Zijun Cui

I am a PhD student in Computer Science at the University of Texas at Dallas (starting June 2026). I am fortunate to be supervised by Prof. Yapeng Tian at the Computer Vision and Multimodal Computing (CVMC) Lab. My research interests lie in Physical AI, with a focus on Audio-Visual Perception & Generation.

I am really fortunate to have collaborated with Dr. Xiulong Liu. Previously, I received my M.S. in Electrical and Computer Engineering from University of Washington, advised by Eli Shlizerman. Before UW, I was very lucky to collaborate with Prof. Zhaopeng Cui's research group at State Key Laboratory of CAD&CG at Zhejiang University.

My full name is pronounced as /ziˈdʒʊn tsweɪ/, with the “C” in Cui sounding like “ts”.

I am actively seeking research opportunities. Feel free to email me if you would like to collaborate!

Email: [email protected]

/ LinkedIn  /  Calendar  /  Email  /  Github  /  Google Scholar  / 

We introduce SAVVY-Bench, the first benchmark for 3D spatial reasoning in dynamic audio-visual scenes. We also propose SAVVY, a novel training-free pipeline integrating egocentric spatial tracks and dynamic global maps, which significantly enhances AV-LLM performance for improved audio-visual spatial awareness in such environments.

Thanks to Jon Barron for providing this template.