ML Anthology

Yang, Saiyong

2 publications

ICLR 2026 LaSeR: Reinforcement Learning with Last-Token Self-Rewarding Wenkai Yang, Weijie Liu, Ruobing Xie, Yiju Guo, Lulu Wu, Saiyong Yang, Yankai Lin
ICLR 2026 Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners Xin Xu, Clive Bai, Kai Yang, Tianhao Chen, Yang Wang, Saiyong Yang, Can Yang