#music generation
topicmusic generation
3 papers · 1 filter
eess.AS2026
WanSong v1.0 Technical Report
Binghui Chen, Pandeng Li, Yu Liu +1
The paper introduces WanSong, a diffusion‑based model that can directly generate high‑fidelity, multilingual songs up to five minutes long, outputting separate vocal and background…
cs.SD2026
Qwen-Music Technical Report
Jin Xu, Kangdi Wang, Ruibin Yuan +24
Qwen-Music is a large language model‑based system that generates high‑fidelity songs with vocals from text prompts or re‑imagines existing tracks, using a semantic token representa…
cs.SD2026
MusicMark: A Robust Generative Watermarking Framework for Music Generation
Seohwan Yun, Jeeyoung Yun, Yongjin Kim +2
The paper introduces MusicMark, a framework that embeds watermarks directly into the latent space of diffusion-based music generation models, making the watermarks robust to transf…