Kyeonghun Kim is a Research Assistant at IMSI Research Lab, Seoul National University, working across medical imaging, generative AI, and multimodal deep learning. He leads the SUDAL Medical Imaging Team and develops clinically grounded systems for 3D MRI synthesis, segmentation, diffusion modeling, and vision-language learning.

He is the first author of 3D-LLDM, a label-guided 3D latent diffusion framework for high-resolution synthetic liver MRI and downstream hepatic-structure segmentation. The work was presented as an oral paper at ISBI 2026 and grew from collaboration spanning Stanford University, NVIDIA researchers, and clinical partners at Samsung Medical Center.

Research Highlight · NeurIPS 2026 Two NeurIPS 2026 Papers Accepted Read about the lab's work on reproducibility, dataset auditing, and robust medical AI evaluation →

Research at a Glance

NeurIPS 2026: 2Accepted papers
MICCAI Workshops: 2Workshop papers
AAAI Workshop: 1Workshop paper
ISBI oral papers: 3Oral presentations
IEEE MedAI: 1Conference paper
AICAS oral papers: 3Oral presentations
APCCAS papers: 4Including one oral paper
GTC posters: 3NVIDIA GTC presentations
AACL-IJCNLP: 1NLP conference paper

Research & Industry Exchange

Representing IMSI Lab in a Silicon Valley technology programme, he coordinated and joined office tours and research exchanges at Google, NVIDIA, Salesforce, Uber, and Microsoft in San Jose and the wider Bay Area. These visits connected the lab's medical-AI work with production-scale AI infrastructure, research practice, and potential industry collaboration.

Research Interests

  • Medical Image Analysis
  • Generative AI & Diffusion Models
  • 3D Medical Imaging
  • Multimodal Deep Learning
  • Computer Vision
  • Foundation Models
  • Hyperspectral Imaging

Education

  • MSc in Artificial Intelligence, 2024

    Kookmin University (GPA: 4.03/4.5)

  • BSc in Computer Science, 2022

    Hankyong National University (GPA: 4.12/4.5)

Recent Publications

This list is updated automatically from the IMSI publication spreadsheet.

  • Loading publications…

View and search all publications →

Professional Experience

  • AI Researcher at GNEWSOFT (Oct. 2024 ~ Present)
  • Medical Imaging Team Lead at OUTTA (Jul. 2023 ~ Present)
  • AI Researcher at Weatherpia (Mar. 2024 ~ Aug. 2024)
  • Data Scientist at LG Uplus (Jan. 2024 ~ Mar. 2024)
  • AI Instructor at SK Telecom (Dec. 2023)
  • AI Software Engineer at AI O2O Inc. (Aug. 2023 ~ Dec. 2023)
  • Data Analyst at OESON (Jan. 2023 ~ Mar. 2023)
  • Software Engineer at NuriFlex Holdings Inc. (Nov. 2021 ~ Dec. 2022)
  • Junior Developer at AST Global (Oct. 2020 ~ Apr. 2021)

Intellectual Property

  • Method for Refining Hyperspectral Images Using Deep Learning (딥러닝을 이용한 초분광이미지의 정제방법) — Registration date: August 27, 2026; Korean Patent Registration No. 10-3010471-0000.

Teaching Experience

His teaching spans AI literacy, prompt engineering, Python, deep learning, English, and practical workplace automation. The following engagements are listed in reverse chronological order.

  • Busan Metropolitan City — Generative AI for Workplace Productivity and Public Administration: October 23, 2026; practical ChatGPT, public-data, and prompt-engineering training for 30 public officials.
  • Kookmin University AX-Startup Bootcamp: August 29 and September 1, 2026; AI literacy and prompt engineering for 28 participants.
  • Seoul National University OUTTA Python & Deep Learning Bootcamp: June 1, 2024–August 30, 2026; instruction for 3,000+ university students and professionals.
  • Busan Metropolitan City — Public-Data Ideation: July 1, 2026; public-data platforms, ChatGPT, and prompt engineering for 36 public officials.
  • KCA / Kyobo Life — AX Insight Training: April 21, 2026; practical AX insights and foundational prompt engineering for 37 employees.
  • TOEFL Instruction: October 5, 2023–December 30, 2025; listening, reading, speaking, and writing instruction for 20 working professionals.
  • HUN Company, Ilsan — AI and ChatGPT for Planners: April 25, 2025; hands-on prompt-engineering training for 20 professionals.
  • TOEIC Instruction: August 23, 2020–February 16, 2024; listening and reading instruction for 100 university students.
  • SK Telecom — Practical Stable Diffusion: December 5–7, 2023; three-day employee programme for 33 engineers using AWS G4 GPU instances.
  • The Joeun Computer Academy — EASY AI: June 8–August 30, 2023; deep-learning foundations and recommender systems for 35 learners.
  • Python Fundamentals & Intermediate Programming: March 2, 2018–Present; online instruction covering data structures, functions, and classes for 5,000+ learners.
  • Fitness Instruction: December 10, 2017–June 17, 2021; bodyweight and gym-training content reaching 2,440 subscribers and 2,302,547 views.

Volunteering

  • Blood Donation Volunteer — Korean Red Cross Blood Services: more than 50 donations since 2018; Blood Donation Merit Silver Award on October 8, 2020, and Gold Award on August 21, 2021.
  • Recurring Donor — NAVER Corp: ongoing giving through NAVER Happy Bean since 2015, beginning with rewards earned from blogging and expanding into recurring and direct donations supporting vulnerable communities.

Certifications & Licenses

Loading credentials…