DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Zherui, Nie, Zheng, Zhou, Zhenhong, Liu, Yue, Zhang, Yitong, Cheng, Yu, Wen, Qingsong, Wang, Kun, Guo, Yufei, Zhang, Jiaheng
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2509.24296