CAMAL: Improving Attention Alignment and Faithfulness with Segmentation Masks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hundal, Rajdeep Singh, Xiao, Yan, Dong, Jin Song, Rigger, Manuel
Format:	Preprint
Published:	2026
Subjects:	Image and Video Processing Artificial Intelligence Machine Learning I.2.6; I.4.0
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2605.08325