VISTA-Bench: 视觉-语言模型是否真的能像纯文本一样理解可视化文本？
VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?
AI总结：
VISTA-Bench通过对比纯文本和可视化文本问题，揭示了视觉-语言模型在处理可视化文本时的模态差距，发现模型在语义相同的情况下表现显著下降。
摘要：
视觉-语言模型（VLMs）在跨模态理解方面取得了显著进展，但现有基准主要关注纯文本查询。本文引入VISTA-Bench，一个涵盖多模态感知、推理和单模态理解的系统性基准，通过受控渲染条件对比纯文本和可视化文本问题，评估模型对可视化文本的理解能力。对超过30个代表性VLMs的评估揭示了显著的模态差距：在纯文本表现优异的模型在同等语义内容以可视化文本呈现时显著退化。这一差距随着感知难度的增加而加剧，凸显了模型对渲染变化的敏感性。VISTA-Bench提供了一个原则性的评估框架，用于诊断这一限制并指导向更统一的语言表征（tokenized文本和像素）的发展。
英文摘要：
Vision-Language Models (VLMs) have achieved impressive performance in cross-modal understanding across textual and visual inputs, yet existing benchmarks predominantly focus on pure-text queries. In real-world scenarios, language also frequently appears as visualized text embedded in images, raising the question of whether current VLMs handle such input requests comparably. We introduce VISTA-Bench, a systematic benchmark from multimodal perception, reasoning, to unimodal understanding domains. It evaluates visualized text understanding by contrasting pure-text and visualized-text questions under controlled rendering conditions. Extensive evaluation of over 30 representative VLMs reveals a pronounced modality gap: models that perform well on pure-text queries often degrade substantially when equivalent semantic content is presented as visualized text. This gap is further amplified by increased perceptual difficulty, highlighting sensitivity to rendering variations despite unchanged semantics. Overall, VISTA-Bench provides a principled evaluation framework to diagnose this limitation and to guide progress toward more unified language representations across tokenized text and pixels. The source dataset and code are publicly available at https://github.com/QingAnLiu/VISTA-Bench.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
