Hongkang Li’s Homepage
Biography
I am a postdoctoral researcher of Department of Electrical and Systems Engineering at the University of Pennsylvania. My advisor is Prof. Rene Vidal. Previously, I received my PhD degree from the Department of Electrical, Computer, and Systems Engineering of Rensselaer Polytechnic Institute in 2024. My advisor is Prof. Meng Wang. I received my Bachelor’s degree from the Department of Electronic Engineering and Information Science at the University of Science and Technology of China in 2019. Here is my CV.
My research area is machine learning and deep learning theory. My research interests include
- Generalization and optimization theory of Transformer-based foundation models.
- Theoretical parameter-efficient fine-tuning.
- Graph neural network and its theory.
Contact: lihk@seas.upenn.edu, lohek330@gmail.com.
Recent News 🔥
2025.06: ❤️ I completed my six great years at RPI and have joined the University of Pennsylvania as a postdoctoral researcher 🚀.
2025.05: 😺 Our paper Theoretical Learning Performance of Graph Networks: the Impact of Jumping Connections and Layer-wise Sparsification is accepted by TMLR.
2025.05: ⭐ I am honored to be recognized as an ICLR 2025 Notable Reviewer.
2025.03: ⭐ I am awarded the MLCommons ML and Systems Rising Star Award. Only 38 of over 150 applicants were accepted.
2025.02: 🚀 Our paper When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers is selected as an oral presentation at ICLR 2025 (acceptance rate = 1.8%).
2025.01: 😺 😺 😺 Three papers, including two first-author works, were accepted in ICLR 2025: ⭐ Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis, ⭐ When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers, and ⭐ Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning.
2024.11: I have passed my doctoral dissertation exam! 🎓
2024.09: 😺 One paper accepted by Neurips 2024.
2024.07: I presented two works at IEEE SAM Workshop held at Oregon State University, US.
2024.06: One paper accepted by ICML 2024 TF2M Workshop and HiLD Workshop.
2024.05: 😺 😺 Two papers accepted by ICML 2024. One is on In-Context Learning. Another is on Graph Transformers.
2024.03: 😺 One paper on learning with group imbalance accepted by IEEE Journal of Selected Topics in Signal Processing.
2023.10: One paper accepted by Neurips 2023 GLFrontiers Workshop.
2023.10: One paper accepted by Neurips 2023 M3L Workshop.
2023.09: ⭐ I received Rensselaer’s Founders Award of Excellence.
2023.09: One paper accepted by Neurips 2023.
2023.05: I will join IBM Research as a research intern this summer, under the supervision of Dr. Songtao Lu, Dr. Hui Wan, and Dr. Xiaodong Cui.