作者位次 #12/14ICML 2026Poster· Deep Learning / Large Language Models
dTRPO : Trajectory Reduction in Policy Optimization of Diffusion Large Language Models
Wenxuan Zhang · Lemeng Wu · Changsheng Zhao · Ernie Chang · Mingchen Zhuge · Zechun Liu · DiJia Su · Hanxian Huang · Jun Chen · Chong Zhou · Raghuraman Krishnamoorthi · Vikas Chandra · Mohamed Elhoseiny · Wei Wen
强化学习与后训练OpenReview