Sangkyu Lee

prof_pic.jpg

I am a research scientist intern at the Artificial Intelligence and Robotics Institute in KIST. I previously researched at LG AI ResearchNaver Cloud and maumAI. I received an M.S. in Artificial Intelligence from Yonsei University under the supervision of Youngjae Yu and Jongmin Lee, and a B.A. in Applied Statistics and a B.S. in Computer Science & Engineering from Yonsei University. My research aims to enable end-to-end continual multimodal learning for accumulating knowledge from real-world embodied experience without human supervision. I strive to achieve this goal by a scalable yet simple approach. I am currently interested in multimodal generative models, AI alignment (specifically for Robotics), long-term memory, and continual learning.

Looking for Ph.D. programs, and feel free to contact me for collaborations!

News

Jun 18, 2026 Our paper, Spanning Tree Autoregressive Visual Generation is accepted at ECCV 2026.
Jun 11, 2026 Our new preprint, Real-Time Execution with Autoregressive Policies, is released.
Nov 24, 2025 Check out our new preprint, Spanning Tree Autoregressive Visual Generation.
Sep 18, 2025 Our paper is accepted at NeurIPS 2025.
Sep 01, 2025 I am starting a research scientist internship at the Artificial Intelligence and Robotics Institute in KIST.

Publications

  1. realfast.png
    Real-Time Execution with Autoregressive Policies
    Sangkyu Lee, Seohyeon Park, Tackgeun You, and 4 more authors
    arXiv preprint, 2026
  2. ECCV 2026
    star.png
    Spanning Tree Autoregressive Visual Generation
    Sangkyu Lee*, Changho Lee, Janghoon Han, and 6 more authors
    ECCV 2026, 2026
  3. NeurIPS 2025
    e-dpo.png
    KL Penalty Control via Perturbation for Direct Preference Optimization
    Sangkyu Lee*, Janghoon Han, Hosung Song, and 3 more authors
    Advances in Neural Information Processing Systems, 2026
  4. ACL 2025
    venus.png
    Speaking Beyond Language: A Large-Scale Multimodal Dataset for Learning Nonverbal Cues from Video-Grounded Dialogues
    Youngmin Kim*, Jiwan Chung*, Jisoo Kim, and 5 more authors
    Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025
  5. seal.png
    SEAL: Entangled White-box Watermarks on Low-Rank Adaptation
    Giyeong Oh, Saejin Kim, Woohyun Cho, and 4 more authors
    arXiv Preprint, 2025
  6. AAAI 2025
    mass.png
    MASS: Overcoming Language Bias in Image-Text Matching
    Jiwan Chung, Seungwon Lim, Sangkyu Lee, and 1 more author
    Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence, 2025
  7. hyperclova_x.jpeg
    HyperCLOVA X Technical Report
    HyperCLOVA X Team
    Technical Report, 2024
  8. ACL 2024
    self_judge.png
    Aligning Large Language Models by On-Policy Self-Judgment
    Sangkyu Lee*, Sungdong Kim, Ashkan Yousefpour, and 3 more authors
    Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024