Stateful Token Reduction for Long-Video Hybrid VLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jiang, Jindong, Deshmukh, Amala Sanjay, Chumachenko, Kateryna, Sapra, Karan, Yu, Zhiding, Liu, Guilin, Tao, Andrew, Molchanov, Pavlo, Kautz, Jan, Byeon, Wonmin
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.00198