About me

Hello!👋 I'm Hayeong Lee, a Ph.D. student in the Department of Artificial Intelligence at Korea University, South Korea. As a member of the Decision Making Lab, led by Professor Byung-Jun Lee, I focus on Deep Reinforcement Learning and its applications.

🎯 My current research focuses on the generalization capabilities of AI, specifically tackling the challenges posed by complex, realistic, and multi-agent environments.

Feel free to connect with me on Google Scholar, Github or LinkedIn if you have any questions or are interested in collaborating! 😸

Curriculum Vitae

Interests

Multi-Agent Reinforcement Learning, Reinforcement Learning, World Model, Zero-shot Generalization

Publications

*Equal contribution, †: co-corresponding author

• TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning, Hayeong Lee*, JunHyeok Oh*, Byung-Jun Lee, The Forty-Third International Conference on Machine Learning (ICML), 2026 (Paper, Github, Project Page)

• GraphMind: LLMs as Dynamic Knowledge Builders for Sequential Decision-Making, Sunguk Shin*, Hayeong Lee*, Jun Ho Seo*, Jinho Lee, Myunsoo Kim, Minsuk Chang, Byung-Jun Lee, Findings of the Association for Computational Linguistics: ACL, 2026 (Paper, Github)

• Evaluating LLM Planning in Partially Observable Environments via Observation Representations and Action Sequences, Hayeong Lee*, Jun Ho Seo*, Sunguk Shin*, Jinho Lee, Myunsoo Kim, Minsuk Chang, Byung-Jun Lee, NeurIPS LAW Workshop: Bridging Language, Agent, and World Models, 2025 (Paper, Github)

• Iterative Prompt Refinement for Safer Text-to-Image Generation, Jinwoo Jeon*, JunHyeok Oh*, Hayeong Lee, Byung-Jun Lee, Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025 (Paper, Github)

• NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations, Myunsoo Kim*, Hayeong Lee*, Seong-Woong Shim, JunHo Seo, Byun-Jun Lee, The Forty-Second International Conference on Machine Learning (ICML), 2025, (Paper, Github)

• ROIDICE: Offline Return on Investment Maximization for Efficient Decision Making, Woosung Kim*, Hayeong Lee*, Jongmin Lee†, Byung-Jun Lee†, The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024, (Paper, Github)

Education

• Korea University - Mar.2023 ~ (present) Integrated M.S. & Ph.D. course of Department of Artificial Intelligence

• Hanyang University ERICA - Mar.2017 ~ Aug.2021

  Bachelor of Science in Computer Science and Engineering (GPA: 4.25 / 4.5)

Awards

• Silver Reviewer Award, 2026 by ICML 2026

• 2022 OpenSource Contribution Academy, 2022 by MSIT & nipa 과학기술정보통신부장관상 First prize (reward: 3,000,000 won)

• AI Voice Data Contest, 2020 by SOLUGATE & KORAIA

  Nationwide, First prize (reward: 5,000,000 won)

• Open Infra Development Competition, 2019 by ManTech

  Nationwide, Bronze prize (reward: 500,000 won) (link)

Scholarship

• National Science and Engineering Undergraduate Scholarship, 2019, KOSAF

  Scholarship supports undergraduates with strong academic performance in science and engineering, with the purpose of developing future leaders in those fields

• Haksan scholarship, 2018, Haksan Foundation

Experience

• DMLab, Korea University - Mar.2023 ~ present Integrated M.S. & Ph.D. student in Korea University (Seoul Korea)

• VMLab, Hanyang University - Mar.2020 ~ Jun.2021

  Undergraduate student intern in Hanyang University (Ansan Korea)

  • Matched feature points in kinect images which are found with SIFT

  • Estimated ground truth of kinect images with BTS (PyTorch)

    From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation

Language

• Korean (Native), English (Intermediate), French (Beginner)