Back to papers
April 2, 2026cs.LGcs.AI
Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
Gengsheng Li, Tianyu Yang, Junfeng Fang, Mingyang Song, Mao Zheng, Haiyun Guo, Dan Zhang, Jinqiao Wang, Tat-Seng Chua
HF Upvotes
23
Categories
cs.LG, cs.AI