logo
today local_bar

Shenzhi Wang

PhD student, Department of Automation, Tsinghua University

2 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

1 paper
Thursday, December 4, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
#5505 · Shenzhi Wang, Le Yu, Chang Gao, Chujie Zheng, Shixuan Liu, Rui Lu, Kai Dang, Xiong-Hui Chen, Jianxin Yang, Zhenru Zhang, Yuqiong Liu, An Yang, Andrew Zhao, Yang Yue, Shiji Song, Bowen Yu, Gao Huang, Junyang Lin

Poster Session 6

1 paper
Friday, December 5, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
#1908 Spotlight · Andrew Zhao, Yiran Wu, Yang Yue, Tong Wu, Quentin Xu, Yang Yue, Matthieu Lin, Shenzhi Wang, Qingyun Wu, Zilong Zheng, Gao Huang

self-play reasoning RL with no data can achieve SOTA against RL models trained with human data