01About

I am an M.S./Ph.D. student in the Optimization and Statistical Inference (OSI) Lab at KAIST AI (Kim Jaechul Graduate School of AI), advised by Prof. Se-Young Yun. I received my B.S. in Mathematical Science with a double major in Computer Science at KAIST. My research focuses on generative models — diffusion models, one-step generative modeling, and test-time alignment — as well as the mathematical foundations of bandit algorithms. I am also interested in world models.

  • Generative Models
  • Diffusion Models
  • Bandit Algorithms
  • World Models

02Publications

* Equal contribution · † Corresponding author

NeurIPS 2026 Comparison of reverse drift, forward drift, and DualDrift
PUBLICATION 01

DualDrift: Forward and Reverse Drifting Fields for One-Step Generative Modeling

Hojung Jung*, Juhyeong Kim*, Jaehyun Kwak, Boryeong Cho, Junhyeok Yang, Youngrok Park, Sangmin Bae, Se-Young Yun†

NeurIPS 2026 · ICML 2026 SPIGM Workshop

A one-step generative modeling framework that jointly leverages forward and reverse drifting fields to produce high-quality samples without iterative generation.

NeurIPS AI4GOOD 2026 · Oral UniSAFE safety risk comparison across tasks and models
PUBLICATION 02

UniSAFE: A Comprehensive Benchmark for Safety Evaluation of Unified Multimodal Models

Segyu Lee*, Boryeong Cho*, Hojung Jung*, Seokhyun An, Juhyeong Kim, Jaehyun Kwak, Yongjin Yang, Sangwon Jang, Youngrok Park, Wonjun Chang, Se-Young Yun†

NeurIPS 2026 AI4GOOD Workshop (Oral)

Paper Code & Data

A system-level safety benchmark for unified multimodal models spanning seven input/output settings and 6,802 curated instances.

03Experience

Kyung Hee University

Research Assistant

Department of Oral Microbiology, College of Dentistry, Kyung Hee University

Advisors: Kyu Hwan Kwack, Jae-Hyung Lee

Research topic:

  • BAGM: Learning Spatial Cell Representations in Gastric Tissue

2026.07 — 2026.08

Research Intern (KAIRI)

Optimization and Statistical Inference (OSI) Lab, KAIST AI · Seoul, South Korea

Advisor: Prof. Se-Young Yun

Research topics:

  • Bandit algorithms
  • Diffusion models: improved TFG for test-time alignment
  • Drifting Model

2023.12 — 2026.08

04Education

KAIST AI

Kim Jaechul Graduate School of AI at KAIST

M.S./Ph.D. in Artificial Intelligence · Seoul, South Korea

2026.09 —

KAIST

KAIST

B.S. in Mathematical Science & Computer Science (Double Major) · Daejeon, South Korea

2022.03 — 2026.08

Technical University of Denmark (DTU)

Exchange Student, Computer Science · Lyngby, Denmark

2025.02 — 2025.06

Gwangju Science Academy for the Gifted

Gwangju Science Academy for the Gifted

High School · Gwangju, South Korea

2019.03 — 2021.12