作者位次 #5/11ICML 2026Poster· Deep Learning / Large Language Models
WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning
Gagan Mundada · Zihan Huang · Rohan Surana · Sheldon Yu · Jennifer Y Zhang · Xintong Li · Tong Yu · Lina Yao · Jingbo Shang · Julian J. McAuley · Junda Wu