Steering Video Diffusion Transformers with Massive Activations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cheng, Xianhang, Zheng, Yujian, Xie, Zhenyu, Liao, Tingting, Li, Hao
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/2603.17825