一项发表在arXiv上的新研究表明，当前的视频大语言模型（Video-LLMs）在长视频中准确跟踪角色的能力方面存在困难。尽管在InfiniBench的全局外观任务等基准测试中表现强劲，但模型常常无法识别特定角色，尤其是在区分同性别的个体时。研究表明，这些模型依赖于性别等表面线索，而不是深层的角色识别，导致在开放式提问或角色名称更改时准确率显著下降。 AI
影响 揭示了当前视频大语言模型的局限性，表明需要改进超越表面线索的角色跟踪机制。
排序理由 该集群包含一篇详细介绍视频大语言模型能力研究结果的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2607.11078v1 Announce Type: cross Abstract: Can a Video Large Language Model (Video-LLM) follow one person through a long video, keeping track of who they are well enough to report, in order, how their outfit changes across a full TV episode? Benchmarks increasingly score t…
Can a Video Large Language Model (Video-LLM) follow one person through a long video, keeping track of who they are well enough to report, in order, how their outfit changes across a full TV episode? Benchmarks increasingly score this kind of task, and the strongest open-source 7-…
Can a Video Large Language Model (Video-LLM) follow one person through a long video, keeping track of who they are well enough to report, in order, how their outfit changes across a full TV episode? Benchmarks increasingly score this kind of task, and the strongest open-source 7-…