Visible Yet Unreadable: A Systematic Blind Spot of Vision Language Models Across Writing Systems
可见却不可读:跨书写系统下视觉语言模型的系统性盲区
专题命中 视觉定位与Grounding :vision language model(title,abstract);分类 cs.CV、cs.AI
AI总结 本文研究了视觉语言模型在跨书写系统下识别碎片化文本的鲁棒性,发现其在可见但不可读的刺激下表现下降,揭示了模型对组成先验依赖不足的结构性限制。
Comments arXiv admin note: This article has been withdrawn by arXiv administrators due to violation of arXiv policy regarding generative AI authorship