How Much Information Can a Vision Token Hold? A Scaling Law for Recognition Limits in VLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhuang, Shuxin, Liang, Zi, Yu, Runsheng, Li, Hongzong, Feng, Rong, Tang, Shiqin, Zhang, Youzhi
Format:	Preprint
Published:	2026
Subjects:	Machine Learning 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/2602.02539