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.
Hi, I’m a second-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 their theoretical foundations, including their universal approximation capabilities, potential to perform complex algorithms, and their links to associative memory such as Hopfield Model. I also work on extending their applications beyond language and vision, particularly in time series analysis and other scientific domain such as astrophysics. I received my B.S. degree in Physics from National Taiwan University, advised by Prof. Hsi-Sheng Goan.
news
| Sep 29, 2026 | One paper accepted to NeurIPS 2026 on precision-aware Hopfield retrieval. |
|---|---|
| Jul 11, 2026 | StarEmbed received the Outstanding Paper Award at the AI4Physics Workshop at ICML 2026. |
| Jul 03, 2026 | StarEmbed selected for an oral presentation at the AI4Physics Workshop at ICML 2026. |
| Apr 30, 2026 | Four papers accepted to ICML 2026: universal approximation of softmax attention, universality and function composition of in-context learning, theoretical advantage of chain-of-thought, and a benchmark for astronomical time series. |
| Mar 20, 2026 | Honored to receive the Lambda Research Grant. |
selected publications
* denotes equal contribution.
- In-Context Universal Approximation, Compositional Generalization, and Algorithm Emulation
- Chain-of-Thought Gradient Descent
- StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars
