Jaehyeong Jo

Jaehyeong Jo

PhD student at KAIST AI

About me

Hi, I am Jaehyeong Jo.
Here is my CV (Curriculum Vitae) and Google Scholar.

Email: harryjo97 [at] kaist [dot] ac [dot] kr

Last updated: Jan 24, 2024

Introduction

I am a PhD student at Machine Learning and Artificial Intelligence (MLAI) lab in KAIST, under the supervision of Prof. Sung Ju Hwang. I recieved my B.S. (Mathematical Sciences) degrees at KAIST in 2020.

My research interest lies in understanding physical systems through the lens of geometrical structures, especially in the context of generative modeling. I am actively contributing to the generation of geometrical structures with diffusion models, including graphs and data on Riemannian manifolds, and their applications to real-world tasks, e.g., drug discovery, protein design, and neural architecture search. My research interest includes following topics:

  • Diffusion Generative Models
  • Geometric Deep Learning

Preprints

  • Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes

    [paper]
    ​Jaehyeong Jo, Sung Ju Hwang
    Preprint 2023

  • Graph Generation with Destination-Predicting Diffusion Mixture

    [paper] [code]
    ​Jaehyeong Jo*, Dongki Kim*, Sung Ju Hwang
    MLDD Workshop @ ICLR 2023

Conference Publications

  • DiffusionNAG: Task-guided Neural Architecture Generation with Diffusion Models

    [paper]
    Sohyun An*, Hayeon Lee*, Jaehyeong Jo, Seanie Lee, Sung Ju Hwang
    ICLR 2024

  • Text-Conditioned Sampling Framework for Text-to-Image Generation with Masked Generative Models

    [paper] [project]
    Jaewoong Lee*, Sangwon Jang*, Jaehyeong Jo, Jaehong Yoon, Yunji Kim, Jin-Hwa Kim, Jung-Woo Ha, Sung Ju Hwang
    ICCV 2023

  • Exploring Chemical Space with Score-based Out-of-distribution Generation

    [paper]
    Seul Lee, Jaehyeong Jo, Sung Ju Hwang
    ICML 2023

  • Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations

    [paper] [code] [talk]
    ​Jaehyeong Jo*, Seul Lee*, Sung Ju Hwang
    ICML 2022

  • Edge Representation Learning with Hypergraphs

    [paper] [code]
    ​Jaehyeong Jo*, Jinheon Baek*, Seul Lee*, Dongki Kim, Minki Kang, Sung Ju Hwang
    NeurIPS 2021