Zizhao Li is a PhD candidate in Computer Science at the University of Melbourne. His research focuses on computer vision, machine learning, and trustworthy AI, with particular interests in open-world recognition, out-of-distribution detection, and uncertainty-aware perception for autonomous systems.
His recent work studies how 2D and 3D perception models can recognize unknown objects and detect distribution shifts in open environments. He has worked on open-world object detection with vision-language models, LiDAR-based out-of-distribution detection, 3D shape anomaly detection, and semantic-guided LiDAR generation. His research has been published at top computer vision venues, including CVPR, ICCV, BMVC, and TMLR.
(* denotes equal contribution)
| Programming | Python, C, C++, Java, JavaScript, TypeScript, Ruby |
| Frameworks / Tools | PyTorch, OpenCV, Git, Linux, LaTeX |
| Research Areas | 3D Computer Vision, Multimodal Learning, LiDAR Perception, OOD Detection, Open-World Recognition |