SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lu, Weikai, Peng, Hao, Zhuang, Huiping, Chen, Cen, Zeng, Ziqian
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Cryptography and Security Multimedia
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.12562