作者位次 #3/7NeurIPS 2026Poster
From Denoising to Refining: A Corrective Framework for Vision-Language Diffusion Model
Yatai Ji · Teng Wang · Yuying Ge · Zhiheng Liu · Sidi Yang · Ying Shan · Ping Luo
多模态OpenReview
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。
Yatai Ji · Teng Wang · Yuying Ge · Zhiheng Liu · Sidi Yang · Ying Shan · Ping Luo
Boyu Chen · Yi Chen · Lu QIU · Jerry Bai · Yuying Ge · Yixiao Ge
Jun Zhang · Teng Wang · Yuying Ge · Yixiao Ge · Xinhao Li · Limin Wang
Shengchao Zhou · Yuxin Chen · Yuying Ge · Wei Huang · Jiehong Lin · Ying Shan · XIAOJUAN QI
Yuxin Guo · Teng Wang · Yuying Ge · Shijie Ma · Yixiao Ge · Wei Zou
Yi Chen · Yuying Ge · Rui Wang · Yixiao Ge · JUNHAO CHENG · Ying Shan · Xihui Liu
Recent reinforcement learning (RL) approaches, such as outcome-supervised GRPO, have advanced reasoning in Large Language Models (LLMs), yet their adaptation to multimodal LLMs (MLLMs) remains underexplored. Progress has been further limited by the lack of evaluation settings that jointly test pe...