Yuexiang Zhai

Joined

September 2019

Names

Yuexiang Zhai (Preferred)

Emails

****@berkeley.edu (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Google Scholar

DBLP

Career & Education History

PhD student

University of California Berkeley (berkeley.edu)

2020 – 2025

Advisors, Relations & Conflicts

PhD Advisor

Sergey Levine

2021 – Present

PhD Advisor

Yi Ma

2020 – Present

Expertise

Multimodal Language Models

2023 – Present

Reinforcement Learning

2020 – Present

Machine Learning

2018 – Present

Publications

LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models
Marwa Abdulhai, Isadora White, Charlie Victor Snell, Charles Sun, Joey Hong, Yuexiang Zhai, Kelvin Xu, Sergey Levine
- ICML 2025 poster
- Readers: Everyone
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Tianzhe Chu, Yuexiang Zhai, Jihan Yang, Shengbang Tong, Saining Xie, Dale Schuurmans, Quoc V Le, Sergey Levine, Yi Ma
- ICML 2025 poster
- Readers: Everyone
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Tianzhe Chu, Yuexiang Zhai, Jihan Yang, Shengbang Tong, Saining Xie, Sergey Levine, Yi Ma
- CPAL 2025 (Recent Spotlight Track)
- Readers: Everyone
LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models
Marwa Abdulhai, Isadora White, Charlie Victor Snell, Charles Sun, Joey Hong, Yuexiang Zhai, Kelvin Xu, Sergey Levine
- Submitted to ICLR 2025
- Readers: Everyone
Is Offline Decision Making Possible with Only Few Samples? Reliable Decisions in Data-Starved Bandits via Trust Region Enhancement
Ruiqi Zhang, Yuexiang Zhai, Andrea Zanette
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
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
- NeurIPS 2024 poster
- Readers: Everyone
Investigating the Catastrophic Forgetting in Multimodal Large Language Models
Yuexiang Zhai, Shengbang Tong, Xiao Li, Mu Cai, Qing Qu, Yong Jae Lee, Yi Ma
- Instruction Workshop @ NeurIPS 2023
- Readers: Everyone
RLIF: Interactive Imitation Learning as Reinforcement Learning
Jianlan Luo, Perry Dong, Yuexiang Zhai, Yi Ma, Sergey Levine
- ICLR 2024 poster
- Readers: Everyone
LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models
Marwa Abdulhai, Isadora White, Charlie Victor Snell, Charles Sun, Joey Hong, Yuexiang Zhai, Kelvin Xu, Sergey Levine
- Submitted to ICLR 2024
- Readers: Everyone
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
- CPAL 2024 (Proceedings Track) Oral
- Readers: Everyone

View all 20 publications

Co-Authors

View all 52 co-authors