Yuexiang Feel free to call me Simon. Zhai

Bio

I am a final year phd candidate at Berkeley EECS, advised by Prof. Yi Ma and Prof. Sergey Levine. I am also affliated Because of my advisors, I have nothing to do with it (except for having a seat at the beautiful Berkeley Way West office). with BAIR. I obtained an MS degree from Columbia University with Prof. John Wright and a BS degree in Math & Applied Math It is only one major, I do not know why Zhejiang University (ZJU) created a major named "Math & Applied Math". Perhaps ZJU is trying suggested that some math majors are not applicable? from Zhejiang University Not from the Chu Kochen Honors College, because I did pretty poorly during undergrad..

Contacts

Research

Publications

Please refer to my Google Scholar profile for my full publication Google scholar is a much better organizer than me list. Some papers selected by topics are listed below. I shamelessly borrowed the style from here.

Large Multimodal Models

Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

Yuexiang Zhai, Hao Bai*, Zipeng Lin*, Jiayi Pan*, Shengbang Tong*, Yifei Zhou*, Alane Suhr, Saining Xie, Yann LeCun, Yi Ma, Sergey Levine

Advances in Neural Information Processing Systems (NIPS), 2024.

paper (arXiv) project code MarketTechPost

Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs

Shengbang Tong, Zhuang Liu, Yuexiang Zhai, Yi Ma, Yann LeCun, Saining Xie

Conference on Computer Vision and Pattern Recognition (CVPR), 2024 (Oral).

paper project code

Investigating the Catastrophic Forgetting in Multimodal Large Language Model Fine-Tuning

Yuexiang Zhai, Shengbang Tong, Xiao Li, Mu Cai, Qing Qu, Yong Jae Lee, Yi Ma

Conference on Parsimony and Learning (CPAL), 2024.

paper project

Reinforcement Learning

Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning

Mitsuhiko Nakamoto*, Yuexiang Zhai*, Anikait Singh, Max Sobol Mark, Yi Ma, Chelsea Finn, Aviral Kumar, Sergey Levine

Advances in Neural Information Processing Systems (NIPS), 2023.

paper project code

Understanding the Complexity Gains of Single-Task RL with a Curriculum

Qiyang Li*, Yuexiang Zhai*, Yi Ma, Sergey Levine

International Conference on Machine Learning (ICML), 2023.

paper

Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learning

Yuexiang Zhai, Christina Baek, Zhengyuan Zhou, Jiantao Jiao, Yi Ma

Journal of Artificial Intelligence Research (JAIR), 2022.

paper

Machine Learning

Complete Dictionary Learning via L4-Norm Maximization over the Orthogonal Group

Yuexiang Zhai, Zitong Yang, Zhenyu Liao, John Wright, Yi Ma

Journal of Machine Learning Research, 2020 (JMLR).

Signal Processing with Adaptive Sparse Structured Representations 2019 (SPARS), Best student paper finalist.

paper

Understanding L4-based Dictionary Learning: Interpretation, Stability, and Robustness

Yuexiang Zhai, Hermish Mehta, Zhengyuan Zhou, Yi Ma

International Conference on Learning Representations (ICLR), 2020.

paper code

Geometric Analysis of Nonconvex Optimization Landscapes for Overcomplete Learning

Qing Qu, Yuexiang Zhai, Xiao Li, Yuqian Zhang, Zhihui Zhu

International Conference on Learning Representations (ICLR), 2020 (Oral).

paper