I’m currently working on Diffusion-based Large Avatar Model. I got my Ph.D. at Zhejiang University, advised by Prof. Zhou Zhao (赵洲). My acedamic experience include 3D Talking Face Generation and Text-to-Speech (TTS). I have also deeply investigated Deep Reinforcement Learning (DRL) and Multi-Agent Systems (MAS). I have published 15+ papers in high-impact conference/journals, including ICLR, IJCAI, ACL, IEEE TMC, etc.

Zhenhui Ye (叶振辉)
Zhejiang University
- Ph.D student in Zhejiang University. Focusing on audio and video generation.
- Hangzhou, China
- DBLP
- Github
- Google Scholar
- ORCID