Risk Awareness Injection: Calibrating Vision-Language Models for Safety without Compromising Utility

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Mengxuan, Chen, Yuxin, Xu, Gang, He, Tao, Jiang, Hongjie, Li, Ming
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2602.03402