Bio

I am Yunhong Min, an M.S. student in the KAIST Visual AI Group, led by Prof. Minhyuk Sung.

My research interests are in diffusion- and flow-based generative models, with a focus on developing a general generative framework leveraging powerful generative priors. Recently, I have been exploring how to effectively incorporate external guidance during sampling to improve generation quality without requiring additional training.

For details, refer to my Curriculum Vitae (CV).

News

Publications

MatLat: Material Latent Space for PBR Texture Generation

Kyeongmin Yeo, Yunhong Min, Jaihoon Kim, Minhyuk Sung

arXiv 2025

[Paper] [Project]

BézierFlow: Learning Bézier Stochastic Interpolant Schedulers for Few-Step Generation

Yunhong Min*, Juil Koo*, Seungwoo Yoo, Minhyuk Sung (*Equal contribution.)

arXiv 2025

[Paper] [Project] [Code]

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

Taehoon Yoon*, Yunhong Min*, Kyeongmin Yeo*, Minhyuk Sung (*Equal contribution.)

NeurIPS 2025 (Spotlight)

[Paper] [Project] [Code]

ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation

Yunhong Min*, Daehyeon Choi*, Kyeongmin Yeo, Jihyun Lee, Minhyuk Sung (*Equal contribution.)

NeurIPS 2025

[Paper] [Project] [Code]

DAFT-GAN: Dual Affine Transformation Generative Adversarial Network for Text-Guided Image Inpainting

Jihoon Lee*, Yunhong Min*, Hwidong Kim*, Sangtae Ahn (*Equal contribution.)

ACM MM 2024

[Paper]

Academic Service