I am a Ph.D. student in the Department of Electrical and Computer Engineering (ECE) at the University of California, San Diego (UCSD), advised by Gal Mishne. My research covers a broad range of machine learning/computer vision problems, and sometimes their application in neuroscience. I am particularly interested in generative models, from traditional statistical modeling to deep generative models such as variational autoencoders (VAEs) and diffusion models (DMs). Currently I am working on the intersection of probablistic graphical modeling and graph signal processing. Previously, I obtained my bachelor degree in Biomedical Engineering from Beihang University (former BUAA). I also interned at NEC Lab America.
Cartesian Product Graph Learning with Laplacian Constraints, C. Shi and G. Mishne, The 27th International Conference on Artificial Intelligence and Statistics (AISTATS 2024).
Conditional Image-to-Video Generation with Latent Flow Diffusion Models, H. Ni, C. Shi, K. Li, S. X. Huang and M. R. Min, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023).
Learning Disentangled Behavior Embeddings, C. Shi, S. Schwartz, S. Levy, S. Achvat, M. Abboud, A. Ghanayim, J. Schiller and G. Mishne, The 35th Conference on Neural Information Processing Systems (NeurIPS 2021).
Online adversarial purification based on self-supervised learning, C. Shi, C. Holtz and G. Mishne, The 9th International Conference on Learning Representations (ICLR 2021).