Seminar by Prof. Li ZHANG from School of Data Science, Fudan University

In this talk, I will explore our work on vision foundation model, starting with the Segmentation Transformer and progressing to the linear and mobile variants. Recently, we aim to create a generative model for visual segmentation. I will also discuss our contribution on autonomous driving, including our pure vision solution Polarformer and Ego3RT, and the multimodal solution Deepinteraction which took the first place on nuScenes, as well as our recent work on large-scale autonomous driving system, Street NeRF.

Li Zhang is a tenure-track Professor at the School of Data Science, Fudan University. Previously, he was a Research Scientist at Samsung AI Center Cambridge, and a Postdoctoral Research Fellow at the University of Oxford. Prior to joining Oxford, he read his PhD in computer science at Queen Mary University of London. The aim of his research group is to make the machine see and empower the next generation AI by striving to achieve the most universal representation of understanding objects and scenes with mathematical models of neural networks. He was elected to the Shanghai Science & Technology 35 Under 35. He serves as the area chair for NeurIPS 2023 and CVPR 2023 & 2024.