CV
This is a description of the page. You can modify it in '_pages/cv.md'. You can also change or remove the top pdf download button.
Contact Information
| Name | JunHyeok Oh |
| Professional Title | Reinforcement Learning Researcher |
| the2ndlaw@korea.ac.kr |
Professional Summary
Researcher at Korea University working on reinforcement learning, including offline RL, diffusion planning, and multi-agent RL.
Education
-
2025 - Seoul, Korea
-
2020 - 2024 Cheongju, Korea
B.S.
Korea National University of Education
Mathematics Education
Publications
-
2026 TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning
International Conference on Machine Learning (ICML)
* Equal contribution (co-first author).
-
2025 Prior-Guided Diffusion Planning for Offline Reinforcement Learning
Conference on Neural Information Processing Systems (NeurIPS)
-
2025 -
2025 Iterative Prompt Refinement for Safer Text-to-Image Generation
Conference on Empirical Methods in Natural Language Processing (EMNLP)
* Equal contribution (co-first author).
-
2025
Awards
-
2022 3rd Place (Encouragement Award), Han River Water Level Prediction AI Competition for Paldang Dam Flood Safety Operation
Korea Hydro & Nuclear Power (KHNP)
Skills
Research Interests: Reinforcement Learning, Offline RL, Diffusion Planning, Multi-Agent RL, LLM Alignment