Kyeongmin Yeo

M.S. Student, KAIST

Visual AI Group

Generative Modeling, Multimodal AI & World Models

I am an M.S. student at the KAIST Visual AI Group, advised by Prof. Minhyuk Sung. My research focuses on generative modeling and multimodal generation. My current interests include generative modeling, multimodal AI, and world models.

I received my B.S. in Computer Science, with a minor in Mathematical Sciences, from KAIST in 2026. I graduated summa cum laude and received the Graduate of the Year Award (KAIST President’s Award).

news

Sep 2026	MUNI was accepted to NeurIPS 2026. Paper · Code
Jul 2026	I was selected for the Presidential Science Scholarship for Graduate Students. Lab announcement
Jun 15, 2026	Our MUNI preprint is available, with a project page and code for coherent any-to-any generation across image, text, and audio.
Jun 04, 2026	I presented MatLat in a highlight talk at the APPX Workshop at CVPR 2026.
Apr 2026	MatLat was selected as a Highlight at CVPR 2026.

publications

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

Kyeongmin Yeo^*, Yunhong Min^*, and Minhyuk Sung

In NeurIPS, 2026

arXiv Bib Code Website

@inproceedings{yeo2026muni,
  title = {MUNI: Multimodal Unified Latent Diffusion for Coherent Any-to-Any Generation},
  author = {Yeo, Kyeongmin and Min, Yunhong and Sung, Minhyuk},
  booktitle = {NeurIPS},
  year = {2026},
  url = {https://arxiv.org/abs/2606.16408},
}

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

Mingue Park^*, Jisung Hwang^*, Seungwoo Yoo^*, Kyeongmin Yeo, and Minhyuk Sung

In ICLR, 2026

arXiv Bib Code Website

@inproceedings{park2026pairflow,
  title = {PairFlow: Closed-Form Source-Target Coupling for Few-Step Generation in Discrete Flow Models},
  author = {Park, Mingue and Hwang, Jisung and Yoo, Seungwoo and Yeo, Kyeongmin and Sung, Minhyuk},
  booktitle = {ICLR},
  year = {2026},
  url = {https://arxiv.org/abs/2512.20063},
}

MatLat: Material Latent Space for PBR Texture Generation

Kyeongmin Yeo, Yunhong Min, Jaihoon Kim, and Minhyuk Sung

In CVPR, 2026

Highlight arXiv Bib Code Website

Selected as a Highlight at CVPR 2026.

@inproceedings{yeo2026matlat,
  title = {MatLat: Material Latent Space for PBR Texture Generation},
  author = {Yeo, Kyeongmin and Min, Yunhong and Kim, Jaihoon and Sung, Minhyuk},
  booktitle = {CVPR},
  year = {2026},
  url = {https://arxiv.org/abs/2512.17302},
}

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

Taehoon Yoon^*, Yunhong Min^*, Kyeongmin Yeo^*, and Minhyuk Sung

In NeurIPS, 2025

Spotlight arXiv Bib Code Website

Selected as a Spotlight at NeurIPS 2025.

@inproceedings{yoon2025psi,
  title = {Ψ-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models},
  author = {Yoon, Taehoon and Min, Yunhong and Yeo, Kyeongmin and Sung, Minhyuk},
  booktitle = {NeurIPS},
  year = {2025},
  url = {https://arxiv.org/abs/2506.01320},
}

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

Yunhong Min^*, Daehyeon Choi^*, Kyeongmin Yeo, Jihyun Lee, and Minhyuk Sung

In NeurIPS, 2025

arXiv Bib Code Website

@inproceedings{min2025origen,
  title = {ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation},
  author = {Min, Yunhong and Choi, Daehyeon and Yeo, Kyeongmin and Lee, Jihyun and Sung, Minhyuk},
  booktitle = {NeurIPS},
  year = {2025},
  url = {https://arxiv.org/abs/2503.22194},
}

Neural Green’s Functions

Seungwoo Yoo, Kyeongmin Yeo, Jisung Hwang, and Minhyuk Sung

In NeurIPS, 2025

arXiv Bib

@inproceedings{yoo2025neural,
  title = {Neural Green's Functions},
  author = {Yoo, Seungwoo and Yeo, Kyeongmin and Hwang, Jisung and Sung, Minhyuk},
  booktitle = {NeurIPS},
  year = {2025},
  url = {https://arxiv.org/abs/2511.01924},
}

StochSync: Stochastic Diffusion Synchronization for Image Generation in Arbitrary Spaces

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

In ICLR, 2025

arXiv Bib Code Website

@inproceedings{yeostochsync,
  title = {StochSync: Stochastic Diffusion Synchronization for Image Generation in Arbitrary Spaces},
  author = {Yeo, Kyeongmin and Kim, Jaihoon and Sung, Minhyuk},
  booktitle = {ICLR},
  year = {2025},
  url = {https://arxiv.org/abs/2501.15445},
}

Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Poses

Seungwoo Yoo, Juil Koo, Kyeongmin Yeo, and Minhyuk Sung

In NeurIPS, 2024

arXiv Bib Website

@inproceedings{yoo2024neuralposerepresentationlearning,
  title = {Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Poses},
  author = {Yoo, Seungwoo and Koo, Juil and Yeo, Kyeongmin and Sung, Minhyuk},
  booktitle = {NeurIPS},
  year = {2024},
  url = {https://arxiv.org/abs/2406.09728},
}

SyncTweedies: A General Generative Framework Based on Synchronized Diffusions

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

In NeurIPS, 2024

arXiv Bib Code Website

@inproceedings{kim2024synctweediesgeneralgenerativeframework,
  title = {SyncTweedies: A General Generative Framework Based on Synchronized Diffusions},
  author = {Kim, Jaihoon and Koo, Juil and Yeo, Kyeongmin and Sung, Minhyuk},
  booktitle = {NeurIPS},
  year = {2024},
  url = {https://arxiv.org/abs/2403.14370},
}