My research interests include deep learning, computer vision, multi-modal understanding and analysis. Specifically, my group currently focuses on open-environment visual understanding, multi-modal LLM reasoning, multi-modal generation, etc. In the long term, we aim to build AI systems that are highly transferable (able to generalize across various scenarios), highly autonomous (able to evolve in dynamic environments), and scalable (able to easily extend to new tasks without forgetting).

Thanks for your interest in joining my group! We always have openings for outstanding students. Interested candidates for Master/PhD opportunities are strongly encouraged to contact me by email. Please attach your CV, and clearly discuss your research interests, coding skills and English ability. We provide extraordinarily strong support to students for internship, visiting, collaboration, and networking opportunities. Besides, we are alway open to working with outstanding BUAA undergraduates on some research projects. If you are interested, please contact me.

I am currently a Professor working in Beihang University. Before joining Beihang, I had been working in Carnegie Mellon Unversity (CMU) and University of Texas Austin (UTA) as a postdoc researcher. I obtained my Ph.D. degree, Master degree, Bachelor degree from University of Technology Sydney (UTS), Beihang Unviersity and Chongqing University respectively.