Kyeongmin Yeo

KAIST '22

Visual AI Lab M.S. Student

Generative AI & Computer Graphics

I am a M.S. student at the KAIST Visual AI Lab, advised by Prof. Minhyuk Sung. My research mainly focuses on generative AI, especially diffusion-based and flow-based models. I am particularly interested in the application of these models in computer vision and content creation.

selected publications

PairFlow: Closed-Form Source-Target Coupling for Few-Step Generation in Discrete Flow Models

Mingue Park, Jisung Hwang, Seungwoo Yoo, and 2 more authors

In ICLR 2026, 2026
MatLat: Material Latent Space for PBR Texture Generation

Kyeongmin Yeo, Yunhong Min, Jaihoon Kim, and 1 more author

In CVPR 2026, 2026
Ψ-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models

Taehoon Yoon^*, Yunhong Min^*, Kyeongmin Yeo^*, and 1 more author

In NeurIPS 2025, 2025
ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation

Yunhong Min^*, Daehyeon Choi^*, Kyeongmin Yeo, and 2 more authors

In NeurIPS 2025, 2025
Neural Green’s Functions

Seungwoo Yoo, Kyeongmin Yeo, Jisung Hwang, and 1 more author

In NeurIPS 2025, 2025
StochSync: Stochastic Diffusion Synchronization for Image Generation in Arbitrary Spaces

Kyeongmin Yeo^*, Jaihoon Kim^*, and Minhyuk Sung

In The Thirteenth International Conference on Learning Representations, 2025
Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Poses

Seungwoo Yoo, Juil Koo, Kyeongmin Yeo, and 1 more author

In NeurIPS 2024, 2024
SyncTweedies: A General Generative Framework Based on Synchronized Diffusions

Jaihoon Kim^*, Juil Koo^*, Kyeongmin Yeo^*, and 1 more author

In NeurIPS 2024, 2024