My research aims to build embodied spatial intelligence systems that enable robots to perceive their surroundings, maintain persistent spatial memory, predict the consequences of actions, and acquire robust skills for long-horizon interaction. This research integrates spatial perception, embodied foundation models, robot policy learning, and the co-design of robot bodies and sensing systems.
My research journey began at Peking University, where my master’s research focused on nonlinear least-squares optimization and geometric computer vision. I later pursued my PhD at the Technical University of Munich, further advancing my research in camera pose tracking, 3D reconstruction, and scene understanding.
I am actively recruiting motivated students and researchers to join the Embodied Spatial AI Lab at HKUST(GZ). Openings are available for MPhil students, research assistants, and interns starting in Fall 2026, and for PhD students starting in Spring/Fall 2027. HKUST(GZ) undergraduate students are also welcome to join the lab through the Explorers Undergraduate Research Program (X Program).
Join the LabGeometry-aware perception systems that enable robots to localize, map, and understand complex real-world environments through spatially consistent representations.
Persistent 3D and 4D world models that support long-horizon robot autonomy through geometry-centric tracking, reconstruction, and structured scene representations.
Learning-based robot systems that connect perception, representation, and reasoning with decision-making and interaction in dynamic environments.
We welcome motivated students and researchers interested in Spatial Intelligence, Foundation Models, and Robot Learning & Systems.
PhD openings are available for Spring/Fall 2027. MPhil applications are welcome from Fall 2026.
Opportunities are available in perception, reconstruction, robot learning, hardware, and intelligent systems.
Undergraduate students may join the lab through the Explorers Undergraduate Research Program.