Q Cache: Visual Attention is Valuable in Less than Half of Decode Layers for Multimodal Large Language Model

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhuang, Jiedong, Lu, Lu, Dai, Ming, Hu, Rui, Chen, Jian, Liu, Qiang, Hu, Haoji
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/2602.01901