| Li Jun Associate Principal Investigator, Master Supervisor Research Institute of Intelligent Complex Systems, Fudan University Email:jun_li@fudan.edu.cn |
Biography
Li Jun received his bachelor’s degree of mathematics and applied mathematics from Fudan University and his doctor’s degree of computer science from Oregon State University. He is dedicated to the fundamental research of artificial intelligence and machine learning, mainly including the algorithms, modeling and theory of 'third generation neural networks' spiking neural networks, as well as the optimization and generalization theory of deep neural networks. He has published papers and given presentations at top international AI/Deep learning conferences (ICLR, CVPR, ICCV, AAAI, etc.) for several times.
Research Interests：
spiking neural networks, deep learning theory
Representative Publications：
1.Ruizhe Zheng*, Jun Li*, Yi Wang, Tian Luo, Yuguo Yu. ScatterFormer: Locally-Invariant Scattering Transformer for Patient-Independent Multispectral Detection of Epileptiform Discharges, (AAAI Oral) 2023. (IF=25.57) (Co-first author)
2.Tan Yu, Jun Li, Yunfeng Cai, Ping Li. Constructing Orthogonal Convolutions in an Explicit Manner, (ICLR) 2022. (IF=20.03)
3.Jianwen Xie, Yaxuan Zhu, Jun Li, Ping Li. A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Model, (ICLR) 2022. (IF=20.03)
4.Jun Li, Sinisa Todorovic. Action Shuffle Alternating Learning for Unsupervised Action Segmentation, (CVPR) 2021. (IF=45.17)
5.Jun Li, Sinisa Todorovic. Anchor-Constrained Viterbi for Set-Supervised Action Segmentation, (CVPR) 2021. (IF= 45.17)
6.Jun Li, Sinisa Todorovic. Set-Constrained Viterbi for Set-Supervised Action Segmentation, (CVPR) 2020. (IF= 45.17)
7.Jun Li, Fuxin Li, Sinisa Todorovic. Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley Transform, (ICLR) 2020. (IF=20.03)
8.Jun Li, Peng Lei, Sinisa Todorovic. Weakly Supervised Energy-Based Learning for Action Segmentation, (ICCV Oral) 2019. (IF=21.94)
