Jindan Li

About Me

I am a Ph.D. student at Cornell University, advised by Prof. Tianyi Chen. I received my B.Eng. in Information Engineering from Zhejiang University in July 2024.

Research

My research interests include physical neural networks and analog learning systems, robust training and parameter-efficient LLM adaptation on non-ideal hardware, and reinforcement learning for wireless network optimization.

Publications

1. Robust Parameter-Efficient LLM Adaptation on Analog Hardware

   Jindan Li, Zhaoxian Wu, Tianyi Chen

   NeurIPS 2026 Workshop on On-Device Intelligence: Foundation Models under Real-World Constraints

   PDF · arXiv

2. METRO: MAP-Enhanced Twin Rollouts for Reinforcement Learning-Based Coverage and Capacity Optimization

   Jindan Li, Samuel Albert, Yan Xin, Jianzhong Zhang, Tianyi Chen

   ACM MobiHoc 2026 AI-RAN Workshop

   PDF

3. Dynamic Symmetric Point Tracking: Tackling Non-ideal Reference in Analog In-memory Training

   Quan Xiao^*, Jindan Li^*, Zhaoxian Wu, Tayfun Gokmen, Tianyi Chen

   International Conference on Machine Learning (ICML 2026)

   PDF · arXiv

4. In-memory Training on Analog Devices with Limited Conductance States via Multi-tile Residual Learning

   Jindan Li, Zhaoxian Wu, Gaowen Liu, Tayfun Gokmen, Tianyi Chen

   International Conference on Artificial Intelligence and Statistics (AISTATS 2026)

   Proceedings · arXiv · Code

^* Equal contribution.

Experience

Education