Publications

2027

  1. Preprint
    Stable Reward Fine-tuning of One-step Generators via Backward Drifting
    Jiwoo Yoon, Hyunsoo Song, Hoseong Hwang, Jaehoon Hahm, and 3 more authors
    Under review at CVPR, 2027
  2. Preprint
    Geometric Flow Matching for Learning Quantum Many-Body States with Classical Shadows
    Jaehoon Hahm and Bryan Clark
    Under review at ICLR, 2027
  3. Preprint
    TILT: Model-Intrinsic Reward Alignment for Compositional Diffusion
    Debottam Dutta, Jianchong Chen, Jaehoon Hahm, and Romit Roy Choudhury
    Under review at ICLR, 2027
  4. Preprint
    Optimal Crystal Flow for Fast and Reliable Crystal Generation
    Seunghoon Yi*, Youngwoo Cho*, Jaehoon Hahm, Jeongwoo Shin, and 4 more authors
    Under review at ICLR, 2027

2026

  1. ICML
    Equivariant Latent Alignment via Flow Matching under Group Symmetries
    Sunghyun Kim*, Jaehoon Hahm*, Jeongwoo Shin, and Joonseok Lee
    International Conference on Machine Learning, 2026
    PDF
  2. ICMLW
    Can Intrinsic Rewards Enable Compositional Alignment in Diffusion?
    Debottam Dutta, Jaehoon Hahm, Jianchong Chen, and Romit Roy Choudhury
    SPIGM at ICML, 2026

2025

  1. ICCV
    SummDiff: Generative Modeling of Video Summarization with Diffusion
    Kwanseok Kim*, Jaehoon Hahm*, Sumin Kim, Jinhwan Sul, and 2 more authors
    International Conference on Computer Vision, Highlight [Top 2.3%], 2025
    PDF Code Project Page

2024

  1. ICML
    Isometric Representation Learning for Disentangled Latent Space of Diffusion Models
    Jaehoon Hahm*, Junho Lee*, Sunghyun Kim, and Joonseok Lee
    International Conference on Machine Learning, 2024
    PDF Code
  2. QTML
    Generative Modeling of Quantum Distribution with Functional Flow Matching
    Jaehoon Hahm*, Tak Hur*, Joonseok Lee, and Daniel K. Park
    Quantum Techniques in Machine Learning, 2024
    PDF