破解“谁在何时说了什么”的多人对话难题，多模态大模型迎来关键突破。
arXiv:2603.21664v3 Announce Type: replace Abstract: While Omni-modal Large Language Models have made strides in joint sensory processing, they fundame…
ICML'26接收，提出一对多时序定位新框架，突破传统单片段局限，实现文本到视频多片段精准匹配。
arXiv:2606.06294v1 Announce Type: cross Abstract: Temporal Grounding (TG) aims to localize video segments corresponding to a textual query. Prior rese…
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…