Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Chunyu, Li, Jiaye, Mei, Ruiqiao, Xia, Haoyuan, Zhu, Hao, Wang, Jingdong, Zhu, Siyu
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Multimedia Sound
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.23632