Publications

2026

Learning When Visual Context Matters for Mouse Behavior Analysis
Weihan Li, Jingyang Ke, Qinheng Pu, Yule Wang, Chengrui Li, and Anqi Wu
The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS), 2026
[paper] [arXiv] [code] [slides] [video] [poster]

Disentangling time-varying neural latent dynamics and circuit-level connectivity with subspace-attention gating
Chengrui Li, Kai Lu, Yen-Shuo Su, Jingyang Ke, Chris Rodgers, Robert C. Liu, and Anqi Wu
Society for Neuroscience (SfN), 2026
[abstract] [poster]

A Hitchhiker’s Guide to Poisson Gradient Estimation
Michael Ibrahim^*, Hanqi Zhao^*, Eli Zachary Sennesh, Zhi Li, Chengrui Li^†, and Hadi Vafaii^†
(^*co-first authorship, ^†co-senior authorship)
The Forty-third International Conference on Machine Learning (ICML), 2026
[paper] [arXiv] [code] [slides] [video] [poster]

A Factorized Low-Rank RNN Framework for Uncovering Independent Neural Latent Dynamics and Connectivity
Chengrui Li, Yunmiao Wang, Yule Wang, Weihan Li, Dieter Jaeger, and Anqi Wu
The Forty-third International Conference on Machine Learning (ICML), 2026 [Spotlight: 2.2%]
[paper] [arXiv] [code] [slides] [video] [poster]

Uncovering Semantic Selectivity of Latent Groups in Higher Visual Cortex with Mutual Information-Guided Diffusion
Yule Wang, Joseph Yu, Chengrui Li, Weihan Li, and Anqi Wu
The Fourteenth International Conference on Learning Representations (ICLR), 2026
[paper] [arXiv] [code] [slides] [video] [poster]

2025

A Revisit of Total Correlation in Disentangled Variational Auto-Encoder with Partial Disentanglement
Chengrui Li, Yunmiao Wang, Yule Wang, Weihan Li, Dieter Jaeger, and Anqi Wu
arXiv:2502.02279, 2025
[paper] [arXiv] [code] [slides] [video] [poster]

Learning Time-Varying Multi-Region Brain Communications via Scalable Markovian Gaussian Processes
Weihan Li, Yule Wang, Chengrui Li, and Anqi Wu
The Forty-second International Conference on Machine Learning (ICML), 2025 [Oral: 1.0%]
[paper] [arXiv] [code] [slides] [video] [poster]

Feature Reconstruction Guided Fusion Network for Hyperspectral and LiDAR Classification
Zhi Li, Ke Zheng, Lianru Gao, Nannan Zi, and Chengrui Li,
IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2024
[paper]

2024

Exploring Behavior-Relevant and Disentangled Neural Dynamics with Generative Diffusion Models
Yule Wang, Chengrui Li, Weihan Li, and Anqi Wu
The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024
[paper] [arXiv] [code] [slides] [video] [poster]

Cross Semantic Heterogeneous Modeling Network for Hyperspectral Image Classification
Zhi Li, Ke Zheng, Jiaxin Li, Chengrui Li, and Lianru Gao
IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2024
[paper]

A Differentiable Partially Observable Generalized Linear Model with Forward-Backward Message Passing
Chengrui Li, Weihan Li, Yule Wang, and Anqi Wu
The Forty-first International Conference on Machine Learning (ICML), 2024
[paper] [arXiv] [code] [slides] [video] [poster] [文章]

Multi-Region Markovian Gaussian Process: An Efficient Method to Discover Directional Communications Across Multiple Brain Regions
Weihan Li, Chengrui Li, Yule Wang, and Anqi Wu
The Forty-first International Conference on Machine Learning (ICML), 2024
[paper] [arXiv] [code] [slides] [video] [poster]

Inverse Kernel Decomposition
Chengrui Li and Anqi Wu
Transactions on Machine Learning Research (TMLR), 2024
[paper] [arXiv] [code] [slides] [文章]

Similarity of Memory Representations Modulate Saccade Curvatures
Golnaz Forouzandehfar, Chengrui Li, Aaron T. Buss, and A. Caglar Tas
Journal of Vision, 2024
[poster] [abstract]

Forward \(\chi^2\) Divergence Based Variational Importance Sampling
Chengrui Li, Yule Wang, Weihan Li, and Anqi Wu
The Twelfth International Conference on Learning Representations (ICLR), 2024 [spotlight 5%]
[paper] [arXiv] [code] [slides] [video] [poster] [文章]

One-hot Generalized Linear Model for Switching Brain State Discovery
Chengrui Li, Soon Ho Kim, Chris Rodgers, Hannah Choi, and Anqi Wu
The Twelfth International Conference on Learning Representations (ICLR), 2024
[paper] [arXiv] [code] [slides] [video] [poster] [文章]

2023

Extraction and Recovery of Spatio-Temporal Structure in Latent Dynamics Alignment with Diffusion Model
Yule Wang, Zijing Wu, Chengrui Li, and Anqi Wu
The Thirty-seventh Annual Conference on Neural Information Processing Systems (NeurIPS), 2023 [Spotlight: 3%]
[paper] [arXiv] [code] [slides] [video] [poster]

2020

The application of fractional order image enhancement in computational neuroscience
Chengrui Li, Wei Deng, and Yifei Pu
Sichuan University Undergraduate Thesis, 2020 [Outstanding Undergraduate Thesis]
[文章]

2019

Continuous-time systems for solving 0-1 integer linear programming feasibility problems
Chengrui Li and Bruce J. MacLennan
arXiv:1905.04612, 2019
[arXiv]