Youngmin Kim

01About

I am a first-year M.S. student at the Kim Jaechul Graduate School of AI, KAIST, advised by Prof. Jong Chul Ye at BISPL. I received my B.S. in Computer Science and Engineering from Korea University in August 2026, graduating early in 3.5 years.

My research focuses on 3D vision and generative modeling, particularly their applications to robotics and embodied AI. I am broadly interested in geometry-aware visual representations and learning-based approaches to spatial perception and interaction.

02News

• Sep. 2026Starting my M.S. at the Kim Jaechul Graduate School of AI, KAIST, joining BISPL under Prof. Jong Chul Ye.
• Aug. 2026Received my B.S. in Computer Science and Engineering from Korea University — early graduation in 3.5 years.
• 2026CRePE: Curved Ray Expectation Positional Encoding for unified-camera-controlled video generation is on arXiv.
• 2026Preprint on DMD-augmented unpaired neural Schrödinger bridges for ultra-low-field MRI enhancement is on arXiv.
• 2026Our ultra-low-field brain MRI enhancement method was presented at the MICCAI ULF-EnC Challenge Workshop.
• Jan. 2025Received the Academic Excellence Award from Korea University.

03Publications

1. 
   CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation

   Seonghyun Jin^*, Youngmin Kim^*, Sunwoo Park^*, Jong Chul Ye

   arXiv preprint2026

   arXiv:2605.12938
2. 
   DMD-augmented Unpaired Neural Schrödinger Bridge for Ultra-Low Field MRI Enhancement

   Youngmin Kim^*, Jaeyun Shin^*, Jeongchan Kim^*, Taehoon Lee, Jaemin Kim, Peter Hsu, Jelle Veraart, Jong Chul Ye

   arXiv preprint2026

   arXiv:2603.03769
3. 
   Ultra-Low-Field Brain MRI Enhancement using Resfusion and Residual Artifact Suppression Network

   Youngmin Kim^*, Jeongchan Kim^*, Taehoon Lee^*, Jaeyun Shin^*, Suhyeon Lee, Jong Chul Ye

   MICCAI ULF-EnC Challenge Workshop2026
4. 
   Performance Analysis of Kubernetes Traffic Scheduling Algorithms in Homogeneous and Heterogeneous Environments

   Youngmin Kim, Hogeon Park, Heonchang Yu

   Korea Computer Congress (KCC)2025
5. Improving Visual Question Answering via Prompt-Level Adaptation and Knowledge-Driven Fine-Tuning: Solution of Meta CRAG-MM Challenge 2025

   Youngmin Kim, Wonyeong Jang, Taehee Jeong

   Proceedings of the KDD Cup Workshop on CRAG-MM2025

^* These authors contributed equally.

04Research Experience

05Education