研究人员开发了两个新框架EcoFrame和EviSelect，旨在提高大型语言模型处理长视频理解的效率。EcoFrame采用一种无需训练的方法，根据模型的输出不确定性和注意力模式来调整帧选择过程，实现了显著的加速，并且准确性与现有方法相当。EviSelect则采用一种基于目标模型内部注意力的动态视觉选择方法，通过自适应地调整采样率和空间分辨率，同时优化准确性和效率。 AI
影响 这些新框架可以显著降低AI模型处理长视频的计算成本，从而在监控、内容分析和自主系统等领域实现更广泛的应用。
排序理由 两篇介绍长视频高效理解新方法的论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
Recent advancements in MLLM-based long-form video understanding have mitigated inference-time computational cost and limited context lengths by selecting query-relevant frames. However, existing approaches predominantly rely on external proxy scorers and rigid heuristic rules, in…
arXiv:2608.03918v1 Announce Type: cross Abstract: Efficient long-video understanding requires vision--language models (VLMs) to reason over a small number of frames selected as sparse visual evidence. Existing relevance-based methods rely on static one-shot selection with fixed f…
arXiv:2608.05780v1 Announce Type: new Abstract: Recent advancements in MLLM-based long-form video understanding have mitigated inference-time computational cost and limited context lengths by selecting query-relevant frames. However, existing approaches predominantly rely on exte…