Chaoran Cheng

Department of Computer Science, University of Illinois Urbana-Champaign


Hi! I am Chaoran Cheng, a third-year CS Ph.D. candidate at the University of Illinois Urbana-Champaign. I am advised by Prof. Ge Liu, before which I was working with Prof. Jian Peng. My research interest mainly spans multiple AI4Science topics with a special focus on generative tasks on 3D molecules and proteins including sequence-structure co-design and structure optimization. Combining both the continuous and discrete modalities together, our work can build a more comprehensive and versatile generative model for molecules and proteins on diverse downstream tasks.

Out of my pure personal interest, I am developing a machine-learning based automatic charter for Cytoid, a community-driven rhythm game inspired by Rayark’s games Cytus and Cytus II. The community provides many fan-made charts that can be used to train a machine learning system.

I obtained my Bachelor’s Degree in EECS, Peking University, before which I also spent my freshman year studying chemistry.


May 28, 2024 Check out our latest work of Statistical Flow Matching (SFM) for discrete generation on arXiv! We applied SFM across image, text, and biological domains demonstrate its superior sampling quality and NLL on discrete tasks.
Sep 21, 2023 My work Equivariant Neural Operator Learning with Graphon Convolution was accepted to NeurIPS 2023 as a Spotlight paper. Check out the paper here. I am also honored to be the Workflow Chair of the New Frontiers in Graph Learning Workshop at NeurIPS 2023!
Dec 7, 2022
Check out this post on the Tensor Field Network! ‚ƨ
Nov 30, 2022
Get a glimpse of Cézanne and the revolution of modern art.

Selected Publications

  1. Categorical Flow Matching on Statistical Manifolds
    Chaoran Cheng, Jiahan Li, Jian Peng, and Ge Liu
    arXiv 2024
  2. Full-Atom Peptide Design based on Multi-modal Flow Matching
    Jiahan Li, Chaoran Cheng, Zuofan Wu, Ruihan Guo, Shitong Luo, Zhizhou Ren, Jian Peng, and Jianzhu Ma
    In International Conference on Machine Learning, ICML 2024
  3. Equivariant Neural Operator Learning with Graphon Convolution
    Chaoran Cheng, and Jian Peng
    In Thirty-seventh Conference on Neural Information Processing Systems 2023
  4. Orientation-Aware Graph Neural Networks for Protein Structure Representation Learning
    Jiahan Li, Shitong Luo, Congyue Deng, Chaoran Cheng, Jiaqi Guan, Leonidas Guibas, Jianzhu Ma, and Jian Peng
    arXiv 2022
  5. Equivariant Point Cloud Analysis via Learning Orientations for Message Passing
    Shitong Luo, Jiahan Li, Jiaqi Guan, Yufeng Su, Chaoran Cheng, Jian Peng, and Jianzhu Ma
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Jun 2022