Why and When Visual Token Pruning Fails? A Study on Relevant Visual Information Shift in MLLMs Decoding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Jiwan, Kim, Kibum, Kim, Wonjoong, Lee, Byung-Kwan, Park, Chanyoung
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/2604.12358