avatar

Ilgee Hong

PhD Student
Georgia Institute of Technology
ihong39 (at) gatech.edu


About Me

Hello! I am a second-year Ph.D. student in Machine Learning at Georgia Institute of Technology, where I am advised by Prof. Tuo Zhao. Before attending GT, I received my M.S. degree in Statistics from the University of Chicago in 2023, where I was advised by Prof. Claire Donnat and Prof. Mladen Kolar. Prior to UChicago, I received my bachelor’s degree in Statistics at Yonsei University. At Yonsei, I was advised by Prof. Sangun Park.

Research Interests

My research focuses on post-training methods for large language models (LLMs). Specifically, I am developing methodologies to improve instruction following, reasoning, and coding abilities by:

  1. training LLMs with reinforcement learning (RL), and
  2. reducing reliance on costly supervision and data.

Experience

Publications

(* – authors alphabetically ordered; † – equal contribution)
  1. Robust Reinforcement Learning from Corrupted Human Feedback
    Alexander Bukharin*, Ilgee Hong*, Haoming Jiang*, Zichong Li*, Qingru Zhang*, Zixuan Zhang*, Tuo Zhao*
    NeurIPS 2024
    PDF
  2. Adaptive Preference Scaling for Reinforcement Learning with Human Feedback
    Ilgee Hong†, Zichong Li†, Alexander Bukharin, Yixiao Li, Haoming Jiang, Tianbao Yang, Tuo Zhao
    NeurIPS 2024
    PDF Code
  3. Who Wrote this Code? Watermarking for Code Generation
    Taehyun Lee†, Seokhee Hong†, Jaewoo Ahn, Ilgee Hong, Hwaran Lee, Sangdoo Yun, Jamin Shin, Gunhee Kim
    ACL 2024
    PDF Code
  4. Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching
    Ilgee Hong†, Sen Na†, Michael W. Mahoney, Mladen Kolar
    ICML 2023
    PDF Code
  5. A Simplified Framework for Contrastive Learning for Node Representations
    Ilgee Hong, Huy Tran, Claire Donnat
    ACSSC 2023
    PDF Code