Beyond Attention Scores: SVD-Based Vision Token Pruning for Efficient Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Apedo, Yvon, Poreba, Martyna, Szczepanski, Michal, Bouchafa, Samia
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/2604.11530