Eunhwan Park

박은환 · 朴殷煥

I am an incoming Ph.D. student in Computer Science at Korea University. I received my M.S. in Computer Science from Jeonbuk National University, advised by Seung-Hoon Na, and my B.S. in Computer Science from Kookmin University.

Eunhwan Park

Education

  • Korea University
    Incoming Ph.D. Student in Computer Science
  • Jeonbuk National University
    M.S. in Computer Science
    Supervisor: Seung-Hoon Na
  • Kookmin University
    B.S. in Computer Science

Experience

  • Moreh / Motif Technologies
    AI Research Engineer
    Motif Technologies is a subsidiary of Moreh.
  • Buzzni
    AI Research Engineer
  • Naver
    Internship
  • Software Maestro 6th
    Mentee

Research

I am interested in mechanistic understanding of neural networks, agentic AI, and foundation models. My recent work focuses on targeted neuron manipulation, short- and long-term memory augmentation for agents, and the full pipeline from pre-training to post-training.

Selected Publications

* Equal contribution · † Corresponding author

  1. Ask, Assess, and Refine: Rectifying Factual Consistency and Hallucination in LLMs with Metric-Guided Feedback Learning

    Dongyub Lee*, Eunhwan Park*, Hodong Lee, Heuiseok Lim†

    Proceedings of EACL 2024 · pdf

  2. MERLIN: Multimodal Embedding Refinement via LLM-based Iterative Navigation for Text-Video Retrieval-Rerank Pipeline

    Donghoon Han*, Eunhwan Park*, Gisang Lee*, Adam Lee, Nojun Kwak†

    EMNLP 2024 Industry Track · pdf

  3. SISER: Semantic-Infused Selective Graph Reasoning for Fact Verification

    Eunhwan Park*, Jong-Hyeon Lee*, Donghyeon Jeon, Seonhoon Kim, Inho Kang, Seung-Hoon Na†

    Proceedings of COLING 2022 · pdf

  4. Unleash the Potential of CLIP for Video Highlight Detection

    Donghoon Han*, Seunghyeon Seo*, Eunhwan Park, Seong-Uk Nam, Nojun Kwak†

    arXiv Preprint · pdf

  5. MAFiD: Moving Average Equipped Fusion-in-Decoder for Question Answering over Tabular and Textual Data

    Sung-Min Lee, Eunhwan Park, Daeryong Seo, Donghyeon Jeon, Inho Kang, Seung-Hoon Na†

    Proceedings of EACL Findings 2023 · pdf

Professional Service