avatar

Ilgee Hong

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


About Me

Hello! I am a third-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 primarily focuses on post-training methods for LLMs. I develop training and inference frameworks to improve their diverse capabilities, such as reasoning, instruction following, and multi-agent collaboration, especially through reinforcement learning.

Experience

Publications

(* – authors alphabetically ordered; † – equal contribution)
  1. Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training
    Ran Xu†, Tianci Liu†, Zihan Dong, Tony You, Ilgee Hong, Carl Yang, Linjun Zhang, Tao Zhao, Haoyu Wang
    Preprint
    PDF
  2. OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment
    Tianci Liu†, Ran Xu†, Tony Yu, Ilgee Hong, Carl Yang, Tuo Zhao, Haoyu Wang
    Preprint
    PDF
  3. Ask a Strong LLM Judge when Your Reward Model is Uncertain
    Zhenghao Xu, Qin Lu, Qingru Zhang, Liang Qiu, Ilgee Hong, Changlong Yu, Wenlin Yao, Yao Liu, Haoming Jiang, Lihong Li, Hyokun Yun, Tuo Zhao
    NeurIPS 2025
    PDF Code
  4. Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models
    Ilgee Hong, Changlong Yu, Liang Qiu, Weixiang Yan, Zhenghao Xu, Haoming Jiang, Qingru Zhang, Qin Lu, Xin Liu, Chao Zhang, Tuo Zhao
    NeurIPS 2025
    PDF Code
  5. SlimMoE: Structured Compression of Large MoE Models via Expert Slimming and Distillation
    Zichong Li, Chen Liang, Zixuan Zhang, Ilgee Hong, Young Jin Kim, Weizhu Chen, Tuo Zhao
    COLM 2025
    PDF Code
  6. Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only
    Qingru Zhang, Liang Qiu, Ilgee Hong, Zhenghao Xu, Tianyi Liu, Shiyang Li, Rongzhi Zhang, Zheng Li, Lihong Li, Bing Yin, Chao Zhang, Jianshu Chen, Haoming Jiang, Tuo Zhao
    COLM 2025
    PDF Code
  7. Discriminative Finetuning of Generative Large Language Models without Reward Models and Preference Data
    Siqi Guo, Ilgee Hong, Vicente Balmaseda, Changlong Yu, Liang Qiu, Xin Liu, Haoming Jiang, Tuo Zhao, Tianbao Yang
    ICML 2025
    PDF Code
  8. Robust Reinforcement Learning from Corrupted Human Feedback
    Alexander Bukharin*, Ilgee Hong*, Haoming Jiang*, Zichong Li*, Qingru Zhang*, Zixuan Zhang*, Tuo Zhao*
    NeurIPS 2024
    PDF Code
  9. 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
  10. 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
  11. Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching
    Ilgee Hong†, Sen Na†, Michael W. Mahoney, Mladen Kolar
    ICML 2023
    PDF Code
  12. A Simplified Framework for Contrastive Learning for Node Representations
    Ilgee Hong, Huy Tran, Claire Donnat
    ACSSC 2023
    PDF Code