avatar

Yenho Chen

Machine Learning Ph.D. Candidate
Georgia Institute of Technology
yenho@gatech.edu


About Me

I am a Machine Learning Ph.D. Candidate at Georgia Tech, advised by Dr. Christopher Rozell. My thesis focuses on improving self-supervised learning for health time-series using mathematical tools from dynamical systems theory. I have developed methods for low-data settings, where we care more about interpretability, and for large-scale single- and multi-sensor data, where we care more about scalability.

Outside of my PhD, I have worked on a range of research problems through industry internships. At IBM Research, I developed SSL methods to discover new CAR-T protein sequences with improved cytotoxicity. At Blackstone Real Estate, I designed new dropout techniques to produce more robust hotel demand forecasts. At Travelers, I investigated domain reweighting strategies for continued pretraining of LLMs.

Prior to my PhD, I was a research fellow in the Machine Learning Team at the National Institute of Mental Health, where I built statistical tools for neural signal analysis.

Research Interests

News

  • [May 2026] Recognized as Gold Reviewer for ICML 2026 🌟!
  • [May 2026] Returning to IBM Research in San Jose, California for internship.
  • [Apr. 2026] Our paper on PULSE, a new SSL approach for health signals based on dynamical systems theory, has been accepted at ICML.
  • [Oct. 2025] Recognized as a Top Reviewer for NeurIPS 2025 🙌!
  • [May 2025] Starting a research internship at IBM Research in San Jose, California.
  • [Mar. 2025] MANGO has been accepted at SampTA as Oral presentation 🥭!
  • [Dec. 2024] Our paper on probabilistic dLDS for robust tracking of sparse coded dynamics has been accepted at NeurIPS.
  • [May 2024] Started a research internship at Blackstone Real Estate in New York City, New York.
  • [Jan. 2024] Starting a applied LLM internship at Travelers Insurance Inc. in Atlanta, Georgia.
  • [Dec 2023] Received my M.S. in Computer Science from Georgia Tech.
  • [Aug. 2023] Our paper on decomposed linear dynamical systems (dLDS) has been accepted at JMLR!.
  • [Aug. 2021] Started PhD in Machine Learning at Georgia Tech 🐝.

Publications

  1. ICML
    Self-Supervised Dynamical System Representations for Physiological Time-Series
    Yenho Chen*, Maxwell A. Xu, James M. Rehg, Christopher J. Rozell
    International Conference on Machine Learning (ICML), 2026.
    Accepted

  2. SampTA
    MANGO: Learning Disentangled Image Transformation Manifolds with Grouped Operators
    Brighton Ancelin*, Yenho Chen*, Alex Saad-Falcon, Peimeng Guan, Chiraag Kaushik, Nakul Singh, and Belen Martin-Urcelay
    Sampling Theory and Applications (SampTA), 2025.
    PDF Oral

  3. NeurIPS
    Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics
    Yenho Chen*, Noga Mudrik, Kyle A. Johnsen, Sankaraleengam Alagapan, Adam S. Charles, Christopher J. Rozell
    Neural Information Processing Systems (NeurIPS), 2024.
    PDF

  4. JMLR
    Decomposed Linear Dynamical Systems (dLDS) for learning the latent components of neural dynamics
    Noga Mudrik*, Yenho Chen*, Eva Yezerets, Christopher J. Rozell, Adam S. Charles
    Journal of Machine Learning Research (JMLR), 2024.
    PDF Code

Reviewer Service