Publications

* equal contribution, random order. Also on Google Scholar.

2026

  • Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Models

    Seo Hyun Kim*, Sunwoo Hong*, Younwoo Choi, Chen-Hao Chao, Se-Young Yun, Rahul G. Krishnan

    EMNLP 2026, Main Conference. Oral presentation

    Project

  • Logical Equivariance in Diffusion Language Models

    Sunwoo Hong*, Seo Hyun Kim*, Chen-Hao Chao, Younwoo Choi, Se-Young Yun, Rahul G. Krishnan

    Under review. Earlier version at the ICML 2026 Workshop on Foundations of Deep Generative Models.

    OpenReview

  • Route-Guided CBF-QP Repair for Safe Vision-Language-Action Models

    Chan Park, Sunwoo Hong, Kirak Kim, Yoonjeong Park, Alexander W. Olson, Ali Pesaranghader

    RSS 2026 Workshop on Trustworthy Embodied Foundation Models.

    PDF Project Code

  • Do World Models Need Clocks? Next-Event State Prediction for Physical Planning

    Sunwoo Hong

    In preparation.

2025

  • KLASS: KL-Guided Fast Inference in Masked Diffusion Models

    Seo Hyun Kim*, Sunwoo Hong*, Hojung Jung, Youngrok Park, Se-Young Yun

    NeurIPS 2025. Spotlight, top 3.2%

    arXiv Code

  • Memory Reduction via Ternary Quantization in Reinforcement Learning

    Sunwoo Hong, Y. Kim, S. Jung, J. Oh, Se-Young Yun

    Korea Institute of Military Science and Technology (KIMST) Conference, 2025.