OOD-MMSafe: Advancing MLLM Safety from Harmful Intent to Hidden Consequences

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wen, Ming, Yang, Kun, Zhang, Jingyu, Liu, Yuxuan, cui, shiwen, Ji, Shouling, Ma, Xingjun
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.09706