Scholar
Hongkang Li
Google Scholar ID: DVlDPjMAAAAJ
University of Pennsylvania
Citations & Impact
Citations
392
H-index
11
i10-index
13
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- - 2025.10: Selected as the Top Reviewer of Neurips 2025
- - 2025.10: One paper accepted by Neurips 2025
- - 2025.05: Paper “Theoretical Learning Performance of Graph Networks: the Impact of Jumping Connections and Layer-wise Sparsification” accepted by TMLR
- - 2025.05: Recognized as an ICLR 2025 Notable Reviewer
- - 2025.03: Awarded the MLCommons ML and Systems Rising Star Award
- - 2025.02: Paper “When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers” selected as an oral presentation at ICLR 2025 (acceptance rate = 1.8%)
- - 2025.01: Three papers, including two first-author papers, accepted in ICLR 2025
- - 2024.11: Passed doctoral dissertation exam
- - 2024.10: Invited talk titled “Theoretical Foundations of In-Context Learning and Chain-of-Thought Using Properly Trained Transformer Models” at NJIT
- - 2024.09: One paper accepted by Neurips 2024
- - 2024.07: 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
- - 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: Received Rensselaer’s Founders Award of Excellence
- - 2023.09: One paper accepted by Neurips 2023
Research Experience
- - 2025.10: Guest lecture at the Machine Learning course of UCF
- - 2025.10: Serving as the Area Chair of CPAL 2026
- - 2025.10: Invited talk titled “Theoretical Perspectives of Efficient Learning for Large Foundation Models” at Illinois Tech
- - 2025.06: Joined the University of Pennsylvania as a postdoctoral researcher
- - 2025.05: Research intern at IBM Research, supervised by Dr. Songtao Lu, Dr. Hui Wan, and Dr. Xiaodong Cui
Education
- - Ph.D.: 2024, Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, Advisor: Prof. Meng Wang
- - B.S.: 2019, Department of Electronic Engineering and Information Science, University of Science and Technology of China
Background
- - Research Area: Machine learning and deep learning theory
- - Research Interests: Generalization and optimization theory of Transformer-based foundation models, Theoretical parameter-efficient fine-tuning, Graph neural network and its theory
Miscellany
- - Contact: lihk@seas.upenn.edu, lohek330@gmail.com
Co-authors