Vision Token Reduction via Attention-Driven Self-Compression for Efficient Multimodal Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Deniz, Omer Faruk, Mao, Ruiyu, Li, Ruochen, Tian, Yapeng, Khan, Latifur
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2602.12618