Chujie Zheng6 papers on this site (2021–2025)Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM ReasoningShenzhi Wang, Le Yu, Chang Gao, et al.2025Group Sequence Policy OptimizationChujie Zheng, Shixuan Liu, Mingze Li, et al.2025ProcessBench: Identifying Process Errors in Mathematical ReasoningChujie Zheng, Zhenru Zhang, Beichen Zhang, et al.2025Qwen3 Technical ReportAn Yang, Anfeng Li, Baosong Yang, et al.2025The Lessons of Developing Process Reward Models in Mathematical ReasoningZhenru Zhang, Chujie Zheng, Yangzhen Wu, et al.2025Towards Emotional Support Dialog SystemsSiyang Liu, Chujie Zheng, Orianna Demasi, et al.2021