作者位次 #2/7ICLR 2026Poster· Computer Vision / Vision Models & Multimodal
MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement Learning
Yueqian Wang · Songxiang Liu · Disong Wang · Nuo Xu · Guanglu Wan · Huishuai Zhang · Dongyan Zhao