research

2015–2018: MS student , Korea Advanced Institute of Science & Technology

Papers (1)

On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention for Long-Context LLM Serving — ICML 2025 poster

Yeyun Gong

2017–2025: Researcher , Microsoft (CN)

2012–2017: PhD student , Fudan University

Papers (1)

Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection — NeurIPS 2025 poster

Yi Ding

2022–present: Assistant Professor , Georgia State University (US)

2015–2022: PhD student , University of California, Santa Barbara (US)

2007–2011: Undergrad student , University of Massachusetts at Amherst

Papers (1)

MamBEV: Enabling State Space Models to Learn Birds-Eye-View Representations — ICLR 2025 Poster

Yi Fan

2021–2025: PhD student , nanjing university (CN)

2018–2021: MS student , Nanjing University of Posts and Telecommunications (CN)

2014–2018: Undergrad student , Nanjing University of Posts and Telecommunications (CN)

Papers (1)

TF-MAS: Training-free Mamba2 Architecture Search — NeurIPS 2025 poster

Yi Sun

2021–2026: PhD student , University of Science and Technology of China (CN)

2017–2021: Undergrad student , University of Science and Technology of China

Papers (1)

Toward Dynamic Non-Line-of-Sight Imaging with Mamba Enforced Temporal Consistency — NeurIPS 2024 poster

Yi Wang

2022–present: PhD student , Zhejiang University (CN)

2018–2022: Undergrad student , Huazhong University of Science and Technology (CN)

Papers (1)

Vision Mamba Mender — NeurIPS 2024 poster

Yi Wang

2013–present: Full Professor , Fudan University (CN)

2000–2013: Associate Professor , Fudan University (CN)

Papers (1)

FAPEX: Fractional Amplitude-Phase Expressor for Robust Cross-Subject Seizure Prediction — NeurIPS 2025 spotlight

Yi Xu

2020–present: PhD student , Northeastern University (US)

2024–2024: Inten , GM Cruise LLC (US)

2022–2023: Intern , Honda Research Institute (US)

2017–2020: MS student , Xi'an Jiaotong University (CN)

2013–2017: Undergrad student , Xi'an Jiaotong University (CN)

Papers (1)

Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports — ICLR 2025 Poster

Yiang Luo

2022–2025: MS student , Harbin Institute of Technology (CN)

2018–2022: Undergrad student , Harbin Institute of Technology (CN)

Papers (1)

Exploring Adversarial Robustness of Deep State Space Models — NeurIPS 2024 poster

Yichao Fu

2024–2029: PhD student , University of California, San Diego (US)

2022–2024: PhD student , University of Hong Kong

2018–2022: Undergrad student , Zhejiang University

Papers (1)

When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models — ICML 2024 Poster

Yichen Liu

2023–present: MS student , Beijing Jiaotong University (CN)

2019–2023: Undergrad student , Beijing Jiaotong University (CN)

Papers (1)

TrajMamba: An Efficient and Semantic-rich Vehicle Trajectory Pre-training Model — NeurIPS 2025 spotlight

Yicheng Xiao

2023–2026: MS student , Tsinghua University, Tsinghua University (CN)

2019–2023: Undergrad student , Xi'an University of Electronic Science and Technology (CN)

Papers (1)

MambaTree: Tree Topology is All You Need in State Space Model — NeurIPS 2024 spotlight

Yichong Xu

2020–present: Senior Researcher , Microsoft

2015–2020: PhD student , School of Computer Science, Carnegie Mellon University

2011–2015: Undergrad student , Tsinghua University

Papers (1)

Sparse Modular Activation for Efficient Sequence Modeling — NeurIPS 2023 poster

Yichuan Cheng

2023–present: PhD student , City University of Hong Kong (HK)

2019–2023: Undergrad student , University of Electronic Science and Technology of China

Papers (1)

Log Neural Controlled Differential Equations: The Lie Brackets Make A Difference — ICML 2024 Poster

Yidi Liu

2023–present: MS student , University of Science and Technology of China (CN)

2019–2023: Undergrad student , South China University of Technology (CN)

Papers (1)

FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining — ICML 2025 poster

Yifei Xing

2022–2027: PhD student , Chinese Academy of Sciences (CN)

2022–2023: MS student , Brown University (US)

2022–2023: MS student , University of Illinois at Urbana-Champaign

2020–2022: PhD student , University of California Berkeley (US)

Papers (1)

EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment — ICLR 2025 Poster

Yifeng Li

2021–2025: MS student , Technische Universität München (DE)

2017–2021: Undergrad student , ShanghaiTech University

Papers (1)

DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Models — Accepted by TMLR

Yihao Feng

2024–present: Researcher , Apple AI/ML (US)

2022–2024: Researcher , Salesforce AI Research (US)

2018–2022: PhD student , University of Texas at Austin

Papers (1)

Longhorn: State Space Models are Amortized Online Learners — ICLR 2025 Poster

Yikui Zhang

2022–2026: PhD student , Forschungszentrum Juelich GmbH (DE)

2022–2026: PhD student , Rheinische Friedrich-Wilhelms Universität Bonn (DE)

Papers (1)

RiverMamba: A State Space Model for Global River Discharge and Flood Forecasting — NeurIPS 2025 poster

Yinan Lin

2024–present: Postdoc , Chongqing Normal University (CN)

2020–2024: Postdoc , National University of Singapore (CN)

2014–2020: PhD student , Renmin University of China (CN)

2010–2014: Undergrad student , SUN YAT-SEN UNIVERSITY (CN)

Papers (1)

Balancing Interference and Correlation in Spatial Experimental Designs: A Causal Graph Cut Approach — ICML 2025 poster

Ying Shan

2021–present: Director , Tencent AI Lab Center of Visual Computing (CN)

2019–present: Director , Tencent PCG ARC Lab (CN)

Papers (1)

MambaTree: Tree Topology is All You Need in State Space Model — NeurIPS 2024 spotlight

Ying Tai

2023–2026: Associate Professor , Nanjing University (CN)

2017–2023: Principal Researcher , Tencent Youtu Lab (CN)

Papers (1)

MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space — NeurIPS 2024 poster

Ying Yang

2010–present: Full Professor , Tsinghua University, Tsinghua University

Papers (1)

AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees — NeurIPS 2025 poster

Ying Zhang

2024–present: Postdoc , RIKEN (JP)

2023–2024: Postdoc , Tokyo Institute of Technology, Tokyo Institute of Technology (JP)

2019–2023: PhD student , Tokyo Institute of Technology, Tokyo Institute of Technology (JP)

2017–2019: MS student , Tokyo Institute of Technology, Tokyo Institute of Technology (JP)

2013–2017: Undergrad student , Chongqing University (CN)

Papers (1)

DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs — NeurIPS 2025 poster

Yingfa Chen

2024–2027: PhD student , Tsinghua University (CN)

2022–2024: MS student , Tsinghua University (CN)

2018–2022: Undergrad student , Tsinghua University (CN)

Papers (1)

Stuffed Mamba: Oversized States Lead to the Inability to Forget — COLM 2025

Yingheng Wang

2022–present: PhD student , Cornell University (US)

Papers (1)

LC-PLM: Long-context Protein Language Modeling Using Bidirectional Mamba with Shared Projection Layers — Accepted by TMLR

Yinghuan Shi

2023–present: Full Professor , Nanjing University (CN)

2017–2023: Associate Professor , Nanjing University (CN)

2013–2017: Assistant Professor , Nanjing University (CN)

Papers (1)

START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation — NeurIPS 2024 poster

Yingshan Chang

2020–2026: PhD student , Carnegie Mellon University (US)

2016–2020: Undergrad student , The Hong Kong University of Science and Technology

Papers (1)

Language Models Need Inductive Biases to Count Inductively — ICLR 2025 Poster

Yingying Wang

2022–present: PhD student , Xiamen University (CN)

2016–2017: MS student , Nanyang Technological University (SG)

2012–2016: Undergrad student , Shandong University (CN)

Papers (1)

FRN: Fractal-Based Recursive Spectral Reconstruction Network — NeurIPS 2025 poster

Yiqiao Wang

2023–present: Intern , Luxi Technology

Papers (1)

Gated Slot Attention for Efficient Linear-Time Sequence Modeling — NeurIPS 2024 poster

Yiran Qin

2021–2026: PhD student , The Chinese University of Hong Kong(Shenzhen) (CN)

2017–2021: Undergrad student , Shandong University

Papers (1)

High-Dynamic Radar Sequence Prediction for Weather Nowcasting Using Spatiotemporal Coherent Gaussian Representation — ICLR 2025 Oral

Yiting Lu

2021–present: PhD student , University of Science and Technology of China (CN)

2017–2021: Undergrad student , Beijing Institute of Technology

Papers (1)

QMamba: On First Exploration of Vision Mamba for Image Quality Assessment — ICML 2025 poster

Yixiao Ge

2021–2027: Researcher , Tencent (CN)

2018–2021: PhD student , The Chinese University of Hong Kong (HK)

Papers (1)

MambaTree: Tree Topology is All You Need in State Space Model — NeurIPS 2024 spotlight

Yixin Wang

2022–present: Assistant Professor , University of Michigan - Ann Arbor (US)

2020–2021: Postdoc , University of California Berkeley (US)

2014–2020: PhD student , Columbia University (US)

Papers (1)

Identifying Neural Dynamics Using Interventional State Space Models — ICML 2025 poster

Yixing Xu

2022–2030: Principal Researcher , Advanced Micro Devices (CN)

Papers (1)

QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion — NeurIPS 2024 poster

Yoav Shoham

2016–2024: Emeritus , Computer Science Department, Stanford University

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Yonatan Belinkov

2020–present: Assistant Professor , Technion, Technion (IL)

2018–2020: Postdoc , Harvard University (US)

2012–2018: PhD student , Massachusetts Institute of Technology (US)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Yonatan Bisk

2020–present: Assistant Professor , Carnegie Mellon University (US)

2022–2024: Visiting Professor , Meta (US)

2019–2020: Postdoc , Microsoft (US)

2017–2019: Postdoc , Department of Computer Science, University of Washington (US)

2015–2017: Postdoc , University of Southern California (US)

2009–2015: PhD student , University of Illinois, Urbana Champaign (US)

2005–2009: Undergrad student , University of Texas, Austin (US)

Papers (1)

Language Models Need Inductive Biases to Count Inductively — ICLR 2025 Poster

Yonatan Dukler

2022–present: Researcher , AWS AI Labs

2017–2021: PhD student , University of California, Los Angeles

2014–2017: MS student , University of California, Los Angeles

2014–2017: Undergrad student , University of California, Los Angeles

Papers (1)

B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory — NeurIPS 2024 poster

Yonatan Slutzky

2023–present: PhD student , Tel Aviv University (IL)

Papers (1)

The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels — NeurIPS 2025 spotlight

Yong Man Ro

2025–present: Full Professor , Korea Advanced Institute of Science & Technology (KR)

2005–present: Full Professor , Korea Advanced Institute of Science and Technology (KR)

1997–2005: Associate Professor , Korea Advanced Institute of Science and Technology (KR)

Papers (1)

Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models — NeurIPS 2024 poster

Yong Xu

2011–2032: Full Professor , Harbin Institute of Technology (CN)

Papers (1)

MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging — NeurIPS 2024 poster

Yong Zhang

2018–present: Full Professor , Huzhou Normal University (CN)

Papers (1)

A Multimodal BiMamba Network with Test-Time Adaptation for Emotion Recognition Based on Physiological Signals — NeurIPS 2025 poster

Yonghong Tian

2013–present: Full Professor , Peking University (CN)

Papers (1)

Spike-driven Transformer — NeurIPS 2023 poster

Yongkang Liu

2023–present: Principal Researcher , Toyota (US)

Papers (1)

MamBEV: Enabling State Space Models to Learn Birds-Eye-View Representations — ICLR 2025 Poster

Yongping He

2021–2025: PhD student , Beijing Institute of Technology

Papers (1)

Probabilistic Time Series Modeling with Decomposable Denoising Diffusion Model — ICML 2024 Poster

Yongqi Pan

2021–2026: PhD student , National University of Defense Technology (CN)

Papers (1)

Improving Bilinear RNN with Closed-loop Control — NeurIPS 2025 spotlight

Yongtao Wu

2022–present: PhD student , Swiss Federal Institute of Technology Lausanne (CH)

Papers (1)

Linear Attention for Efficient Bidirectional Sequence Modeling — NeurIPS 2025 poster

Yongyong Chen

2024–present: Associate Professor , Harbin Institute of Technology (Shenzhen) (CN)

2020–2023: Assistant Professor , Harbin Institute of Technology (CN)

2017–2020: PhD student , University of Macau

Papers (1)

MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging — NeurIPS 2024 poster

Yota Maeda

2022–present: Researcher , Keio University (JP)

2021–present: Researcher , Sony Group Corporation (JP)

2021–2023: PhD student , Kyoto University (JP)

2019–2021: MS student , Kyoto University (JP)

Papers (1)

MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba — ICLR 2025 Poster

Yotam Alexander

2021–2025: PhD student , Tel Aviv University, Tel Aviv University (IL)

Papers (1)

The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels — NeurIPS 2025 spotlight

Youfang Lin

2002–present: Full Professor , Beijing Jiaotong University (CN)

1999–2002: PhD student , Beijing Jiaotong University (CN)

Papers (1)

TrajMamba: An Efficient and Semantic-rich Vehicle Trajectory Pre-training Model — NeurIPS 2025 spotlight

Young Jin Kim

2021–present: Principal Researcher , Microsoft (US)

2018–2021: Researcher , Microsoft

2016–2018: Researcher , Intel

2013–2017: PhD student , Georgia Institute of Technology

Papers (1)

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation — NeurIPS 2025 poster

Youngsoo Jang

2025–present: Assistant Professor , Ulsan National Institute of Science and Technology (KR)

2022–2025: Researcher , LG AI Research (KR)

2018–2022: PhD student , Korea Advanced Institute of Science and Technology (KR)

2016–2018: MS student , Korea Advanced Institute of Science and Technology (KR)

2011–2016: Undergrad student , Korea Advanced Institute of Science and Technology (KR)

Papers (1)

Information-Theoretic State Space Model for Multi-View Reinforcement Learning — ICML 2023 OralPoster

Youngwan Lee

2021–present: PhD student , Korea Advanced Institute of Science & Technology (KR)

2017–present: Researcher , Electronics and Telecommunication Research Institute (KR)

Papers (1)

Training Free Exponential Context Extension via Cascading KV Cache — ICLR 2025 Poster

Youze Zheng

2022–2026: Undergrad student , University of California, San Diego (US)

Papers (1)

Single-Pass Document Scanning for Question Answering — COLM 2025

Yu Bo

—–present: PhD student , Zhejiang University (CN)

Papers (1)

Revisiting Convolution Architecture in the Realm of DNA Foundation Models — ICLR 2025 Poster

Yu Luo

2025–present: Researcher , Huawei Technologies Ltd. (CN)

2019–2025: PhD student , Tsinghua University (CN)

2016–2019: MS student , Beijing Institute of Technology

2012–2016: Undergrad student , Tsinghua University

Papers (1)

Slimming the Fat-Tail: Morphing-Flow for Adaptive Time Series Modeling — ICML 2025 poster

Yu Sun

2023–2026: Postdoc , Stanford University (US)

2017–2023: PhD student , University of California Berkeley (US)

2015–2017: Undergrad student , Cornell University (US)

2013–2015: Undergrad student , Washington University, St. Louis (US)

Papers (1)

Learning to (Learn at Test Time): RNNs with Expressive Hidden States — ICML 2025 spotlightposter

Yu Wang

2019–present: Full Professor , Tsinghua University, Tsinghua University (CN)

2012–2018: Associate Professor , Tsinghua University, Tsinghua University (CN)

Papers (1)

Evaluating Quantized Large Language Models — ICML 2024 Poster

Yu Zhou

2022–present: PhD student , Leibniz-Institut für Analytische Wissenschaften – ISAS – e.V. (DE)

2020–2022: MS student , KTH Royal Institute of Technology (SE)

2017–2020: Undergrad student , Southeast University (CN)

Papers (1)

Orochi: Versatile Biomedical Image Processor — NeurIPS 2025 spotlight

Yu Zhu

2009–2035: Full Professor , East China University of Science and Technology (CN)

1995–1999: PhD student , Nanjing University of Science and Technology (CN)

1991–1995: Undergrad student , Nanjing University of Science and Technology

Papers (1)

CSV-Occ: Fusing Multi-frame Alignment for Occupancy Prediction with Temporal Cross State Space Model and Central Voting Mechanism — ICML 2025 poster

Yu-Bin Yang

2007–present: Full Professor , Nanjing University, China (CN)

2005–2006: Researcher , University of New South Wales, Australia (AU)

2003–2005: Postdoc , The Chinese University of Hong Kong (CN)

2000–2003: PhD student , Nanjing University, China (CN)

1997–2000: MS student , Nanjing University, China (CN)

1993–1997: Undergrad student , Wuhan University, China (CN)

Papers (1)

TF-MAS: Training-free Mamba2 Architecture Search — NeurIPS 2025 poster

Yuan He

2025–present: Applied Scientist , Amazon (US)

2024–2025: Postdoc , University of Oxford (GB)

2020–2024: PhD student , University of Oxford (GB)

2016–2020: Undergrad student , University of Edinburgh (GB)

Papers (1)

DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Models — Accepted by TMLR

Yuan Zhang

2024–2028: PhD student , Peking University (CN)

2020–2023: MS student , Peking University (CN)

2016–2020: Undergrad student , Hohai University (CN)

Papers (1)

Orochi: Versatile Biomedical Image Processor — NeurIPS 2025 spotlight

Yuan Zhao

2021–present: Researcher , National Institute of Mental Health

2016–2021: Postdoc , State University of New York, Stony Brook

2012–2016: PhD student , State University of New York, Stony Brook

2010–2012: MS student , George Washington University

Papers (1)

eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modeling — NeurIPS 2024 poster

Yuanlong Zhang

2025–present: Assistant Professor , Tsinghua University, Tsinghua University (CN)

2022–2024: Postdoc , Tsinghua University, Tsinghua University (CN)

Papers (1)

Slimming the Fat-Tail: Morphing-Flow for Adaptive Time Series Modeling — ICML 2025 poster

Yuanqing Xia

2010–present: Full Professor , Beijing Institute of Technology (CN)

2006–2010: Associate Professor , Beijing Institute of Technology (CN)

2002–2005: Assistant Professor , Beijing Institute of Technology (CN)

1998–2001: PhD student , Beijing University of Aeronautics and Astronautics (CN)

1995–1998: MS student , Anhui University (CN)

1989–1991: Undergrad student , Chuzhou University (CN)

Papers (1)

Probabilistic Time Series Modeling with Decomposable Denoising Diffusion Model — ICML 2024 Poster

Yuanxi Que

2022–2026: Undergrad student , Shenzhen University (CN)

Papers (1)

Hierarchical Information Aggregation for Incomplete Multimodal Alzheimer's Disease Diagnosis — NeurIPS 2025 poster

Yubin Kim

2023–2025: Undergrad student , Georgia Institute of Technology (US)

Papers (1)

ZeroS: Zero‑Sum Linear Attention for Efficient Transformers — NeurIPS 2025 spotlight

Yuchen Duan

2023–present: PhD student , The Chinese University of Hong Kong (HK)

2021–2023: Intern , Shanghai AI Laboratory (CN)

2018–2022: Undergrad student , Electronic Engineering, Tsinghua University, Tsinghua University (CN)

Papers (1)

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures — ICLR 2025 Spotlight

Yuchen Wang

2024–2029: PhD student , College of William and Mary (US)

Papers (1)

A Generalizable Physics-Enhanced State Space Model for Long-Term Dynamics Forecasting in Complex Environments — ICML 2025 poster

Yucheng Li

2025–present: Researcher , Alibaba Group (CN)

2021–2025: PhD student , University of Surrey (GB)

2018–2021: MS student , East China Normal University (CN)

Papers (1)

SCBench: A KV Cache-Centric Analysis of Long-Context Methods — ICLR 2025 Poster

Yucheng Shi

2020–2024: PhD student , University of Dublin, Trinity College (IE)

Papers (1)

Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient — ICLR 2025 Poster

Yucheng XU

2021–2025: PhD student , University of Edinburgh, University of Edinburgh (GB)

2016–2020: Undergrad student , Nankai University

Papers (1)

FACTS: A Factored State-Space Framework for World Modelling — ICLR 2025 Poster

Yuchuan Tian

2022–present: PhD student , Peking University (CN)

2018–2022: Undergrad student , Shanghai Jiao Tong University (CN)

Papers (1)

DiJiang: Efficient Large Language Models through Compact Kernelization — ICML 2024 Oral

Yue Huang

2022–present: Full Professor , Xiamen University (CN)

2014–2022: Associate Professor , Xiamen University (CN)

2010–2014: Assistant Professor , Xiamen University (CN)

2005–2010: PhD student , Tsinghua University (CN)

Papers (1)

FRN: Fractal-Based Recursive Spectral Reconstruction Network — NeurIPS 2025 poster

Yue Li

2021–2026: PhD student , University of Science and Technology of China (CN)

Papers (1)

Toward Dynamic Non-Line-of-Sight Imaging with Mamba Enforced Temporal Consistency — NeurIPS 2024 poster

Yue Liu

2021–2026: PhD student , University of the Chinese Academy of Sciences (CN)

2017–2021: Undergrad student , University of the Chinese Academy of Sciences (CN)

Papers (1)

VMamba: Visual State Space Model — NeurIPS 2024 spotlight

Yue Yu

2023–present: Full Professor , Lehigh University (US)

2019–2023: Associate Professor , Lehigh University (US)

2014–2019: Assistant Professor , Lehigh University (US)

2014–2014: Postdoc , Harvard University (US)

2008–2014: PhD student , Brown University (US)

Papers (1)

Neural Interpretable PDEs: Harmonizing Fourier Insights with Attention for Scalable and Interpretable Physics Discovery — ICML 2025 poster

Yue Zhang

2024–2025: Researcher , ByteDance Inc. (CN)

2021–2024: MS student , Suzhou University (CN)

Papers (1)

Gated Slot Attention for Efficient Linear-Time Sequence Modeling — NeurIPS 2024 poster

Yue-Jiao Gong

2019–2024: Full Professor , South China University of Technology (CN)

2017–2019: Associate Professor , South China University of Technology (CN)

2015–2016: Postdoc , University of Macau (CN)

2010–2014: PhD student , Sun Yat-sen University (CN)

Papers (1)

Meta-Black-Box-Optimization through Offline Q-function Learning — ICML 2025 poster

Yuehao Wang

2024–2029: PhD student , University of Texas at Austin (US)

2021–2024: MS student , The Chinese University of Hong Kong (HK)

2017–2021: Undergrad student , ShanghaiTech University (CN)

Papers (1)

Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing — ICLR 2025 Poster

Yuehong HU

2023–2025: MS student , Hong Kong University of Science and Technology (GuangZhou)

Papers (1)

Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective — NeurIPS 2024 poster

Yuexiang Li

2023–2025: Full Professor , Guangxi Medical University (CN)

2018–2023: Researcher , Tencent (CN)

2016–2018: Postdoc , Shenzhen University (CN)

2012–2016: PhD student , University of Nottingham (GB)

Papers (1)

Samba: Severity-aware Recurrent Modeling for Cross-domain Medical Image Grading — NeurIPS 2024 poster

Yueyi Zhang

2025–present: Researcher , MiroMind (SG)

2024–2025: Staff Engineer , Hesai Technology (CN)

2018–2024: Associate Researcher , University of Science and Technology of China (CN)

Papers (1)

Toward Dynamic Non-Line-of-Sight Imaging with Mamba Enforced Temporal Consistency — NeurIPS 2024 poster

Yufei Cui

2022–present: Postdoc , McGill University (CA)

2021–2022: Postdoc , City University of Hong Kong (HK)

2017–2021: PhD student , City University of Hong Kong (HK)

Papers (1)

Mamba Modulation: On the Length Generalization of Mamba Models — NeurIPS 2025 poster

Yufeng Zhan

2023–present: Associate Professor , Beijing Institute of Technology (CN)

2018–2020: Postdoc , Hong Kong Polytechnic University (HK)

2014–2018: PhD student , Beijing Institute of Technology (CN)

Papers (1)

Probabilistic Time Series Modeling with Decomposable Denoising Diffusion Model — ICML 2024 Poster

Yuguo Yu

2011–present: Full Professor , Fudan University (CN)

2001–2004: Postdoc , Carnegie Mellon University (US)

1998–2001: PhD student , Nanjing University (CN)

Papers (1)

FAPEX: Fractional Amplitude-Phase Expressor for Robust Cross-Subject Seizure Prediction — NeurIPS 2025 spotlight

Yuhang Song

2022–2026: PhD student , University of Liverpool (GB)

2022–2026: PhD student , National Tsinghua University (TW)

Papers (1)

Toward Linearly Regularizing the Geometric Bottleneck of Linear Generalized Attention — Accepted by TMLR

Yuhao Zhou

2022–2027: PhD student , Sichuan University (CN)

2018–2022: Undergrad student , Sichuan University

Papers (1)

Pruning-Robust Mamba with Asymmetric Multi-Scale Scanning Paths — NeurIPS 2025 poster

Yuheng Shi

2025–2028: PhD student , University of Sydney (AU)

2024–2025: Researcher , City University of Hong Kong (HK)

2021–2024: MS student , Tianjin University (CN)

Papers (1)

Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model — NeurIPS 2024 poster

Yuhu Bai

2022–present: MS student , Zhejiang University (CN)

Papers (1)

MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection — NeurIPS 2024 poster

Yuhui Ding

2022–present: PhD student , Department of Computer Science, ETHZ - ETH Zurich

2019–2021: MS student , Hong Kong University of Science and Technology

2015–2019: Undergrad student , Tsinghua University

Papers (1)

Recurrent Distance Filtering for Graph Representation Learning — ICML 2024 Poster

Yujia Chen

2023–2026: MS student , University of Science and Technology of China (CN)

Papers (1)

BeyondMix: Leveraging Structural Priors and Long-Range Dependencies for Domain-Invariant LiDAR Segmentation — NeurIPS 2025 poster

Yukang Lin

2023–2026: MS student , Tsinghua University, Tsinghua University (CN)

2024–2025: Intern , Ant Group (CN)

2024–2024: Intern , Alibaba Group (CN)

2019–2023: Undergrad student , Jilin University (CN)

2022–2022: Intern , Nanyang Technological University (SG)

Papers (1)

MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models — NeurIPS 2024 poster

Yule Wang

2022–2027: PhD student , Georgia Institute of Technology (US)

2019–2022: MS student , Shanghai Jiaotong University

2015–2019: Undergrad student , Shanghai Jiaotong University

Papers (1)

Learning Time-Varying Multi-Region Brain Communications via Scalable Markovian Gaussian Processes — ICML 2025 oral

Yulin Wang

2019–present: PhD student , Tsinghua University, Tsinghua University (CN)

2015–2019: Undergrad student , Beihang University, Tsinghua University (CN)

Papers (1)

RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing — NeurIPS 2025 poster

Yulun Zhang

2024–present: Associate Professor , Shanghai Jiaotong University (CN)

2021–2024: Postdoc , Swiss Federal Institute of Technology (CH)

2017–2021: PhD student , Northeastern University (US)

2014–2017: MS student , Tsinghua University (CN)

2009–2013: Undergrad student , Xidian University (CN)

Papers (1)

ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correction — NeurIPS 2024 poster

Yun Fu

2015–2025: Full Professor , Northeastern University (US)

2010–2015: Associate Professor , Northeastern University (US)

Papers (1)

Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports — ICLR 2025 Poster

Yunfan Liu

2023–2025: Postdoc , University of the Chinese Academy of Sciences (CN)

2019–2023: PhD student , University of the Chinese Academy of Sciences (CN)

2015–2017: MS student , University of Michigan - Ann Arbor (US)

2011–2015: Undergrad student , Tsinghua University, Tsinghua University (CN)

Papers (1)

VMamba: Visual State Space Model — NeurIPS 2024 spotlight

Yunfan Liu

2023–2028: PhD student , Westlake University (CN)

2023–2028: PhD student , Zhejiang University (CN)

2019–2023: Undergrad student , Tongji University (CN)

Papers (1)

Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences — ICML 2024 Poster

Yunhua Zhou

2024–present: Postdoc , Shanghai Artificial Intelligence Laboratory (CN)

2020–2024: PhD student , Fudan University (CN)

Papers (1)

Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures — ICLR 2025 Poster

Yunjie Tian

2024–2026: Postdoc , State University of New York at Buffalo (US)

2019–2024: PhD student , University of the Chinese Academy of Sciences (CN)

2015–2019: Undergrad student , Jilin University

Papers (1)

VMamba: Visual State Space Model — NeurIPS 2024 spotlight

Yunjun Gao

2010–present: Full Professor , Zhejiang University (CN)

Papers (1)

Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach — NeurIPS 2025 poster

Yunpu Ma

2025–present: Lecturer , Ludwig-Maximilians-Universität München (DE)

2020–present: Researcher , Siemens Corporate Research (DE)

2020–2023: Principal Researcher , Institut für Informatik (DE)

Papers (1)

DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Models — Accepted by TMLR

Yunqing Liu

2024–present: Researcher , Fujitsu Research and Development Center (CN)

2023–2024: Postdoc , Hong Kong University of Science and Technology (HK)

2018–2023: PhD student , Shanghai Jiaotong University (CN)

Papers (1)

Mamba Only Glances Once (MOGO): A Lightweight Framework for Efficient Video Action Detection — NeurIPS 2025 poster

Yunxiao Shi

2021–present: Researcher , Qualcomm AI Research (US)

2018–2021: MS student , New York University (US)

Papers (1)

PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer — ICLR 2025 Poster

Yuqi Pan

2024–present: PhD student , Institute of automation, Chinese academy of science, Chinese Academy of Sciences (CN)

2020–2024: Undergrad student , nanjing university (CN)

Papers (1)

MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map — NeurIPS 2024 oral

Yuqing Yang

2019–present: Researcher , Research, Microsoft (CN)

2012–2017: Researcher , Broadcom (CN)

2006–2011: PhD student , Fudan University (CN)

Papers (1)

SCBench: A KV Cache-Centric Analysis of Long-Context Methods — ICLR 2025 Poster

Yurong Qian

2016–2025: Associate Professor , Xinjiang University (CN)

2007–2011: PhD student , nanjing university (CN)

2002–2005: MS student , Xinjiang University (CN)

1998–2002: Undergrad student , Xinjiang University (CN)

Papers (1)

ZigzagPointMamba: Spatial-Semantic Mamba for Point Cloud Understanding — NeurIPS 2025 poster

Yury Nahshan

—–present: Researcher , Huawei Technologies Ltd.

Papers (1)

Linear Log-Normal Attention with Unbiased Concentration — ICLR 2024 poster

Yuta Tarumi

2025–present: Postdoc , RIKEN (JP)

2023–2025: Postdoc , Preferred Networks, Inc. (JP)

2018–2023: PhD student , The University of Tokyo, Tokyo Institute of Technology (JP)

2014–2018: Undergrad student , The University of Tokyo, Tokyo Institute of Technology (JP)

Papers (1)

Deep Bayesian Filter for Bayes-Faithful Data Assimilation — ICML 2025 poster

Yutao Cui

2024–present: Researcher , Tencent Hunyuan (CN)

2019–2024: PhD student , Nanjing University (CN)

Papers (1)

VFIMamba: Video Frame Interpolation with State Space Models — NeurIPS 2024 poster

Yuting Hu

2022–present: PhD student , State University of New York at Buffalo (US)

2016–2019: MS student , North China Electric Power University (CN)

2012–2016: Undergrad student , North China Electric Power University (CN)

Papers (1)

Sub-Sequential Physics-Informed Learning with State Space Model — ICML 2025 poster

Yuting Huang

2024–2027: MS student , Zhejiang University (CN)

2020–2024: Undergrad student , Zhejiang University (CN)

Papers (1)

Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach — NeurIPS 2025 poster

Yuval Globerson

2016–present: MS student , Hebrew University of Jerusalem (IL)

2008–2010: Undergrad student , Tel Aviv University (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Yuval Peleg Levy

2022–present: Algorithm Developer , AI21 (IL)

2018–2022: Algorithm Developer , SparkBeyond (IL)

Papers (1)

Jamba: Hybrid Transformer-Mamba Language Models — ICLR 2025 Poster

Yuval Ran-Milo

2024–2027: PhD student , Tel Aviv University (IL)

Papers (1)

Provable Benefits of Complex Parameterizations for Structured State Space Models — NeurIPS 2024 poster

Yuxian Gu

2021–2026: PhD student , Tsinghua University, Tsinghua University (CN)

2017–2021: Undergrad student , Tsinghua University, Tsinghua University (CN)

Papers (1)

Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search — NeurIPS 2025 poster

Yuxin Chang

2021–2026: PhD student , University of California, Irvine (US)

2019–2020: MS student , University of Cambridge (GB)

2015–2019: Undergrad student , University of Edinburgh (GB)

Papers (1)

Deep Continuous-Time State-Space Models for Marked Event Sequences — NeurIPS 2025 spotlight

Yuxing Tang

2022–present: Researcher , Alibaba Group (US)

2020–2022: Researcher , PAII (US)

2017–2020: Postdoc , NIH (US)

2011–2016: PhD student , Ecole Centrale de Lyon (FR)

Papers (1)

Dual-Res Tandem Mamba-3D: Bilateral Breast Lesion Detection and Classification on Non-contrast Chest CT — NeurIPS 2025 poster

Yuxuan Hu

2022–2027: PhD student , Renmin University of China (CN)

2018–2022: Undergrad student , Beijing Jiaotong University (CN)

Papers (1)

MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation — NeurIPS 2025 poster

Yuxuan Yue

2023–2026: MS student , Harbin Institute of Technology (CN)

2019–2023: Undergrad student , Ocean University of China

Papers (1)

MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods — ICLR 2025 Poster

Yuyang Zhao

2025–present: Researcher , NVIDIA (US)

2021–2025: PhD student , National University of Singapore (SG)

Papers (1)

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer — ICML 2025 poster

Yuyin Zhou

2022–present: Assistant Professor , University of California, Santa Cruz (US)

2020–2021: Postdoc , Stanford University

2016–2020: PhD student , Johns Hopkins University

Papers (1)

Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More — ICML 2025 poster

Yuzhong Zhao

2023–present: PhD student , University of the Chinese Academy of Sciences (CN)

2020–2023: MS student , University of the Chinese Academy of Sciences (CN)

Papers (1)

VMamba: Visual State Space Model — NeurIPS 2024 spotlight

Zedong Wang

2025–present: PhD student , The Hong Kong University of Science and Technology (HK)

2022–2024: Intern , Westlake University (CN)

2019–2023: Undergrad student , Huazhong University of Science and Technology (CN)

2021–2021: Intern , Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences (CN)

Papers (1)

Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences — ICML 2024 Poster

Zehao Liu

2023–2025: MS student , Georgia Institute of Technology (CN)

Papers (1)

ZeCO: Zero-Communication Overhead Sequence Parallelism for Linear Attention — NeurIPS 2025 poster

Zejun MA

2024–present: Principal Researcher , TikTok (SG)

2017–2024: Principal Researcher , ByteDance Inc. (CN)

2007–2012: Principal Researcher , iscas (CN)

Papers (1)

ZeCO: Zero-Communication Overhead Sequence Parallelism for Linear Attention — NeurIPS 2025 poster

Zekun Li

2024–present: PhD student , Institute of automation, Chinese academy of science (CN)

2021–2024: MS student , Xidian University (CN)

2017–2021: Undergrad student , Inner Mongolia University (CN)

Papers (1)

MVA: Linear Attention with High-order Query-Keys Integration and Multi-level Vocabulary Decomposition — ICML 2025 poster

Zekun Wang

2025–present: Researcher , Alibaba Group (CN)

2019–2025: PhD student , Harbin Institute of Technology (CN)

Papers (1)

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free — NeurIPS 2025 oral

Zeyu Huang

2024–2027: PhD student , University of Edinburgh, University of Edinburgh (GB)

Papers (1)

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free — NeurIPS 2025 oral

Zeyu Zhou

2022–2025: MS student , Beijing Jiaotong University (CN)

2018–2022: Undergrad student , Beijing Jiaotong University (CN)

Papers (1)

TrajMamba: An Efficient and Semantic-rich Vehicle Trajectory Pre-training Model — NeurIPS 2025 spotlight

Zeyuan Allen-Zhu

2022–present: Researcher , Meta FAIR Labs (US)

2022–present: Researcher , Allen-Zhu Research (US)

Papers (1)

Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers — NeurIPS 2025 poster

Zeyuan Ma

2022–2026: PhD student , South China University of Technology (CN)

2018–2022: Undergrad student , South China University of Technology (CN)

Papers (1)

Meta-Black-Box-Optimization through Offline Q-function Learning — ICML 2025 poster

Zhan Ma

2015–present: Full Professor , Nanjing University (CN)

2013–2015: Principal Researcher , Huawei Technologies Ltd. (US)

2011–2013: Researcher , Samsung (US)

2006–2011: PhD student , New York University (US)

Papers (1)

Efficient LiDAR Reflectance Compression via Scanning Serialization — ICML 2025 poster

Zhaocheng Zhu

2025–present: Researcher , NVIDIA (US)

2018–2024: PhD student , Université de Montréal (CA)

2014–2018: Undergrad student , Peking University (CN)

Papers (1)

Overcoming Long Context Limitations of State Space Models via Context Dependent Sparse Attention — NeurIPS 2025 poster

Zhaokun Zhou

2021–2025: PhD student , Peking University (CN)

2018–2021: MS student , Chongqing University (CN)

2014–2018: Undergrad student , Chongqing University (CN)

Papers (1)

Spike-driven Transformer — NeurIPS 2023 poster

Zhaoxiang Zhang

2015–present: Full Professor , Institute of automation, Chinese academy of science, Chinese Academy of Sciences (CN)

Papers (1)

Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection — NeurIPS 2024 spotlight

Zhaoyang Li

2023–2027: PhD student , Nanyang Technological University (SG)

Papers (1)

MamKO: Mamba-based Koopman operator for modeling and predictive control — ICLR 2025 Spotlight

Zhe Chen

2022–2026: PhD student , Nanjing University (CN)

2020–2022: MS student , Nanjing University (CN)

Papers (1)

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures — ICLR 2025 Spotlight

Zhe Liu

2025–2028: Postdoc , University of Hong Kong (CN)

2020–2025: PhD student , Huazhong University of Science and Technology (CN)

2017–2020: MS student , Huazhong University of Science and Technology (CN)

Papers (1)

LION: Linear Group RNN for 3D Object Detection in Point Clouds — NeurIPS 2024 poster

Zhejian Yang

2022–2027: PhD student , Jilin University (CN)

Papers (1)

Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling — NeurIPS 2024 poster

Zhen Lei

2018–present: Full Professor , Institute of Automation, Chinese Academy of Sciences (CN)

2013–2018: Associate Professor , Institute of Automation, Chinese Academy of Sciences (CN)

2011–2013: Assistant Professor , Institute of Automation, Chinese Academy of Sciences (CN)

Papers (1)

Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection — NeurIPS 2024 spotlight

Zhen-Liang Ni

2022–2026: Researcher , Huawei Technologies Ltd. (CN)

2017–2022: PhD student , Institute of automation, Chinese academy of science, Chinese Academy of Sciences (CN)

Papers (1)

TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-state — ICML 2025 poster

Zheng Chen

2022–present: Assistant Professor , ISIR, Osaka University, Japan (JP)

2022–2022: Postdoc , Osaka University, Japan

2019–2022: PhD student , Nara Institute of Science and Technology, Japan

2017–2019: MS student , Nara Institute of Science and Technology, Japan

Papers (1)

EvoBrain: Dynamic Multi-Channel EEG Graph Modeling for Time-Evolving Brain Networks — NeurIPS 2025 spotlight

Zheng Qingfang

2024–present: Researcher , Peng Cheng Lab (CN)

2017–2023: Researcher , ZTE Corp.

2013–2017: Researcher , Lenovo Group Limited (CN)

2008–2013: Researcher , Nufront Corp. (CN)

2002–2008: PhD student , Institute of Computing Technology, Chinese Academy of Sciences (CN)

Papers (1)

EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment — ICLR 2025 Poster

Zheng Wang

2025–present: PhD student , University of Illinois at Urbana-Champaign (US)

2023–2025: MS student , Georgia Institute of Technology (US)

Papers (1)

When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models — ICML 2024 Poster

Zheng Zhang

2024–present: Full Professor , Harbin Institute of Technology (CN)

2021–2023: Associate Professor , Harbin Institute of Technology (CN)

2019–2020: Assistant Professor , Harbin Institute of Technology (CN)

Papers (1)

PolaFormer: Polarity-aware Linear Attention for Vision Transformers — ICLR 2025 Poster

Zheng Zhu

2023–present: Principal Researcher , GigaAI (CN)

2021–2023: Researcher , PhiGent Robotics (CN)

2019–2021: Postdoc , Tsinghua University (CN)

2014–2019: PhD student , Institute of Automation, Chinese Academy of Sciences (CN)

Papers (1)

Pruning-Robust Mamba with Asymmetric Multi-Scale Scanning Paths — NeurIPS 2025 poster

Zheng-Jun Zha

2015–present: Full Professor , University of Science and Technology of China (CN)

Papers (1)

FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining — ICML 2025 poster

Zhengfu He

2024–present: PhD student , Shanghai Innovation Institute (CN)

2023–present: PhD student , Fudan University (CN)

2019–2023: Undergrad student , Fudan University

Papers (1)

Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures — ICLR 2025 Poster

Zhenghao Pan

2023–present: MS student , Harbin Institute of Technology (Shenzhen) (CN)

Papers (1)

MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging — NeurIPS 2024 poster

Zhengqi Pei

2025–2028: PhD student , Chinese Academy of Sciences (CN)

2022–2025: MS student , University of the Chinese Academy of Sciences (CN)

2014–2019: Undergrad student , University of Toronto (CA)

Papers (1)

Modeling Language Tokens as Functionals of Semantic Fields — ICML 2024 Poster

Zhengqiang ZHANG

2022–present: PhD student , The Hong Kong Polytechnic University, Hong Kong Polytechnic University (HK)

2017–2020: MS student , Huazhong University of Science and Technology (CN)

2013–2017: Undergrad student , Huazhong University of Science and Technology (CN)

Papers (1)

Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion — ICLR 2025 Poster

Zhengyang Zhou

2023–2025: Researcher , University of Science and Technology of China (CN)

2018–2023: PhD student , University of Science and Technology of China (CN)

2014–2018: Undergrad student , Jiangnan University (CN)

Papers (1)

Enhancing the Maximum Effective Window for Long-Term Time Series Forecasting — NeurIPS 2025 poster

Zhengyu Tian

2022–2026: Undergrad student , Beijing Jiaotong University (CN)

Papers (1)

A Multimodal BiMamba Network with Test-Time Adaptation for Emotion Recognition Based on Physiological Signals — NeurIPS 2025 poster

Zhenhua Lin

2019–present: Assistant Professor , National University of Singapore (SG)

2013–2017: PhD student , University of Toronto

2008–2013: MS student , Simon Fraser University

Papers (1)

Balancing Interference and Correlation in Spatial Experimental Designs: A Causal Graph Cut Approach — ICML 2025 poster

Zhenli Zhou

2024–2025: Researcher , ByteDance Inc. (CN)

2021–2024: MS student , Peking University (CN)

Papers (1)

MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected Layers — NeurIPS 2024 poster

Zhenqiao Song

2023–2027: PhD student , Carnegie Mellon University (US)

2022–2023: PhD student , University of California, Santa Barbara

2020–2022: NLP Researcher , ByteDance AI Lab

2017–2020: MS student , Fudan University

Papers (1)

JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation Model — NeurIPS 2025 poster

Zhenxiong Tan

2024–present: Researcher , National University of Singapore (SG)

2022–2024: MS student , National University of Singapore (SG)

Papers (1)

CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up — NeurIPS 2025 poster

Zhenye Gan

2018–present: Researcher , Tencent Youtu Lab (CN)

2015–2018: MS student , Shanghai Jiaotong University (CN)

2011–2015: Undergrad student , Shanghai Jiaotong University (CN)

Papers (1)

MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection — NeurIPS 2024 poster

Zhenyu Cui

2021–present: PhD student , Peking University (CN)

2018–2021: MS student , University of the Chinese Academy of Sciences (CN)

2014–2018: Undergrad student , China University of Petroleum (CN)

Papers (1)

State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding — NeurIPS 2025 poster

Zhenyu Wang

2023–present: MS student , Peking University (CN)

2019–2023: Undergrad student , Southeast University (CN)

Papers (1)

RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation — NeurIPS 2024 poster

Zhenyu Zhang

2022–present: PhD student , University of Texas at Austin

2019–2022: MS student , University of Science and Technology of China

2015–2019: Undergrad student , University of Science and Technology of China

Papers (1)

On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention for Long-Context LLM Serving — ICML 2025 poster

Zheyang Xiong

2025–present: Intern , Research, Microsoft (US)

2023–present: PhD student , University of Wisconsin - Madison (US)

2019–2023: Undergrad student , Rice University

Papers (1)

Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks — ICML 2024 Poster

Zhi Wang

2018–present: Associate Professor , SIGS, Tsinghua University (CN)

2014–2018: Assistant Professor , SIGS, Tsinghua University (CN)

2008–2014: PhD student , Tsinghua University, Tsinghua University

Papers (1)

LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling — NeurIPS 2024 poster

Zhi-Qin John Xu

2019–present: Associate Professor , Shanghai Jiao Tong University (CN)

2016–2019: Postdoc , New York University Abu Dhabi

2012–2016: PhD student , Shanghai Jiao Tong University

Papers (1)

Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data — NeurIPS 2025 spotlight

Zhibo Chen

2014–present: Full Professor , University of Science and Technology of China (CN)

Papers (1)

QMamba: On First Exploration of Vision Mamba for Image Quality Assessment — ICML 2025 poster

Zhifan Ye

2023–present: PhD student , Georgia Institute of Technology (US)

2022–2023: PhD student , Rice University (US)

2018–2022: Undergrad student , University of Science and Technology of China (CN)

Papers (1)

LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement — ICLR 2025 Poster

Zhiguang Cao

2023–present: Assistant Professor , Singapore Management University (SG)

2022–2023: Scientist , Institute for Infocomm Research, A*STAR

2021–2022: Scientist , Singapore Institute of Manufacturing Technology, A*STAR

2018–2021: Research Assistant Professor , National University of Singapore

2013–2017: PhD student , Nanyang Technological University

Papers (1)

Meta-Black-Box-Optimization through Offline Q-function Learning — ICML 2025 poster

Zhihang Yuan

2025–present: Researcher , ByteDance Inc. (CN)

2024–2025: Researcher , Infinigence AI (CN)

2022–2024: Researcher , Houmo AI (CN)

2017–2022: PhD student , Peking University (CN)

2013–2017: Undergrad student , Peking University (CN)

Papers (1)

MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods — ICLR 2025 Poster

Zhihao He

2024–present: PhD student , Shanghai Jiaotong University (CN)

Papers (1)

Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions — ICLR 2025 Poster

Zhihao Ouyang

2024–present: Researcher , Meta (US)

2020–2024: Researcher , Bytedance (US)

2018–2021: MS student , Tsinghua University, Tsinghua University (CN)

2019–2020: MS student , Carnegie Mellon University (US)

2014–2018: Undergrad student , Beijing University of Aeronautics and Astronautics (CN)

Papers (1)

LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling — NeurIPS 2024 poster

Zhihao Zeng

2021–2026: PhD student , Zhejiang University (CN)

2017–2021: Undergrad student , South China University of Technology (CN)

Papers (1)

Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach — NeurIPS 2025 poster

Zhihao Zhan

2024–2028: PhD student , Mila - Quebec Artificial Intelligence Institute (CA)

2024–2028: PhD student , Université de Montréal (CA)

2019–2023: Undergrad student , Peking University (CN)

Papers (1)

Overcoming Long Context Limitations of State Space Models via Context Dependent Sparse Attention — NeurIPS 2025 poster

Zhikang Zou

2020–present: Researcher , Baidu

2017–2020: MS student , Huazhong University of Science and Technology

Papers (1)

PointMamba: A Simple State Space Model for Point Cloud Analysis — NeurIPS 2024 poster

Zhiming Tan

2007–present: Researcher , FUJITSU RESEARCH & DEVELOPMENT CENTER CO., LTD. (CN)

2003–2007: PhD student , Shanghai Jiaotong University

Papers (1)

Mamba Only Glances Once (MOGO): A Lightweight Framework for Efficient Video Action Detection — NeurIPS 2025 poster

Zhiqi Gao

2023–present: PhD student , Department of Computer Science, University of Wisconsin - Madison (US)

2023–2023: Intern , Roblox Corporation (US)

2019–2023: Undergrad student , Department of Computer Science, University of Wisconsin - Madison (US)

Papers (1)

Pretrained Hybrids with MAD Skills — COLM 2025

Zhiqiang Shen

2022–present: Assistant Professor , Mohamed bin Zayed University of Artificial Intelligence (AE)

2019–2021: Postdoc , Carnegie Mellon University (US)

Papers (1)

Bi-Mamba: Towards Accurate 1-Bit State Space Model — Accepted by TMLR

Zhiqiang Yan

2025–present: Postdoc , National University of Singapore (SG)

2020–2024: PhD student , Nanjing University of Science and Technology (CN)

2014–2018: Undergrad student , Nanjing University of Science and Technology (CN)

Papers (1)

MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space — NeurIPS 2024 poster

Zhiwei Wang

2021–2026: PhD student , Shanghai Jiaotong University (CN)

2017–2021: Undergrad student , Shanghai Jiao Tong University (CN)

Papers (1)

Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data — NeurIPS 2025 spotlight

Zhiwei Xiong

2016–present: Professor , USTC (CN)

2011–2016: Researcher , Research, Microsoft (US)

Papers (1)

Toward Dynamic Non-Line-of-Sight Imaging with Mamba Enforced Temporal Consistency — NeurIPS 2024 poster

Zhixin Cheng

2022–present: PhD student , University of Science and Technology of China (CN)

2020–2022: MS student , University of Science and Technology of China (CN)

2016–2020: Undergrad student , Huazhong University of Science and Technology (CN)

Papers (1)

BeyondMix: Leveraging Structural Priors and Long-Range Dependencies for Domain-Invariant LiDAR Segmentation — NeurIPS 2025 poster

Zhixuan Chen

2024–present: Researcher , houmo (CN)

2014–2017: MS student , Nanjing University of Aeronautics and Astronautics (CN)

Papers (1)

MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods — ICLR 2025 Poster

Zhixuan Lin

2023–present: PhD student , Université de Montréal (CA)

2021–2023: MS student , Université de Montréal (CA)

2016–2020: Undergrad student , Zhejiang University (CN)

Papers (1)

Forgetting Transformer: Softmax Attention with a Forget Gate — ICLR 2025 Poster

Zhiyu Yao

2024–present: Researcher , Tsinghua University (CN)

2019–2024: PhD student , Tsinghua University, Tsinghua University (CN)

2015–2019: Undergrad student , Tsinghua University, Tsinghua University

Papers (1)

Mobile Attention: Mobile-Friendly Linear-Attention for Vision Transformers — ICML 2024 Poster

Zhiyuan Liang

2024–2025: Intern , National University of Singapore (SG)

2021–2025: Undergrad student , University of Science and Technology of China (CN)

Papers (1)

Pruning-Robust Mamba with Asymmetric Multi-Scale Scanning Paths — NeurIPS 2025 poster

Zhiyuan Liu

2018–present: Associate Professor , Tsinghua University (CN)

2016–2017: Assistant Professor , Tsinghua University (CN)

Papers (1)

Stuffed Mamba: Oversized States Lead to the Inability to Forget — COLM 2025

Zhiyuan Ma

2025–present: Associate Professor , Huazhong University of Science and Technology (CN)

2023–2025: Postdoc , Tsinghua University, Tsinghua University (CN)

2019–2023: PhD student , Huazhong University of Science and Technology (CN)

Papers (1)

Exploring Adversarial Robustness of Deep State Space Models — NeurIPS 2024 poster

Zhongchen Zhao

2024–2028: PhD student , Xi'an Jiaotong University (CN)

Papers (1)

Polyline Path Masked Attention for Vision Transformer — NeurIPS 2025 spotlight

Zhongdao Wang

2022–present: Researcher , Huawei Technologies Ltd. (CN)

2017–2022: PhD student , Tsinghua University, Tsinghua University (CN)

2013–2017: Undergrad student , Tsinghua University, Tsinghua University

Papers (1)

QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model — NeurIPS 2024 poster

Zhongnan Cai

2023–present: MS student , Xiamen University (CN)

2019–2023: Undergrad student , Hebei University (CN)

Papers (1)

FRN: Fractal-Based Recursive Spectral Reconstruction Network — NeurIPS 2025 poster

Zhou Jiang

2022–2026: Undergrad student , South China University of Technology (CN)

Papers (1)

Meta-Black-Box-Optimization through Offline Q-function Learning — ICML 2025 poster

Zhuo Chen

2021–present: PhD student , Massachusetts Institute of Technology

2017–2021: Undergrad student , University of Illinois, Urbana-Champaign

Papers (1)

L$^2$M: Mutual Information Scaling Law for Long-Context Language Modeling — NeurIPS 2025 poster

Zhuotao Jin

2023–2028: PhD student , Massachusetts Institute of Technology (US)

Papers (1)

L$^2$M: Mutual Information Scaling Law for Long-Context Language Modeling — NeurIPS 2025 poster

Zhuoyuan Li

2023–2026: MS student , University of Science and Technology of China (CN)

2019–2023: Undergrad student , University of Electronic Science and Technology of China (CN)

Papers (1)

BeyondMix: Leveraging Structural Priors and Long-Range Dependencies for Domain-Invariant LiDAR Segmentation — NeurIPS 2025 poster

Zi Gong

2020–2023: MS student , Harbin Institute of Technology (Shenzhen)

Papers (1)

Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions — ICLR 2025 Poster

Zibin Zheng

2018–present: Full Professor , Sun Yat-sen University (CN)

Papers (1)

State Space Models on Temporal Graphs: A First-Principles Study — NeurIPS 2024 poster

Zichen Liu

2022–2025: MS student , Peking University (CN)

2018–2022: Undergrad student , Xi'an Jiaotong University (CN)

Papers (1)

State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding — NeurIPS 2025 poster

Zichen Wang

2025–present: Researcher , Oracle (US)

2021–2025: Researcher , Amazon (US)

2019–2021: Researcher , Sema4

2017–2019: Assistant Professor , Icahn School of Medicine at Mount Sinai

2012–2016: PhD student , Icahn School of Medicine at Mount Sinai

Papers (1)

LC-PLM: Long-context Protein Language Modeling Using Bidirectional Mamba with Shared Projection Layers — Accepted by TMLR

Zicheng Liu

2020–2025: PhD student , Westlake University (CN)

2020–2025: PhD student , Zhejiang University (CN)

2016–2020: Undergrad student , University of Liverpool (GB)

Papers (1)

Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences — ICML 2024 Poster

Zichong Meng

2025–present: PhD student , Northeastern University (US)

2023–2025: MS student , Northeastern University (US)

2019–2021: Undergrad student , University of California, San Diego (US)

Papers (1)

Exploring Token Pruning in Vision State Space Models — NeurIPS 2024 poster

Zifeng Ding

2024–2026: Postdoc , University of Cambridge (GB)

2021–2024: PhD student , LMU Munich (DE)

2018–2021: MS student , Technical University of Munich (DE)

Papers (1)

DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Models — Accepted by TMLR

Zihan Qiu

2024–present: Researcher , Alibaba Group (CN)

2020–2024: Undergrad student , Tsinghua University, Tsinghua University (CN)

Papers (1)

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free — NeurIPS 2025 oral

Zihan Su

2024–2027: MS student , Tsinghua University (CN)

2020–2024: Undergrad student , Shenzhen University (CN)

Papers (1)

Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking — NeurIPS 2025 poster

Zihao Jing

2024–present: MS student , University of Western Ontario (CA)

2019–2024: Undergrad student , Beijing University of Aeronautics and Astronautics (CN)

Papers (1)

Structure-Aware Fusion with Progressive Injection for Multimodal Molecular Representation Learning — NeurIPS 2025 poster

Zihao Yu

2023–present: MS student , University of Science and Technology of China (CN)

Papers (1)

QMamba: On First Exploration of Vision Mamba for Image Quality Assessment — ICML 2025 poster

Zikai Song

2023–2026: Postdoc , Huazhong University of Science and Technology (CN)

2019–2023: PhD student , Huazhong University of Science and Technology (CN)

Papers (1)

Coupled Mamba: Enhanced Multimodal Fusion with Coupled State Space Model — NeurIPS 2024 poster

Zike Wu

2024–present: PhD student , University of British Columbia (CA)

2022–2024: MS student , Nanyang Technological University (SG)

Papers (1)

MVGamba: Unify 3D Content Generation as State Space Sequence Modeling — NeurIPS 2024 poster

Ziming Zhu

2022–2026: PhD student , East China University of Science and Technology (CN)

Papers (1)

CSV-Occ: Fusing Multi-frame Alignment for Occupancy Prediction with Temporal Cross State Space Model and Central Voting Mechanism — ICML 2025 poster

Ziqiao Peng

2022–2027: PhD student , Renmin University of China (CN)

Papers (1)

MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation — NeurIPS 2025 poster

Ziquan Fang

2023–present: Assistant Professor , Zhejiang University (CN)

2018–2023: PhD student , Zhejiang University (CN)

Papers (1)

Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach — NeurIPS 2025 poster

Zixiang Chen

2025–2026: Researcher , SalesForce.com (US)

2019–2025: PhD student , University of California, Los Angeles (US)

2015–2019: Undergrad student , Tsinghua University, Tsinghua University (CN)

Papers (1)

How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression? — ICLR 2024 spotlight

Zixu Jiang

2023–2026: MS student , nanjing university (CN)

Papers (1)

MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods — ICLR 2025 Poster

Ziye Wang

2024–present: Researcher , The Chinese University of Hong Kong (Shenzhen)) (CN)

2021–2024: MS student , Harbin Institute of Technology (CN)

2017–2021: Undergrad student , Harbin Institute of Technology (CN)

Papers (1)

High-Dynamic Radar Sequence Prediction for Weather Nowcasting Using Spatiotemporal Coherent Gaussian Representation — ICLR 2025 Oral

Ziyi Wang

2024–present: Intern , Tsinghua University, Tsinghua University (CN)

2021–2023: MS student , Duke University (US)

2016–2020: Undergrad student , University of Oregon (US)

Papers (1)

Demystify Mamba in Vision: A Linear Attention Perspective — NeurIPS 2024 poster

Ziyu Jia

2023–present: Assistant Professor , Institute of automation, Chinese academy of science (CN)

Papers (1)

A Multimodal BiMamba Network with Test-Time Adaptation for Emotion Recognition Based on Physiological Signals — NeurIPS 2025 poster

Ziyue Li

2025–present: Assistant Professor , Technical University of Munich (DE)

2022–2025: Assistant Professor , University of Cologne (DE)

2022–2023: Principal Researcher , EWI gGmbH (DE)

2021–2022: Researcher , SenseTime Research (HK)

2017–2021: PhD student , The Hong Kong University of Science and Technology

Papers (1)

Hybrid Mamba for Few-Shot Segmentation — NeurIPS 2024 poster

Zizheng Huang

2024–2028: PhD student , nanjing university (CN)

2021–2024: MS student , Nanjing University (CN)

Papers (1)

Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training — ICML 2025 poster

Zohar Rimon

2023–present: PhD student , Technion - Israel Institute of Technology, Technion - Israel Institute of Technology

2021–2023: MS student , Technion - Israel Institute of Technology, Technion - Israel Institute of Technology

2016–2020: Undergrad student , Technion - Israel Institute of Technology, Technion - Israel Institute of Technology

Papers (1)

MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning — ICLR 2024 poster

Zongsheng Li

2023–2027: PhD student , The Chinese University of Hong Kong, ShenZhen (CN)

2018–2019: MS student , Nanyang Technological University (SG)

2014–2018: Undergrad student , Dalian University of Technology (CN)

Papers (1)

Multi-dataset Joint Pre-training of Emotional EEG Enables Generalizable Affective Computing — NeurIPS 2025 poster

Zongyue Qin

2020–present: PhD student , University of California, Los Angeles

2016–2020: Undergrad student , Peking University

Papers (1)

STree: Speculative Tree Decoding for Hybrid State Space Models — NeurIPS 2025 poster

Zukang Xu

2024–present: Researcher , HOUMO AI (CN)

2014–2018: MS student , Nanjing University of Science and Technology (CN)

Papers (1)

MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods — ICLR 2025 Poster

Zunlei Feng

2022–present: Associate Professor , Zhejiang University (CN)

2019–2022: Assistant Professor , Zhejiang University (CN)

2014–2019: PhD student , Zhejiang University (CN)

2010–2014: Undergrad student , Soochow University (CN)

Papers (1)

Vision Mamba Mender — NeurIPS 2024 poster

Zunnan Xu

—–present: MS student , Tsinghua University (CN)

Papers (1)

MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models — NeurIPS 2024 poster

Çağatay Yıldız

2022–present: Postdoc , Eberhard-Karls-Universität Tübingen (DE)

2017–2022: PhD student , Aalto University (FI)

2014–2017: MS student , Bogazici University (TR)

Papers (1)

Identifying latent state transitions in non-linear dynamical systems — ICLR 2025 Poster

Çağlar Hızlı

2020–2025: PhD student , Aalto University

2017–2020: MS student , Boğaziçi University

Papers (1)

Identifying latent state transitions in non-linear dynamical systems — ICLR 2025 Poster