1
MLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues
多模态大模型对视频时间定位不可靠？这篇论文通过注意力线索揭示并恢复时间感知，有望突破时序理解瓶颈。
arXiv:2605.21954v1 Announce Type: new Abstract: Video temporal grounding (VTG), which localizes the start and end times of a queried event in an untri…