Hong-Yu Chen | Northwestern University

Department of Computer Science.
Address: Mudd Hall 3205, 2233 Tech Drive, Third Floor, Evanston, IL 60208.
Email: charlie.chen@u.northwestern.edu.

website_self_2.png

Hi, I’m a first-year PhD student at Northwestern University in MAGICS lab advised by Prof. Han Liu. I focus on advancing the understanding and application of foundation models. My research explores the theoretical foundations of these models, including their universal approximation capabilities and potential to perform complex algorithms. I also work on extending their applications beyond language and vision, particularly in time series analysis and other scientific domain such as astrophysics.

selected publications

  1. Outlier-Efficient Hopfield Layers for Large Transformer-Based Models
    Jerry Yao-Chieh Hu, Pei-Hsuan Chang, Haozheng Luo, Hong-Yu Chen, Weijian Li, Wei-Po Wang, and Han Liu
    In Proceedings of the 41st International Conference on Machine Learning, 21–27 jul 2024
    arXiv PDF Code Poster Slides
  2. Universal Approximation with Softmax Attention
    Jerry Yao-Chieh Hu*, Hude Liu*, Hong-Yu Chen*, Weimin Wu, and Han Liu
    21–27 jul 2025
    *Equal Contribution
    arXiv
  3. Learning spectral methods by transformers
    Yihan He, Yuan Cao, Hong-Yu Chen, Dennis Wu, Jianqing Fan, and Han Liu
    arXiv preprint arXiv:2501.01312, 21–27 jul 2025
    arXiv