Assistant Professor (incoming)
Conducting research on multimodal large models, embodied intelligence, and spatial intelligence in the field of AI, dedicated to promoting the application and optimization of foundational models in intelligent perception, robot naviga
2017: Bachelor's degree in Computer Science from Hong Kong Baptist University.
2021: Master's degree in Computer Science from the University of California, Davis.
2024: Ph.D. in Computer Science from the University of Wisconsin-Madison.
June 2024-Present: Employed at the University of California, San Diego, as a Postdoctoral Research Fellow.
In terms of academic innovation, we have created a family of multimodal general-purpose models—including X-Decoder, SEEM, and FIND—that have gained notable influence in image understanding and have been further extended to embodied and spatial intelligence tasks. The corresponding series of works has been published at top-tier computer-vision conferences (ICCV, ECCV), leading robotics conferences (RSS, CORL, ICRA), and premier machine-learning conferences (NeurIPS, ICLR).
During my Ph.D., my research received the Best Paper Award at BMVC 2020 and was supported by the Microsoft Research Fund for Foundational Models. In my postdoctoral work, I have been funded by the NSF TILOS grant. These efforts demonstrate strong scholarly potential and promising prospects for real-world applications.