Evading Visual Aphasia: Contrastive Adaptive Semantic Token Pruning for Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ma, Jie, Liu, Yihang, Qiu, Zhike, Ji, Jiayi, Sun, Xiaoshuai
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/2605.09429