johnjaejunlee95's Easy AI Blog

Hello! I am @johnjaejunlee95, a 5th-year M.S./Ph.D. integrated student at the Graduate School of Artificial Intelligence, UNIST.

My research stems from a fundamental question: “How do AI models learn and generalize?”

  • Past: Meta-Learning, Generalization
  • Current: Multimodal Learning (Theoretical Approach & Applications e.g., VLA), Flatness (Loss Landscape Perspective), AI4Science (Bio)

While my earlier research focused on Meta-Learning, I am currently conducting research on Multimodal Learning. I focus on analyzing Multimodal Learning through a theoretical lens, specifically connecting it to the geometry of the Loss Landscape (Flatness). Recently, I have also developed an interest in Bioinformatics (e.g., EEG) and have begun exploring the field of AI4Science.

My goal extends beyond merely building high-performance models; I aim to become a researcher who “deeply understands AI based on solid theoretical and mathematical grounds and explains it clearly to the audience.” I aspire to uncover the operating principles of models both intuitively and theoretically, and to act as a bridge, conveying complex engineering concepts to the public in an intuitive and approachable way.

This blog will primarily feature posts on:

  • Deep Learning: Concepts, Algorithms & Intuition
  • Essential Mathematics for AI
  • Paper Reviews
🧾 My CV (click to expand)

🎓 Education


  • UNIST (Ulsan National Institute of Science and Technology)
    M.S.-Ph.D. Combined Candidate — Graduate School of Artificial Intelligence (AIGS)
    Mar. 2022 - Present · GPA: 3.97 / 4.30
  • Dankook University
    B.S. — Electronics and Electrical Engineering (EE)
    Mar. 2015 - Feb. 2022 · GPA: 3.93 / 4.50

🧪 Experience


  • Machine Intelligence and Information Theory Lab (MIIT), UNIST
    M.S.–Ph.D. Combined Research Student
    Mar. 2022 - Present
    • Research on meta-learning / multimodal learning / robust VLA (ongoing).
  • Design Technology Laboratory (DTL), Yonsei University
    B.S. Internship
    Feb. 2021 - Aug. 2021
    • Worked on applied ML / mobile pipeline development.
  • SoC and Embedded System (SES), Dankook University
    B.S. Internship
    Jul. 2020 - Feb. 2021
    • Worked on embedded / SoC-related projects.

📝 Publications


  • Can One Modality Model Synergize Training of Other Modality Models?
    Jae-Jun Lee, Sung Whan Yoon
    The Thirteenth International Conference on Learning Representations (ICLR), Singapore EXPO, Singapore (2025)
  • XB-MAML: Learning Expandable Basis Parameters for Effective Meta-Learning with Wide Task Coverage
    Jae-Jun Lee, Sung Whan Yoon
    International Conference on Artificial Intelligence and Statistics (AISTATS), Valencia, Spain (2024)

🧾 Patents


  • Single modality model-based multimodal learning device and method thereof
    Sung Whan Yoon, Jae-Jun Lee
    KR 10-2025-0066240 · Publication: May 21, 2025
  • MAML-based domain adaptation algorithm to improve the effectiveness of developing biomedical AI systems
    Han-Jeong Hwang, Sung Whan Yoon, Ga-Young Choi, Jae-Jun Lee
    KR 10-2024-0176258 · Publication: Dec 02, 2024

🧩 Projects


Virtual Tactile Signal Generation (Vision–Tactile Integrated AGI) (Sept. 2025 - Present)
Sponsor: IITP
Role: Core member (MIIT, UNIST)
Partners:
- Research: Korea University Sejong Campus, UNIST, Technische Universität Berlin
- Industry: Immertix, PSDL, SURROMIND, Sotong Five, Nongshim Data System (NDS)
  • Developing 3D reconstruction with object-part segmentation enriched with tactile information.
Reinforcement Learning for High-Efficiency & Reliable Combustion System (Mar. 2022 - Aug. 2023)
Sponsor: Samyang Corp. & UNIST
Role: Core member (MIIT, UNIST)
  • Designed a smart control system for combustion processes using deep reinforcement learning.
Heterogeneous Home Appliance Data Analysis Framework (Jul. 2022 - Jan. 2023)
Sponsor: LG H&A
Role: Core member (MIIT, UNIST)
  • Built a causal discovery framework under limited data using CCM + Meta-Learning.
Identification Data Processing for On-Site Police Use (Apr. 2021 - Aug. 2021)
Sponsor: NRF
Role: Project member (DTL, Yonsei University)
  • Developed an Android app for facial verification (Java / Android Studio).

🧑‍🏫 Teaching & Service


📚 TA

  • Non-Parametric Bayesian
    Teaching Assistant · UNIST
    Sep. 2023 - Dec. 2023
  • Meta & Multi-task Learning
    Teaching Assistant · UNIST
    Sep. 2023 - Dec. 2023

🏫 Special Program

  • LG Electronics DX Intensive Course
    Instructor (Deep Learning coding sessions) · UNIST
    Summer 2024 - Summer 2024
  • ROK Navy AI Specialist Program
    Instructor (CNN/RNN coding sessions) · ROK Navy & UNIST
    Aug. 2023 - Aug. 2023
  • LG Electronics DX Intensive Course
    Instructor (Deep Learning coding sessions) · UNIST
    Summer 2022 - Summer 2022

🌱 AI Novatus Academia

  • AI Novatus Academia
    Instructor (Basics of AI coding sessions) · Changwon & Ulsan
    Summer 2024 - Summer 2024
  • AI Novatus Academia
    Instructor (Basics of AI coding sessions) · Changwon & Ulsan
    Spring 2023 - Spring 2023
  • AI Novatus Academia
    Instructor (Basics of AI coding sessions) · Changwon & Ulsan
    Spring 2022 - Spring 2022

🛠️ Skills


Programming
Python · MATLAB (basic) · C/C++ (basic)
Tools & Platforms
Linux · Bash · Git · Conda
AI Frameworks / Libraries
PyTorch · JAX (basic) · Scikit-Learn · Pandas · Hugging Face
Math Background
Linear Algebra · Probability & Statistics · Information Theory · Estimation Theory (basic) · Learning Theory (basic)
Writing / Workflow
LaTeX · Markdown · Notion
Search