**摘要**
Full-length song generation must preserve coherence and musicality, render detailed vocal and accompaniment acoustics, and follow lyrics and prompts. Existing language model-based systems face a structural trade-off: mixed-token modeling preserves vocal-instrument coordination but obscures track-specific details, whereas dual-track prediction improves acoustics but requires longer sequences and we
👤 作者: Shun Lei, Huaicheng Zhang, 吴大鹏, Yaoxun Xu, Lishi Zuo, Wei Tan, Hangting Chen, Guangzheng Li, Jianwei Yu, Zhiyong Wu, Dong Yu

---
🔗 **[LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training](https://arxiv.org/abs/2606.30642v1)**

> LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training
🏷️ 来源: ArXiv cs.AI
⏱️ 2026-06-30 14:00