Self-Introduction
I am a fourth-year undergraduate in the 2023 cohort of the Experimental Program in Intelligence Science and Technology (Zhi Class) at the School of Electronics Engineering and Computer Science, Peking University.
My previous research has explored several aspects of audio and music intelligence, including automatic music transcription, music preference and reward modeling, and the post-training of generative music models. These experiences have led me toward a broader goal: unified audio intelligence. I hope to build agents that engage with the acoustic world more like humans do by perceiving complex polyphonic audio, understanding both fine-grained structure and high-level semantics, maintaining long-context memory, and interacting with users and their surroundings in real time. Looking further ahead, I am also interested in neural signal analysis, particularly MEG/EEG, and in studying the relationship between auditory perception and brain activity.
Music is also an essential part of my life beyond research. I play the violin, compose classical music, and have a strong interest in electronic music. These experiences continually shape the questions I ask and connect my technical work with the way people perceive, understand, and enjoy sound.