News

May. 2026New preprint on universal retrieval across heterogeneous knowledge sources is out on arXiv. 🔥
May. 2026New preprint on self-distillation for contextual integrity is out on arXiv. 🔥
May. 2026New preprint on self-distillation for long-horizon agents is out on arXiv. 🔥
Apr. 2026WorldMM is selected as a highlight presentation at CVPR 2026! ✨
Apr. 2026UniversalRAG is accepted to ACL 2026 as an oral presentation! 🇺🇸
Mar. 2026New preprint on multi-agent egocentric video QA benchmark is out on arXiv. 🔥
Feb. 2026WorldMM is accepted to CVPR 2026! 🇺🇸
Jan. 2026I gave a talk on multimodal memory agent at TwelveLabs. 🎙️
Sep. 2025Joined MLAI Lab at KAIST as a master’s student. 👨🏻‍🎓
Feb. 2025VideoICL is accepted to CVPR 2025! 🎉

Selected Publications

  1. It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs
    Sangwoo Park*, Woongyeong Yeo*, Seanie Lee, Yumin Choi, Hyomin Lee, Kangsan Kim, Jinheon Baek, Seong Joon Oh, Sung Ju Hwang
    arXiv preprint, 2026
  2. WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning
    Woongyeong Yeo*, Kangsan Kim*, Jaehong Yoon, Sung Ju Hwang
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026 (Highlight)
  3. UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities
    Woongyeong Yeo*, Kangsan Kim*, Soyeong Jeong, Jinheon Baek, Sung Ju Hwang
    Annual Meeting of the Association for Computational Linguistics (ACL), 2026 (Oral)