文献索引号: https://doi.org/10.48550/arXiv.2412.02930 Video LLMs for Temporal Reasoning in Long Videos下载 微信扫描下方的二维码阅读本文 文章导航 [文献CS-NEP-EN-20250528]Fostering Video Reasoning via Next-Event Prediction[文献CS-LVLM-EN-20231116]Video-LLaVA: Learning United Visual Representation by Alignment Before Projection