YuE2：以符号化规划统一符号与音频音乐生成
原标题：Paper page - YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality
AI 摘要
研究团队发布 YuE2 技术报告，提出通过符号化规划统一符号音乐与音频音乐生成：单一 AR-NAR Mixture-of-Transformers 模型先写出可读的旋律与和声乐谱，再扩展为语义音乐 token 并渲染成含人声与伴奏的完整歌曲。在 WildSongBench 上 YuE2 的 SongBench Global Avg 达 6.73，best-of-8 达 6.96，专家听测显示其优于 Suno v4.5、与 Suno v5 接近。报告还引入 MERT2 与 SheetSage2 提供语义与符号监督，并支持零样本翻唱、乐谱编辑及由外部语言模型代理驱动的音乐编辑。
正文节选
YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality Abstract 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 in