Xinghang Li
Xinghang Li is a PhD student in the Department of Computer Science and Technology at Tsinghua University and a researcher at Xiaomi Robotics, where he bridges academic world-model research and industrial robotics. He is best known as a co-corresponding author of X-WAM (Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising), a system that is the first to unify real-time robotic control, photorealistic 4D video generation, and 3D spatial reconstruction within a single model pretrained on over 5,800 hours of robotic data. His broader research focuses on vision-language-action models, large-scale robot learning, and connecting visual pretraining with robotic manipulation.
“A Xiaomi Robotics / Tsinghua team has built the first system to simultaneously do real-time robot control, spatially-accurate 3D reconstruction, and photorealistic video prediction from a *single* model — trained on 5,800+ hours of robot data.”
Source→“As co-corresponding author at Xiaomi Robotics, Li is a key figure in translating world-model research into deployed hardware products.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.