LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fang, Kechen, Qin, Yihua, Wang, Chongyi, Ma, Wenshuo, Yu, Tianyu, Yao, Yuan
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/2605.08985