Published first-author papers at top international AI conferences like NeurIPS/ICLR/ICML/ACL/IJCAI. Awarded the Best Thesis Award by the Electrical Engineering Association (2025.04). Released several notable algorithms, including UniAudio, AudioGPT, etc. Published multiple papers in important conferences.
Research Experience
Worked at the Seamless Team at FAIR. Developed several well-known Speech/NLP algorithms such as Seamless-Interaction (LLama4+Dyadic Motion Diffusion), AudioGPT, UniAudio, etc.
Education
Graduated from the College of Computer Science, Zhejiang University, supervised by Prof. Zhou Zhao. Also obtained a Bachelor’s degree from Zhejiang University.
Background
Research interests include Multi-modal Large Language Model, Video-Audio Generative Models, and Audio-Visual Language Processing. Previously worked at the Seamless Team at FAIR.