Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wen, Yuxin, Cao, Qingqing, Fu, Qichen, Mehta, Sachin, Najibi, Mahyar
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2410.14072