YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality
Symbolic models make melody, harmony, rhythm, and form explicit but typically stop before a finished recording; audio models produce complete songs while leaving composition implicit. We introduce YuE2, which unifies symbolic and audio music generation at frontier quality through symbolic planning. A single AR-NAR Mixture-of-Transformers (MoT) first writes a readable score specifying melody and harmony, expands it into semantic music tokens, and realizes it as full-song audio. In comparisons using the same checkpoint, experts prefer symbolic planning for overall quality and musicality, with 49.3% of overall preferences versus 34.6% without planning. Experts also favor the unified model ov...
| Authors | Ruibin Yuan, Jiahao Pan, Junyan Jiang et al. |
|---|---|
| Primary category | eess.AS |
| Published | 27 September 2026 |
| Last updated at source | 27 September 2026 |
Connected in the knowledge graph
- m-a-p/MERT-v2-30sModel · cited by
- m-a-p/WildSongBenchDataset · cited by
- m-a-p/MERT-v2-FullSongModel · cited by
- m-a-p/SheetSage2Model · cited by
- m-a-p/YuE2-VaeModel · cited by
- drgaz/SheetSage2Model · cited by
- m-a-p/YuE2-3BModel · cited by
- m-a-p/YuE2-Vae-legacyModel · cited by
Models and datasets referencing this paper
- m-a-p/YuE2-3BModel
- m-a-p/YuE2-VaeModel
- m-a-p/SheetSage2Model
- m-a-p/MERT-v2-FullSongModel
- m-a-p/MERT-v2-30sModel
- m-a-p/WildSongBenchDataset
- m-a-p/YuE2-Vae-legacyModel
- drgaz/SheetSage2Model
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.