English(EN)How Robust is OCR-Reasoning? Evaluating OCR-Reasoning Robustness of Vision-Language Models under Visual Perturbations
视觉语言模型在鲁棒性、因果推理和视觉搜索方面接受测试
作者PulseAugur 编辑部·[6 个来源]·
研究人员正在从多个维度调查视觉语言模型（VLM）的鲁棒性和推理能力。一项研究引入了OCR-Robust，这是一个用于评估VLM在光学字符识别任务中对视觉扰动的韧性的基准，揭示了图表和表格等结构性元素特别脆弱。另一篇论文探讨了VLM在因果顺序推理方面的挣扎，发现它们尽管在物体识别方面表现出色，但由于训练数据中缺乏明确的因果表达，因此表现不佳。此外，一项研究检查了VLM执行视觉搜索任务的情况，将其“推理令牌”使用与人类反应时间进行比较，并指出了它们搜索策略的相似性和差异性。
AI
arXiv:2606.26041v1 Announce Type: cross Abstract: Vision-language models (VLMs) have achieved strong performance on OCR-based benchmarks and increasingly focused on text-rich understanding, but their robustness under controlled visual degradation remains insufficiently understood…
Vision-language models (VLMs) have achieved strong performance on OCR-based benchmarks and increasingly focused on text-rich understanding, but their robustness under controlled visual degradation remains insufficiently understood. This gap is critical for OCR reasoning, where vi…
Vision-language models (VLMs) have achieved strong performance on OCR-based benchmarks and increasingly focused on text-rich understanding, but their robustness under controlled visual degradation remains insufficiently understood. This gap is critical for OCR reasoning, where vi…
arXiv:2605.08245v4 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) increasingly power high-stakes applications, from medical imaging to autonomous systems, yet they routinely hallucinate, confidently describing content not present in the input. We investigate…
arXiv:2506.00869v3 Announce Type: replace Abstract: Despite the impressive performance of vision-language models (VLMs) on downstream tasks, their ability to understand and reason about causal relationships in visual inputs remains unclear. Robust causal reasoning is fundamental …
arXiv:2606.25066v1 Announce Type: cross Abstract: Visual search has been one of the most productive paradigms in the study of visual attention: the way reaction time scales with the number of items distinguishes parallel, "pop-out" search from serial, attention-demanding search. …
