Mingxuan joined the NVIDIA Dynamic Vision and Learning (DVL) group as a Research Intern in April 2026. He is a final-year PhD student at the University of Trento (Italy), under the supervision of Professor Elisa Ricci. His research interests include open-vocabulary perception and urban simulation for embodied AI, with the goal of developing open-world machines to see, understand, and reason about the visual, semantic, and physical complexity of the real world.

Previously, he was a Visiting Graduate Researcher at the University of California, Los Angeles (UCLA) for 9 months, where he worked on automatic urban simulation scene creation and large-scale 3D assets auto-labeling for last-mile sidewalk autonomy under the guidance of Professor Bolei Zhou. From 2024 to 2025, he was also a Visiting Researcher at NAVER LABS Europe in France, working on open-vocabulary object detection with Gabriela Csurka, Riccardo Volpi, and Tyler L. Hayes. Before his PhD, Mingxuan earned two Master’s degrees in robotics from KTH Royal Institute of Technology (Sweden) and the University of Trento. He also spent three years as an Automation Innovation Engineer at Siemens, developing IoT-enabled solutions for smart urban infrastructure.

Outside research, he enjoys going to the gym, hiking and camping in the mountains, and cooking at home.