DeAR: Fine-Grained VLM Adaptation by Decomposing Attention Head Roles

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ma, Yiming, Yang, Hongkun, Wang, Lionel Z., Chen, Bin, Xian, Weizhi, Teng, Jianzhi
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/2603.01111