English(EN) OccludeBench: Can VLMs Find What's Missing?

新的OccludeBench基准揭示VLM在处理被遮挡物体时存在困难

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-12 04:00

一个名为OccludeBench的新基准已被开发出来，用于测试视觉语言模型（VLM）在图像中推断缺失或被遮挡物体romino的能力。该基准显示，当前VLM在恢复被直接遮挡的物体（准确率为42.7%）方面，其表现明显差于从更广泛的场景上下文中推断（准确率为62.7%），而人类在这些任务之间的差异很小。一个名为OccludeTrace的诊断工具发现，VLM在从特定的视觉线索（如阴影或反射）中恢复物体时最为困难。提示技术和工具使用显示出不稳定的改进，但一项在评估前对候选物体进行修复（inpainting）的干预措施，显著缩小了具有图像生成能力的模型的性能差距。 AI

影响突出了VLM视觉推理中的一个特定弱点，可能指导未来模型开发以获得更好的上下文理解和物体推断。

排序理由该集群包含一篇介绍用于评估AI模型的新基准和诊断工具的学术论文。[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 →

本文如何被排名

Signal score: 11 / 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用于评估AI模型的新基准和诊断工具的学术论文。[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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Jasin Cekinmez, Addison J. Wu, Ryo Mitsuhashi, Linrong Cai, Xingyu Fu, Zhuang Liu · 2026-10-12 04:00

OccludeBench：视觉语言模型能找到缺失的部分吗？

arXiv:2610.13790v1 Announce Type: cross Abstract: How well can vision-language models (VLMs) reason about what is missing from an image? We study this question with OccludeBench, a manually curated benchmark for recovering fully occluded objects from the visual evidence that rema…

本文如何被排名

报道来源 [1]

OccludeBench：视觉语言模型能找到缺失的部分吗？

相关实体

相关话题