Yong-Hyun Park

Incoming Ph.D@UPenn-CIS. park19@seas.upenn.edu

prof_pic.jpg

My goal is to develop and interpret machine intelligence capable of understanding, reasoning, and interacting with the world. I am particularly interested in designing robust representation learning algorithms that can extract fundamental structures and governing principles from data, such as physical laws.

news

Mar 11, 2024 Our paper “Jump Your Steps: Optimizing Sampling Schedule of Discrete Diffusion Models” has been accepted at ICLR 2025! (Mentor: Chieh-Hsin (Jesse) Lai)
Jan 22, 2024 I will be joining UPenn CIS as a Ph.D. student starting Fall 2025, advised by Prof. Jiatao Gu.

selected publications

  1. ICLR
    jys.png
    Jump Your Steps: Optimizing Sampling Schedule of Discrete Diffusion Models
    Yong-Hyun Park, Chieh-Hsin Lai, Satoshi Hayakawa, and 2 more authors
    In The Thirteenth International Conference on Learning Representations, 2025
  2. NeurIPS
    duo.png
    Direct Unlearning Optimization for Robust and Safe Text-to-Image Models
    Yong-Hyun Park, Sangdoo Yun, Jin-Hwa Kim, and 5 more authors
    In The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024
  3. NeurIPS
    geometry.png
    Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometry
    Yong-Hyun Park, Mingi Kwon, Jaewoong Choi, and 2 more authors
    In Advances in Neural Information Processing Systems, 2023