Enhance Generation Quality of Flow Matching V2A Model via Multi-Step CoT-Like Guidance and Combined Preference Optimization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Haomin, Shan, Sizhe, Wang, Haoyu, Chen, Zihao, Liu, Xiulong, Ding, Chaofan, Di, Xinhan
Format:	Preprint
Published:	2025
Subjects:	Sound Computer Vision and Pattern Recognition Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2503.22200