NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
6 results for “keyword:"reinforcement learning for llms"” in ICLR 2027. 1 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Just Reuse the Rollout Log-Probs: Stable Mixture-of-Experts Reinforcement Learning with a Vocabulary-KL Clip▼5.8k2.33
[PDF]Do Language Models Revise the Right Conclusions? Diagnosing and Training Evidence-Contingent Reasoning▼5.8k2.33
[PDF]Same Mastery, Opposite Directions: Signed Learning Progress for Prompt Revisiting in RLVR▼1.2k1.67