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 unified multimodal generative framework. Recently, I have been exploring how to improve the flexibility, efficiency, and alignment of generative models in diverse domains.

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

News

Publications

MUNI: Multimodal Unified Latent Diffusion for Coherent Any-to-Any Generation

Kyeongmin Yeo*, Yunhong Min*, Minhyuk Sung (* equal contributions.)

arXiv 2026

[Paper] [Project]

Drifting Field Policy: A One-Step Generative Policy via Wasserstein Gradient Flow

Juil Koo, Mingue Park, Jiwon Choi, Yunhong Min, Minhyuk Sung

arXiv 2026

[Paper] [Project] [Code]

NoiseTilt: Noise-Tilted Reverse Kernels for Diffusion Reward Alignment

Jisung Hwang, Yunhong Min, Jaihoon Kim, I-Chao Shen*, Minhyuk Sung* (* co-corresponding authors)

ECCV 2026

[Paper]

MatLat: Material Latent Space for PBR Texture Generation

Kyeongmin Yeo, Yunhong Min, Jaihoon Kim, Minhyuk Sung

CVPR 2026 (Highlight)

[Paper] [Project] [Code]

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

Yunhong Min*, Juil Koo*, Seungwoo Yoo, Minhyuk Sung (* equal contributions.)

ICLR 2026

[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 contributions.)

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 contributions.)

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 contributions.)

ACM MM 2024

[Paper]

Academic Service