GuardAlign: Test-time Safety Alignment in Multimodal Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhu, Xingyu, Zhu, Beier, Fang, Junfeng, Wang, Shuo, Zhang, Yin, Wang, Xiang, He, Xiangnan
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Multimedia
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2602.24027