Kwanhee Lee

bassist_kwan.JPG

Hi, I’m a second-year Master’s student at Graduate School of Artificial Intelligence, POSTECH, advised by Prof. Namhoon Lee

I design optimization algorithms for scalable and robust compression of large language models, aiming to make them efficient and usable for everyone.

If you have any questions or want to collaborate with me, feel free to reach me via kwanhee.lee@postech.ac.kr

news

Jan 26, 2026 Our paper on extreme LLM sparsity has been accepted to ICLR 2026!
Jan 05, 2026 Our paper SAFE won the Best Paper Award at POSTECH-GSAI BK21 2025!
Nov 17, 2025 Our new paper on extreme LLM sparsity won Best Paper Award at JKAIA 2025!
Aug 02, 2025 Our paper on dynamic network pruning has been accepted to Neural Networks (Q1, SCI)!
Jun 10, 2025 Will be attending ICML 2025 in person! See you in Vancouver :D

selected publications

  1. The Unseen Frontier: Pushing the Limits of LLM Sparsity with Surrogate-Free ADMM
    Kwanhee Lee, Hyeondo Jang, Dongyeop Lee, and 2 more authors
    In ICLR, 2026
    Best Paper Award @ JKAIA 2025
    arXiv
  2. SAFE: Finding Sparse and Flat Minima to Improve Pruning
    Dongyeop Lee, Kwanhee Lee, Jinseok Chung, and 1 more author
    In ICML, 2025
    spotlight(top 2.6%) poster
    arXiv Code
  3. Dynamic Network Compression via Probabilistic Channel Pruning
    Kwanhee Lee, and Hyang-Won Lee
    Neural Networks, 2026