Xudong Xu

Xudong Xu is a researcher at Shanghai Artificial Intelligence Laboratory, specializing in Embodied AI with a focus on interactive scene generation and 3D object synthesis. He earned his Ph.D. in Information Engineering from The Chinese University of Hong Kong (2018-2023), advised by Prof. Dahua Lin, and holds a Bachelor's degree in Automation from Nanjing University (2014-2018), where he ranked first in his cohort.

His research explores compositional scene generation, procedural modeling of articulated objects, and material-aware 3D synthesis. He has published in top venues like SIGGRAPH Asia, ECCV, NeurIPS, and contributed to projects such as MATLABER and RoomTex. His work leverages Gaussian splatting, PBR materials, and occupancy fields for high-fidelity 3D environments.

Xudong has received prestigious awards including the Shanghai Leading Talent Program, CUHK Postgraduate Scholarship, and National Scholarship at Nanjing University. He serves as a reviewer for major AI/ML conferences like CVPR, ICCV, and NeurIPS, and mentors interns from institutions such as University of Virginia and UC San Diego.