English 中文

My Research: Towards a more creative, expressive, interactive world via Music AI.

My research journey so far has unfolded in three stages. The first stage centered on Music AI technologies, including music information retrieval, expressive performance modeling, music robotics, and haptic guidance for flute education. The second stage turned toward interpretability and control in Music AI, with a focus on self-supervised learning, representation disentanglement, style transfer, hierarchical modeling, and symbolic music generation.

In the third, current stage, music serves as a lens for uncovering the fundamental organizing principles of human intelligence. My team and I are developing two related ideas: Function Alignment, which studies how System 1 and System 2 processes work together, and Emergent Language, which asks how symbolic systems can arise from intuitive processes. I believe these questions are central to understanding aesthetics, creativity, and human expression.

For me, music is not only an application domain for AI, but also a privileged window into the mechanisms through which humans make meaning, create beauty, and build culture.

About me: A computer scientist and professional musician.

I am an Associate Professor in Machine Learning at MBZUAI, where I direct the Music X Lab. I received my Ph.D. from the Machine Learning Department at Carnegie Mellon University, advised by Prof. Roger Dannenberg, and was a Neukom Fellow at Dartmouth from 2016 to 2017. I received my undergraduate degree in Information Science, with a minor in Psychology, from Peking University.

I am also a professional DI and XIAO player, keeping music at the center of my life. At Peking University, I was the principal soloist of the Chinese Music Institute (CMI), and served as its president and assistant conductor. I held my solo concert in 2010 and a Music AI concert in 2022. (See Music Events)