作者位次 #2/3ICML 2026Oral
Skip a Layer or Loop It? Learning Program-of-Layers in LLMs
Ziyue Li · Yang Li · Tianyi Zhou
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Ziyue Li · Yang Li · Tianyi Zhou
Xiaozhe Li · Yang Li · Xinyu Fang · Shengyuan Ding · Peiji Li · Yongkang Chen · Yichuan Ma · TianYi Lyu · Linyang Li · Dahua Lin · Qipeng Guo · Qingwen Liu · Kai Chen
Xiaozhe Li · Xinyu Fang · Shengyuan Ding · Yang Li · Linyang Li · Haodong Duan · Qingwen Liu · Kai Chen
Large Language Models (LLMs) have achieved remarkable success on reasoning benchmarks through Reinforcement Learning with Verifiable Rewards (RLVR), excelling at tasks such as math, coding, logic and puzzles. However, existing benchmarks evaluate only correctness, overlooking optimality—the abili...