Publications: - One paper accepted by ICLR 2023. - Two papers accepted by AAAI 2023. - One paper accepted by ECCV 2022. - One paper accepted by CVPR 2021. - Released high-performance anchor-free YOLOX in 2021. - Released BEVStereo, a new SOTA camera-only 3D detector on nuScenes dataset in September 2022.
Research Experience
He currently works as a researcher at Megvii Technology, supervised by Dr. Xiangyu Zhang. He leads a team working on unified foundation models for autonomous driving, as well as 2D detection models for solving real-world challenges. His team develops and maintains several well-known projects, including YOLOX and BEVDepth series.
Education
Ph.D. in Computer Science from Waseda University in 2022, supervised by Prof. Osamu Yoshie; B.S. in ECE from Southeast University in 2017.
Background
Currently a researcher at Megvii Inc., with research interests in Multi-modal Foundation Models, AIGC, and Self-supervised Representation Learning.