Flash-Unified: A Training-Free and Task-Aware Acceleration Framework for Native Unified Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ke, Junlong, Wen, Zichen, Yang, Boxue, Yang, Yantai, Liu, Xuyang, Liao, Chenfei, Chen, Zhaorun, Wang, Shaobo, Zhang, Linfeng
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.15271