cv
Basics
| Name | Kyeongmin Yeo |
| Label | M.S. Student |
| aaaaa@kaist.ac.kr | |
| Url | https://32V.github.io/ |
| Summary | M.S. student at KAIST Visual AI Group, advised by Prof. Minhyuk Sung. Researching generative modeling and multimodal generation. Current interests include generative modeling, multimodal AI, and world models. |
Interests
| Academic Interests | |
| Generative Modeling | |
| Multimodal AI | |
| World Models |
Education
Research Experience
-
2026.02 - Present Daejeon, South Korea
-
2023.12 - 2026.02 Daejeon, South Korea
Undergraduate Intern
KAIST Visual AI Group
Research on visual content generation using diffusion models.
Teaching
- Spring 2026
CS.40709 (CS479): Machine Learning for 3D Data
Teaching Assistant (TA) · School of Computing, KAIST
Talks
- June 4, 2026
MatLat: Material Latent Space for PBR Texture Generation
Highlight Talk · APPX: Appearance Understanding and Generation Workshop, CVPR 2026
Publications
* denotes equal contribution.
-
2026 MUNI: Multimodal Unified Latent Diffusion for Coherent Any-to-Any Generation
Kyeongmin Yeo*, Yunhong Min*, Minhyuk Sung
NeurIPS 2026
A shared latent diffusion framework for coherent generation across image, text, and audio.
-
2026 MatLat: Material Latent Space for PBR Texture Generation
Kyeongmin Yeo, Yunhong Min, Jaihoon Kim, Minhyuk Sung
CVPR 2026 (Highlight)
A material latent space for physically based rendering (PBR) texture generation.
-
2026 PairFlow: Closed-Form Source-Target Coupling for Few-Step Generation in Discrete Flow Models
Mingue Park*, Jisung Hwang*, Seungwoo Yoo*, Kyeongmin Yeo, Minhyuk Sung
ICLR 2026
A closed-form source-target coupling method for few-step generation in discrete flow models.
-
2025 Ψ-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models
Taehoon Yoon*, Yunhong Min*, Kyeongmin Yeo*, Minhyuk Sung
NeurIPS 2025 (Spotlight)
A novel initial particle sampling method for SMC-based inference-time reward alignment in score models.
-
2025 ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation
Yunhong Min*, Daehyeon Choi*, Kyeongmin Yeo, Jihyun Lee, Minhyuk Sung
NeurIPS 2025
A method for zero-shot 3D orientation grounding in text-to-image generation.
-
2025 Neural Green's Functions
Seungwoo Yoo, Kyeongmin Yeo, Jisung Hwang, Minhyuk Sung
NeurIPS 2025
A neural solution operator for linear partial differential equations inspired by Green's functions.
-
2025 StochSync: Stochastic Diffusion Synchronization for Image Generation in Arbitrary Spaces
Kyeongmin Yeo*, Jaihoon Kim*, Minhyuk Sung
ICLR 2025
A stochastic diffusion synchronization framework for image generation in arbitrary spaces.
-
2024 Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Poses
Seungwoo Yoo, Juil Koo, Kyeongmin Yeo, Minhyuk Sung
NeurIPS 2024
A neural pose representation for generating and transferring non-rigid object poses.
-
2024 SyncTweedies: A General Generative Framework Based on Synchronized Diffusions
Jaihoon Kim*, Juil Koo*, Kyeongmin Yeo*, Minhyuk Sung
NeurIPS 2024
A general framework for generating diverse visual content by synchronizing multiple diffusion processes.
Awards
- 2026.07
Presidential Science Scholarship for Graduate Students
Korea Student Aid Foundation (KOSAF)
- 2026.02.20
- 2025
Next-Generation Engineer Grand Prize, 2nd Cohort
Institute for Promotion of Engineering and Science of Korea (IPESK)
- 2025
- 2025
Outstanding Award (2nd place), Undergraduate Research Participation Program (URP)
College of Engineering, KAIST
Winter/Spring 2025
- 2025
Global Leadership Award (Creativity)
KAIST
- 2024
- 2022–2023
- 2023
- 2022
National Excellence Scholarship (Natural Sciences and Engineering)
Korea Student Aid Foundation (KOSAF)