Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings
@UCME1020
UCME1020
Follow

Highlights

  • Pro

Block or report UCME1020

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
UCME1020 /README.md

👨‍💻 Uicheol Jung (정의철)

M.S. Student @ Sejong Univ. RCV Lab

Researcher at Robotics & Computer Vision Lab (RCV)


🌱 Interests

  • Multimodal Large Language Models (MLLM)
    • Vision-language modeling, Multimodal reasoning, Agentic RAG
  • Video Understanding
    • Temporal modeling, Text-video retrieval, Long-form reasoning
  • Efficient Multimodal Learning
    • Mixture-of-Experts (MoE), Parameter-efficient fine-tuning (PEFT), Inference optimization
  • Computer Vision
    • Open-vocabulary scene graph generation (OVSGG), Visual-semantic representation

🎓 Education

  • M.S. in AI Robotics, Sejong University | 2025.09 – Present
  • B.S. in AI Robotics, Sejong University | 2018.03 – 2025.08

🔬 Research Experience

  • Researcher, Sejong RCV Lab, Sejong University | 2023.07 – Present

📄 Publications

  • TAME: Temporal-Aware Mixture-of-Experts for Text-Video Retrieval IEEE Access, Jan. 2026 | Ui-Cheol Jung, Juyoung Hong, Yukyung Choi | 📄 Paper | 💻 Code
  • Visual-Semantic Hierarchical Learning for OVSGG Under Review | Geuntaek Lim, Juyoung Hong, Ui-Cheol Jung, Yukyung Choi
  • Self-supervised Learning for Multispectral Pedestrian Detection ICROS Journal, May 2025 | Jae-Yeon Heo, Ui-Cheol Jung, Yujin Hwang, Yukyung Choi

⚡Research Projects

  • Role: Program planning, recruitment, and system pipeline design.
  • Developed System: AutoFolio
    • Automated developer portfolio system leveraging GitHub activity logs.
    • Designed to track participant progress and generate portfolio artifacts automatically.
  • Tech Stack: LangGraph, Vision-Language Models (MLLMs), FastAPI, VectorDB

[IITP] Development of Multimodal Data Input-based Search Augmented Generation Technology

  • Related Area: Retrieval-Augmented Generation (RAG), Multimodal Large Language Models (MLLM)
  • Role: Researcher | Cross-modal (Text/Image/Video) retrieval and indexing

🛡️ Patents & SW

  • Patent | Method and apparatus for OVSGG based on Deep Learning (KR 10-2025-0048046)

🥇 Awards

Grand Prize, Sejong AI Challenge 2025S


Popular repositories Loading

  1. smart_pill smart_pill Public

    C++

  2. ML_Competition ML_Competition Public

    Forked from lastdefiance20/ML_Competition

    kaggle(캐글), dacon(데이콘) 등 데이터 경진대회 참가 코드 저장소

    Jupyter Notebook

  3. AI_Kaggle_Practice AI_Kaggle_Practice Public

    Forked from SeonminKim1/AI_Kaggle_Practice

    Kaggle 경진대회 코드리뷰

    Jupyter Notebook

  4. modern-software-dev-assignments modern-software-dev-assignments Public

    Forked from mihail911/modern-software-dev-assignments

    Assignments for CS146S: The Modern Software Dev (Stanford University Fall 2025)

    Python

  5. lmms-eval lmms-eval Public

    Forked from EvolvingLMMs-Lab/lmms-eval

    One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

    Python

  6. Awesome-Video-Datasets Awesome-Video-Datasets Public

    Forked from xiaobai1217/Awesome-Video-Datasets

    Video datasets

AltStyle によって変換されたページ (->オリジナル) /