Ying Wen

Associate Professor, Shanghai Jiao Tong University

3 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 2

Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM

ReMA: Learning to Meta-Think for LLMs with Multi-agent Reinforcement Learning

#400 · Ziyu Wan, Yunxiang LI, Xiaoyu Wen, Yan Song, Hanjing Wang, Linyi Yang, Mark Schmidt, Jun Wang, Weinan Zhang, Shuyue Hu, Ying Wen

Training a new reasoning paradigm of LLMs explicitly contains meta-thinking in a multi-agent and multi-turn setting with RL

ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning

#109 · Shulin Huang, Linyi Yang, Yan Song, Shuang Chen, Leyang Cui, Ziyu Wan, Qingcheng Zeng, Ying Wen, Kun Shao, Weinan Zhang, Jun Wang, Yue Zhang

Poster Session 6

1 paper

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

STAR: Efficient Preference-based Reinforcement Learning via Dual Regularization

#413 · Fengshuo Bai, Rui Zhao, Hongming Zhang, Sijia Cui, Shao Zhang, bo xu, Lei Han, Ying Wen, Yaodong Yang

An efficient PbRL method that mitigates overfitting and overestimation via dual regularization, enhancing feedback efficiency in both online and offline settings