Hamin Koo

hamin_temp__.png

Hello! I am a Master student in AI at Yonsei University, advised by Prof. Jaehyung Kim in the Machine and Language Learning Lab (ML3).

I’m interested in understanding and controlling how large language models (LLMs) behave in practice. In particular, I study emergent behaviors such as systematic biases, robustness issues, and other unintended patterns. My work focuses on building structured and data-driven methods to analyze and improve the reliability of these models across different settings.

News

Jan 26, 2026 AMIS is accepted to ICLR 2026! See you in Lio 🇧🇷
May 07, 2025 Our new preprint EMCEE is out!

Publications

2026

  1. Jailbreak, Optimization
    amis_figure.png
    Align to Misalign: Automatic LLM Jailbreak with Meta-Optimized LLM Judges
    Hamin Koo, Minseon Kim, and Jaehyung Kim
    International Conference on Learning Representations (ICLR), 2026
    PDF Code

2025

  1. Multilingual
    emcee_figure.png
    Extracting and Emulsifying Cultural Explanation to Improve Multilingual Capability of LLMs
    Hamin Koo and Jaehyung Kim
    Preprint, 2025
    PDF Code

2024

  1. RAG, Optimization
    qoqa_figure.png
    Optimizing Query Generation for Enhanced Document Retrieval in RAG
    Hamin Koo, Minseon Kim, and Sungju Hwang
    Preprint, 2024
    PDF