• I am a tenure-track assistant professor at IICS lab at Fudan University.
• My research interests lie in the general area of machine learning, particularly in deep learning, generative AI, computer vision, and optimization.
• I received my Ph.D. Degree in the Electrical Engineering and Computer Science Department at Oregon State University, advised by Prof.Sinisa Todorovic.
• I received my Bachelor’s Degree in mathematics at Fudan University.

Recent News

• Aug 8, 2022. I joined IICS lab at Fudan University as a tenure-track assistant professor.

Selected Publications

• Zitao Yang, Amin Ullah, Shuai Li, Fuxin Li, Jun Li
  Convex Potential Mirror Langevin Algorithm for Efficient Sampling of Energy-Based Models
  The Thirty-Ninth Annual Conference on Neural Information Processing Systems. NeurIPS 2025.
  

• Ruizhe Zheng*, Jun Li*, Yi Wang, Tian Luo, Yuguo Yu.
  ScatterFormer: Locally-Invariant Scattering Transformer for Patient-Independent Multispectral Detection of Epileptiform Discharges
  The 37th AAAI Conference on Artificial Intelligence. AAAI 2023 (Oral). (equal contribution)
  [paper]

• 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
  The 10th International Conference on Learning Representations. ICLR 2022.
  [paper]

• Tan Yu, Jun Li, Yunfeng Cai, Ping Li.
  Constructing Orthogonal Convolutions in an Explicit Manner
  The 10th International Conference on Learning Representations. ICLR 2022.
  [paper]

• Jun Li, Sinisa Todorovic.
  Action Shuffle Alternating Learning for Unsupervised Action Segmentation
  Conference on Computer Vision and Pattern Recognition 2021. CVPR 2021.
  [paper]

• Jun Li, Sinisa Todorovic.
  Anchor-Constrained Viterbi for Set-Supervised Action Segmentation
  Conference on Computer Vision and Pattern Recognition 2021. CVPR 2021.
  [paper]

• Jun Li, Sinisa Todorovic.
  Set-Constrained Viterbi for Set-Supervised Action Segmentation
  Conference on Computer Vision and Pattern Recognition 2020. CVPR 2020.
  [paper]

• Jun Li, Fuxin Li, Sinisa Todorovic.
  Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley Transform
  The 8th International Conference on Learning Representations. ICLR 2020.
  [paper]

• Jun Li, Peng Lei, Sinisa Todorovic.
  Weakly Supervised Energy-Based Learning for Action Segmentation
  International Conf. on Computer Vision 2019. ICCV 2019 (Oral).
  [paper][code][video][slides][poster]