JunHyeok Oh

Dept. of Artificial Intelligence

Korea University, Seoul

the2ndlaw [at] korea.ac.kr

I am an Integrated M.S./Ph.D. student in the Department of Artificial Intelligence at Korea University, advised by Prof. Byung-Jun Lee. My research centers on reinforcement learning — including offline RL, diffusion-based planning, and multi-agent RL — as well as preference optimization and safety for large generative models.

Feel free to reach out by email. You can also find my work on Google Scholar and GitHub.

selected publications

ICML

TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning

Hayeong Lee^*, JunHyeok Oh^*, and Byung-Jun Lee

In International Conference on Machine Learning (ICML), 2026

* Equal contribution

arXiv Bib

@inproceedings{oh2026tabx,
  title = {TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning},
  author = {Lee, Hayeong and Oh, JunHyeok and Lee, Byung-Jun},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  note = {* Equal contribution},
}

EMNLP

Iterative Prompt Refinement for Safer Text-to-Image Generation

Jinwoo Jeon^*, JunHyeok Oh^*, Hayeong Lee, and 1 more author

In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025

* Equal contribution

arXiv Bib Code

@inproceedings{jeon2025iterative,
  title = {Iterative Prompt Refinement for Safer Text-to-Image Generation},
  author = {Jeon, Jinwoo and Oh, JunHyeok and Lee, Hayeong and Lee, Byung-Jun},
  booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year = {2025},
  note = {* Equal contribution},
}