YuE: Scaling Open Foundation Models for Long-Form Music Generation

Ruibin Yuan, Hanfeng Lin, Shuyue Guo, Ge Zhang, jiahao, Yongyi Zang, haoheliu, yimingliang, Wenye Ma, du, Xinrun Du, Zhen Ye, TY.Zheng, Yinghao Ma, minghao, Zeyue, Ziya Zhou, Liumeng Xue, HKUST Audio, Yizhi Li, Shangda Wu, Tianhao Shen, Ziyang Ma, Jun Zhan, Chun-Hui Wang, Yatian Wang, Xiaowei Chi, Xinyue Zhang, Zhenzhu Yang, Xiangzhou Wang, Shansong Liu, Lingrui Mei, Peng Li, wangjunjie, Jianwei Yu, Guojian Pang, Xu Li, Zihao Wang, Xiaohuan Zhou, Lijun Yu, Emmanouil Benetos, Yong Chen, Chenghua Lin, Xie Chen, Gus Xia, zhangzhaoxiang, Chao Zhang, Wenhu Chen, Xinyu Zhou, Xipeng Qiu, Roger Dannenberg, Jiaheng Liu, Jian Yang, Wenhao Huang, weixue, Xu Tan, Yike Guo

YuE: Scaling Open Foundation Models for Long-Form Music Generation: 78 upvotes on Hugging Face Daily Papers, #3 of 40 papers on 2025-03-12. Day-by-day upvote history.

We tackle the task of long-form music generation--particularly the challenging lyrics-to-song problem--by introducing YuE, a family of open foundation models based on the LLaMA2 architecture. Specifically, YuE scales to trillions of tokens and generates up to five minutes of music while maintaining lyrical alignment, coherent musical structure, and engaging vocal melodies with appropriate accompaniment. It achieves this through (1) track-decoupled next-token prediction to overcome dense mixture signals, (2) structural progressive conditioning for long-context lyrical alignment, and (3) a multitask, multiphase pre-training recipe to converge and generalize. In addition, we redesign the in-context learning technique for music generation, enabling versatile style transfer (e.g., converting Japanese city pop into an English rap while preserving the original accompaniment) and bidirectional generation. Through extensive evaluation, we demonstrate that YuE matches or even surpasses some of the proprietary systems in musicality and vocal agility. In addition, fine-tuning YuE enables additional controls and enhanced support for tail languages. Furthermore, beyond generation, we show that YuE's learned representations can perform well on music understanding tasks, where the results of YuE match or exceed state-of-the-art methods on the MARBLE benchmark. Keywords: lyrics2song, song generation, long-form, foundation model, music generation

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.