一作ICML 2026Poster· Deep Learning / Foundation Models
Rubric Curriculum RL: Exploiting the Generation-Verification Gap in Non-Verifiable Domains
Tejas Krishnan · Sumeet Motwani · Charles London · Suhaas Bhat · Huitian Jiao · Phil Torr · Riashat Islam · Christopher Summerfield · Christian Schroeder de Witt · Qilong Gu · Shital Shah
强化学习与后训练OpenReview