作者位次 #6/9ICML 2026Poster· Applications / Computer Vision
Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO
Yunze Tong · Mushui Liu · Canyu Zhao · Wanggui He · Shiyi Zhang · Peng Zhang · Hongwei Zhang · Jinlong Liu · Hao Jiang