Jindan Li
|
Ph.D. student Email: jl4767@cornell.edu 2 W Loop Rd, New York, NY 10044 |
About me
I am currently a Ph.D. student at Cornell University, and am fortunately advised by Prof. Tianyi Chen. From Sep 2024 to Aug 2025, I worked as a Research Assistant at RPI ECSE with Prof. Chen. In Spring 2025, I also served as a Teaching Assistant for the undergraduate course ECSE 2500 – Engineering Probability at RPI. I received my B.Eng. in Information Engineering from Zhejiang University in July 2024.
Research
Research interests: Physical neural networks, analog learning systems, robust training on non-ideal hardware, and wireless communication.
My research focuses on physical learning: how to train neural networks directly on analog hardware despite limited precision, asymmetric updates, and other device non-idealities. Rather than treating hardware imperfections as an afterthought, I design training algorithms that work with the underlying device physics and enable reliable on-chip learning.
One platform I study is analog hardware based on resistive device arrays, where weights are stored as physical conductance states and updated directly on-chip. My recent work proposes a multi-tile residual learning framework that represents each weight across multiple physical tiles with geometric scaling, improving effective precision and robustness under low-state, asymmetric device behavior.
News
Our paper has been accepted to AISTATS 2026. The full paper is available on arXiv, and the implementation and experimental results are available in my code repository: github.com/Jindanli898/AIMC.
Education
- Cornell University, New York, NY, USA — Ph.D., Electrical and Computer Engineering, Aug 2025 – Present
- Rensselaer Polytechnic Institute, Troy, NY, USA — Research Assistant (RA), Sep 2024 – Aug 2025
- Zhejiang University, Hangzhou, China — B.Eng., Information Engineering, 2020 – 2024