作者位次 #6/9ICLR 2026Poster· Reinforcement Learning / Everything Else
Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs
Haoming Meng · Kexin Huang · Shaohang Wei · Chiyu Ma · Shuo Yang · xue wang · Guoyin Wang · Bolin Ding · Jingren Zhou
强化学习与后训练OpenReview