作者位次 #4/14ICML 2026Poster· Deep Learning / Large Language Models
Spurious Rewards: Rethinking Training Signals in RLVR
Rulin Shao · Stella Li · Rui Xin · Scott Geng · Yiping Wang · Sewoong Oh · Simon Du · Nathan Lambert · Sewon Min · Ranjay Krishna · Yulia Tsvetkov · Hannaneh Hajishirzi · Pang Wei Koh · Luke Zettlemoyer
强化学习与后训练OpenReview