Window-Diffusion: Accelerating Diffusion Language Model Inference with Windowed Token Pruning and Caching

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zuo, Fengrui, Ke, Zhiwei, Liu, Yiming, Lou, Wenqi, Wang, Chao, Zhou, Xuehai
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2601.20332