English(EN) TempCloze: Can Video-LLMs Identify the Missing Middle?

新的TempCloze基准测试视频大模型的时间推理能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-02 04:00

研究人员推出TempCloze，这是一个旨在评估视频大模型（Video-LLMs）时间推理能力的新基准。该基准通过向模型展示视频的开头和结尾，并要求它们从四个选项中识别出正确的缺失中间片段，来缓解语言捷径问题。对各种专有和开源视频大模型的初步评估表明，时间对齐是当前模型面临的一个重大挑战。 AI

影响该基准有望推动视频大模型在时间推理能力方面的改进，这对于需要理解连续事件的应用至关重要。

排序理由该集群包含一篇介绍新AI模型评估基准的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

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

本文如何被排名

Signal score: 29 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇介绍新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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

arXiv cs.AI TIER_1 English(EN) · Wenqi Pei, Henry Hengyuan Zhao, Yilai Liu, Jiahao Meng, Han Chen, Ziyu Wang, Hongyang Du · 2026-09-02 04:00

TempCloze：视频大模型能否识别中间缺失部分？

arXiv:2609.01515v1 Announce Type: cross Abstract: Temporal reasoning benchmarks for Video-LLMs are often mediated by language, leaving room for linguistic shortcuts from option wording, answer correlations, or language priors. To reduce such shortcuts, we introduce TempCloze, a v…