MedPruner: Training-Free Hierarchical Token Pruning for Efficient 3D Medical Image Understanding in Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Shengyuan, Ye, Zanting, Lin, Yunrui, Hu, Chen, Geng, Wanting, Han, Xu, Ibragimov, Bulat, Zheng, Yefeng, Yuan, Yixuan
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/2603.11625