V-CAST: Video Curvature-Aware Spatio-Temporal Pruning for Efficient Video Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Xinying, Liu, Xuyang, Wang, Yiyu, Ma, Teng, Ren, Wenqi
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/2603.27650