作者位次 #9/10ICML 2026Poster· Deep Learning / Large Language Models
TGPO: Efficient Policy Optimization through Sequence Anchor and Information Gating
Hang Ding · Dongqi Liu · Qiming Feng · Jian Li · Tong Lei · Jiafu Wu · Shuo Wang · Jiangning Zhang · Chengjie Wang · Yabiao Wang