Generative AI is transforming creative practice across music, visual art, and writing, yet most current systems leave human creators on the margins, reducing creation to trial-and-error prompting and repeated sampling. Genuine creative work is an iterative process of expressing and refining intention. The path to meaningful machine creativity therefore lies not in fully automated generation, but in symbiotic creativity: human–AI co-creation with the human in the loop, where machine generation and human aesthetic judgment form a continuous feedback loop and the creator remains in control.
We present YuE2, a music foundation model built around this principle. Rather than producing audio end-to-end as a black box, YuE2 combines symbolic and audio generation. Given lyrics and style prompts, it first produces a readable, editable symbolic score (e.g., ABC notation with melody and chords), then based on that score, further creates the high-fidelity audio. This intermediate process improves the modeling of complex musical structure and creates a clear point of intervention: human creators or external language models can revise the score before synthesis, or re-edit the generated results.
YuE2 is the first open-source music model to match leading commercial systems, while offering substantially greater controllability. It has gained wide recognition in the open-source community, reaching #4 on Hugging Face’s global trending list alongside with DeepSeek and Qwen.

Professor Yike Guo is a world-renowned computer scientist and a foreign member of the Chinese Academy of Engineering. He currently serves as Provost of the Hong Kong University of Science and Technology, Chair Professor in the Department of Computer Science and Engineering, and Founding Director of the Hong Kong Generative AI Research and Development Center (HKGAI). With his main research interests in machine learning and large-scale data management, he has been leading numerous large-scale AI research projects in Hong Kong, Mainland China, the UK, and other European countries.
Previously, he was the Founding Director of the Data Science Institute at Imperial College London, and the Vice President (Research and Development) at Hong Kong Baptist University. In recognition of his work, he holds numerous prestigious titles, including Fellow of the Royal Academy of Engineering (FREng), Member of Academia Europaea (MAE), Fellow of the Hong Kong Academy of Engineering Sciences (FHKEng), Fellow of the Institute of Electrical and Electronics Engineers (FIEEE), Fellow of the British Computer Society (FBCS), and Fellow of the Chinese Association for Artificial Intelligence (FCAAI). He is also the recipient of 2023 Wu Wenjun Outstanding Contribution Award for Artificial Intelligence.