Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Binghui Chen

Binghui Chen

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

Audio and Speech Processing×1Vision×1

Frequent co-authors

Pandeng Li1×
Yu Liu1×
Jingren Zhou1×

Research Timeline

2026
WanSong v1.0 Technical Report

This paper introduces WanSong, a diffusion-based model for long-form, commercial-grade song generation that directly generates high-fidelity, multilingual songs up to 5 minutes and outputs dual stems, enabling faster inference and customization.

Highlighted terms show continued research focus across papers

Papers

eess.AScs.CVEmpiricalRecentJul 16, 2026

WanSong v1.0 Technical Report

Binghui Chen, Pandeng Li, Yu Liu, Jingren Zhou

This paper introduces WanSong, a diffusion-based model for long-form, commercial-grade song generation that directly generates high-fidelity, multilingual songs up to 5 minutes and outputs dual stems,…

View →