Mingue Park

Ph.D. Student
KAIST
kicikicik (at) kaist.ac.kr

About Me

I am a first year Ph.D. student at the AI Computing at KAIST, advised by Prof. Minhyuk Sung.

Research Interests

Generative Models:
Diffusion / Flow Models

World Model:
Representation Learning for World Modeling

News

[Sep. 2026] One paper is accepted to NeurIPS 2026.
[Jun. 2026] One paper is accepted to ECCV 2026.
[Apr. 2026] One paper is accepted to CVPR 2026.
[Feb. 2026] One paper is accepted to ICLR 2026.

Publications

NeurIPS

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

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

Conference on Neural Information Processing Systems (NeurIPS), 2026.

PDF Code

CVPR

Token Warping Helps MLLMs Look from Nearby Viewpoints

Phillip Y. Lee*, Chanho Park*, Mingue Park, Seungwoo Yoo, Juil Koo, Minhyuk Sung (*Equal Contribution)

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.

PDF Code

ICLR

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

Mingue Park*, Jisung Hwang*, Seungwoo Yoo*, Kyeongmin Yeo, Minhyuk Sung (*Equal Contribution)

International Conference on Learning Representations (ICLR), 2026.

PDF Code

ECCV

DiverseVAR: Balancing Diversity and Quality of Next-Scale Visual Autoregressive Models

Mingue Park*, Prin Phunyaphibarn*, Phillip Y. Lee, Minhyuk Sung (*Equal Contribution)

European Conference on Computer Vision (ECCV), 2026.

PDF Code

Past Experience

SW Development Intern, Hyundai Motor Company (Sep. 2023 - Feb. 2024)
- Autonomous Driving Perception Team

Powered by Jekyll and Minimal Light theme.