When Looking Is Not Enough: Visual Attention Structure Reveals Hallucination in MLLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cao, Fanpu, Zou, Xin, Hu, Xuming, Xiong, Hui
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/2605.11559