Our lab is dedicated to advancing computer vision, deep learning, and artificial intelligence. Our aim is to push visual intelligence forward toward open-world environments and power its applications on open-ended agents. We believe it has the potential to transform future manufacturing, robotics, autonomous driving, virtual reality and more, thereby generate positive impacts on our lives. Currently, we are interested in exploring the following topics:
Open-world intelligence: Representation, representation learning, data-centric methods, efficient and trustworthiness models.
Interactive environment simulation: 3D reconstruction, neural rendering, 3D generation, and motion simulation.
Applications on open-ended agents: Vision for robotics, language as an interface for visual models.
We are also interested in utilizing AI to advance scientific and medical research (AI for Science and Medicine).
Lab Updates
-
Five papers are accepted to ICCV 2023. Congratulations to my students and collaborators.
-
Dr. Xiaojuan Qi will be an area chair for NeurIPS 2023.
-
Seven papers are accepted to CVPR 2023. Congratulations to my students and collaborators.
-
Three papers are accepted to ICLR 2023 with two spotlight papers. Congratulations to my students and collaborators.
-
Six papers are accepted to NeurIPS 2022. Congratulations to my students and collaborators.
Lab Members