Yeobin Hong

Contents

• Education
• Publications

Education

• Korea Advanced Institute of Science and Technology (KAIST) | Sep.2024 - Present

  M.S. in Artificial Intelligence (advisor: Jong Chul Ye)

• Korea University | Mar.2020 - Aug.2024

  B.S. in Mathematics & Artificial Intelligence

Publications

2025

• InverseCrafter: Efficient Video ReCapture as a Latent Domain Inverse Problem

  Yeobin Hong*, Suhyeon Lee*, Hyungjin Chung†, Jong Chul Ye†

  arXiv preprint

  

  InverseCrafter is an inpainting inverse solver that reformulates the 4D generation task as an inpainting problem solved in the latent space.

• Alignment-Guided Score Matching for Text-to-Image Alignment in Diffusion Models

  Jaa-Yeon Lee*, Yeobin Hong*, Taesung Kwon, Jong Chul Ye

  ICML 2026 Spotlight (536/6352=2.2%)

  

  AGSM improves text–image alignment using score-level preference optimization with a Plackett–Luce objective without an explicit reward. By explicitly guiding positive and negative pairs within the diffusion score-matching loss, AGSM reduces SoftREPA’s failure modes while improving generation and editing across different backbones.

• FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing Code

  Jeongsol Kim*, Yeobin Hong*, Jonghyun Park, Jong Chul Ye

  ICLR 2026

  

  FlowAlign is an inversion-free, flow-based image editing method that achieves smooth and stable trajectories through a flow-matching loss. It also enables reversible editing by leveraging the intrinsic properties of ODE-based transformations.

• DreamMakeup: Face Makeup Customization using Latent Diffusion Models

  Geon Yeong Park*, Inhwa Han*, Serin Yang*, Yeobin Hong*, Seongmin Jeong, Heechan Jeon, Myeongjin Goh, Sung Won Yi, Jin Nam, Jong Chul Ye

  WACV 2026

  

  DreamMaekup is a face makeup customization method that can get various conditioning as input - reference images, RGB colors, textual descriptions.

2024

• GaussianTalker: Real-Time High-Fidelity Talking Head Synthesis with Audio-Driven 3D Gaussian Splatting Code

  Kyusun Cho*, Joungbin Lee*, Heeji Yoon*, Yeobin Hong, Jaehoon Ko, Sangjun Ahn, Seungryong Kim

  ACM MM 2024

  

  GaussianTalker is a framework for real-time generation of pose-controllable talking heads. It leverages the fast rendering capabilities of 3D Gaussian Splatting (3DGS) while addressing the challenges of directly controlling 3DGS with speech audio.