一作ECCV 2026Poster
Video-Holmes: Can MLLM Think like Holmes for Complex Video Reasoning?
JUNHAO CHENG · Yuying Ge · Teng Wang · Yixiao Ge · Jing Liao · Ying Shan
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。
JUNHAO CHENG · Yuying Ge · Teng Wang · Yixiao Ge · Jing Liao · Ying Shan
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...