Rejection Mixing: Fast Semantic Propagation of Mask Tokens for Efficient DLLM Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ye, Yushi, Hong, Feng, Zheng, Huangjie, Chen, Xu, Chen, Zhiyong, Wang, Yanfeng, Yao, Jiangchao
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2602.22868