Fre-Res: Frequency-Residual Video Token Compression for Efficient Video MLLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Feng, Yigui, Wang, Qinglin, Liu, Yang, Liu, Jie
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence I.2.10
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2605.16366