Textural or Textual: How Vision-Language Models Read Text in Images

Hanzhang Wang; Qingyuan Ma

2025 ICML ICML 2025

Textural or Textual: How Vision-Language Models Read Text in Images

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Hanzhang Wang, Qingyuan Ma

Topics

Artificial Intelligence > Core AI > Multimodal Learning Machine Learning > Core Methods > Representation Learning Deep Learning > Learning Types > Multimodal Learning

Keywords

semantic representation intrinsic dimension layer-wise analysis vision-language model typographic attack orthographic form

Download PDF