Reading $\neq$ Seeing: Diagnosing and Closing the Typography Gap in Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Heng, Yu, Ao, Kang, Li, Fan, Yuchen, Fan, Yutao, Song, Xiufeng, Geng, Hejia, Qin, Yiran
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.08497