DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tao, Keda, Qin, Can, You, Haoxuan, Sui, Yang, Wang, Huan
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2411.15024