Seokwon Song

Logo

Ph.D. Student @ SNU


GitHub Google Scholar LinkedIn

I’m a Ph.D. student in the Interdisciplinary Program in Artificial Intelligence at Seoul National University, advised by Prof. Gunhee Kim in the Vision and Learning Lab.

I’m interested in Natural Language Processing (NLP) and Multimodal Large Language Models (MLLMs), with a long-term goal of developing autonomous AI agents that can collaboratively discover new knowledge alongside humans.

I’m currently working on:

  • Large vision-language models
  • Multimodal retrieval-augmented generation
  • Open-ended question answering

  • Education

    Seoul National University Mar 2024-Present
  • Combined M.S. / Ph.D. of Interdisciplinary Program in Artificial Intelligence
  • Korea University Mar 2018-Feb 2024
  • B.S. in Computer Science and Engineering

  • Publication (* equal contribution)

    MAVIS: A Benchmark for Multimodal Source Attribution in Long-form Visual Question Answering
    Seokwon Song, Minsu Park, Gunhee Kim
    AAAI 2026

    Is a Peeled Apple Still Red? Evaluating LLMs' Ability for Conceptual Combination with Property Type
    Seokwon Song*, Taehyun Lee*, Jaewoo Ahn, Jae Hyuk Sung, Gunhee Kim
    NAACL 2025 (Oral)

    Read-only Prompt Optimization for Vision-Language Few-shot Learning
    Dongjun Lee*, Seokwon Song*, Jehee Suh, Junmyeong Choi, Sanghyeok Lee, Hyunwoo J. Kim
    ICCV 2023


    Research Experience

    Vision and Learning Lab, SNU Oct 2023–Present
    Advised by Prof. Gunhee Kim

    Language Lab, LG AI Research Jan 2023–Sep 2023
    Mentored by Hyunkyung Bae

    Machine Learning & Vision Lab, Korea University May 2022–Dec 2022
    Advised by Prof. Hyunwoo J. Kim


    Work Experience

    LG AI Research Feb 2026–Present (Upcoming)
    NLP Research Internship

    LG AI Research Jan 2023–Sep 2023
    Software Engineering Internship at Language Lab