publications

(*) denotes equal contribution, (‡) denotes equal advising.

2026

  1. Coarse-to-Fine Compositional Diffusion for Long-Horizon Planning
    Byoungwoo Park, Utkarsh A. Mishra, Jaemoo Choi, Juho Lee, and Yongxin Chen
    Preprint
    PDF Code Page
  2. Warehouse.png
    Function-Space Diffusion for Motion Planning
    Zinuo Chang, Yipu Chen, Byoungwoo Park, Hongzhe Yu, and Yongxin Chen
    Preprint
    PDF
  3. chignolin_fold.gif
    Functional Adjoint Sampler: Scalable Sampling on Infinite Dimensional Spaces
    Byoungwoo Park, Juho Lee, and Guan-Horng Liu
    International Conference on Machine Learning (ICML), 2026
    NeurIPS 2025 Workshop on Frontiers in Probabilistic Inference
    PDF Code
  4. brain.png
    Stochastic Optimal Control for Continuous-Time fMRI Representation Learning
    Joonhyeong Park*, Byoungwoo Park*, Chang-Bae Bang, Jungwon Choi, Hyungjin Chung, Byung-Hoon Kim‡, and Juho Lee‡
    International Conference on Learning Representations (ICLR), 2026
    PDF

2025

  1. smc.png
    Improving Constrained Language Generation via Self-Distilled Twisted Sequential Monte Carlo
    Sooyeon Kim, Giung Nam, Byoungwoo Park, and Juho Lee
    NeurIPS 2025 Workshop on Frontiers in Probabilistic Inference
    PDF
  2. petal.gif
    Multi-Marginal Schrödinger Bridge Matching
    Byoungwoo Park, and Juho Lee
    Preprint
    PDF Code
  3. concept_thumbnail.jpeg
    Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Series
    Byoungwoo Park, Hyungi Lee, and Juho Lee
    International Conference on Learning Representations (ICLR), 2025
    Oral Presentation at ICLR 2025 [Top 1.8%]
    NeurIPS 2024 Workshop on Bayesian Decision-making and Uncertainty
    PDF Code

2024

  1. catwild128x128.gif
    Stochastic Optimal Control for Diffusion Bridges in Function Spaces
    Byoungwoo Park, Jungwon Choi, Sungbin Lim‡, and Juho Lee‡
    Advances in Neural Information Processing Systems (NeurIPS), 2024
    PDF Code

2023

  1. mackey.gif
    Nerual Stochastic Differential Games for Time-Series Analysis
    Sungwoo Park*, Byoungwoo Park*, Moontae Lee, and Changhee Lee
    International Conference on Machine Learning (ICML), 2023
    PDF Code Page