Zhu, Guangcheng

1 publications

ICLR 2026 TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning Shenzhi Yang, Guangcheng Zhu, Haobo Wang, Xing Zheng, Yingfan Ma, Zhongqi Chen, Bowen Song, Weiqiang Wang, Junbo Zhao, Gang Chen