Yinuo Wang

Hi, I’m Yinuo. I build digital humans that can talk, listen, respond, and remember.

My research focuses on generative digital avatars, with an emphasis on modeling expressive listening behavior and creating interactive 3D heads that respond naturally to people in real time. Ultimately, I hope to make virtual humans feel less like scripted animations and more like perceptive, consistent conversational partners.

My recent work explores diffusion-based interactive head generation, multimodal interaction, long-term conversational memory, and controllable generation for 3D heads. Before focusing on digital avatars, I worked on a range of machine learning problems, including multi-view clustering, image classification, and robust time-series forecasting. This background continues to shape how I think about representing and generating complex human behavior.

I am currently in the final stages of my PhD at Xi'an Jiaotong University and am seeking new opportunities. If you are interested in my work or potential collaboration, please feel free to get in touch.