Contents
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
-
InverseCrafter: Efficient Video ReCapture as a Latent Domain Inverse Problem
Code
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.
-
Score Matching for Soft Token Optimization in Text-to-Image Alignment
Jaa-Yeon Lee*, Yeobin Hong*, Taesung Kwon, Jong Chul Ye
arXiv preprint
Alignment-guided score matching trains soft tokens for text alignment using diffusion model’s conditional likelihood as implicit reward, leveraging both positive & negative (text, image) pairs.
-
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.
2025
-
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.