PulseAugur
中
实时 03:48:47
English(EN) MMR-V: What's Left Unsaid? A Benchmark for Multimodal Deep Reasoning in Videos

新的MMR-V基准揭示LLM在深度视频推理方面存在困难

作者 PulseAugur 编辑部 · [1 个来源] ·

引入了一个名为MMR-V的新基准，用于评估大型语言模型（LLM）在处理视频内容时的多模态深度推理能力。与侧重于简单帧匹配的现有基准不同，MMR-V要求模型执行长距离、多帧推理，并推断超出直接感知的信息。使用MMR-V进行的实验（包含317个视频中的1,257个任务）显示，即使是像Gemini 2.5 Pro这样的先进模型也面临困难，准确率仅为64.3%，而像Chain-of-Thought这样的常用推理增强策略改进有限。 AI

影响 凸显了当前LLM在复杂视频理解方面的局限性，可能指导未来多模态推理的研究方向。

排序理由 该项目是一篇介绍新AI模型评估基准的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新的MMR-V基准揭示LLM在深度视频推理方面存在困难

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该项目是一篇介绍新AI模型评估基准的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
78 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.CL TIER_1 English(EN) · Kejian Zhu, Zhuoran Jin, Hongbang Yuan, Jiachun Li, Shangqing Tu, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao ·

    MMR-V：未言之意何在？视频多模态深度推理基准

    arXiv:2506.04141v2 Announce Type: replace-cross Abstract: The sequential structure of videos poses a challenge to the ability of multimodal large language models (MLLMs) to locate multi-frame evidence and conduct multimodal reasoning. However, existing video benchmarks mainly foc…

相关实体

相关话题