안녕하세요! 👋

저는 Multimodal AI & Generative Model을 연구하는 김종하(Jongha Kim)입니다.

세상 밖으로 나온 무처럼, 끊임없이 배우고 성장하며 새로운 도전을 즐깁니다.


🎓 Education

  • Inha University, Incheon, Korea
    • B.S. in Electronic Engineering
    • Feb. 2019 ~ Aug. 2025
    • GPA: 3.98 / 4.5

🔬 Research Interests

  • Generative Models (Diffusion Models, Transformer-based Architectures)
  • Multimodal AI (Audio-Visual-Text)
  • Video Synthesis (Scene Graph to Video, Talking Face Generation)
  • Speech & Language Processing (SpeechLLM, Medical ASR)

💼 Research Experience

Research Intern

IIP Lab (Intelligent Information Processing Lab), Sogang University
Jul. 2025 ~ Present

  • SCH Medical Domain ASR
  • Contextual Biasing with SpeechLLM

Machine Intelligence Lab, Inha University
Jan. 2024 ~ Dec. 2024

  • Video Synthesis
  • Scene Graph to Video Generation
  • Long Video Generation with Diffusion

Intelligence Embedding System Lab (IESL), Inha University
Jul. 2022 ~ Dec. 2022

  • Computer Vision
  • Robotics and Autonomous Driving

R&D Department, STS Engineering
Mar. 2025 ~ Present

  • ML Scientist and Embedded Engineer

📚 Selected Projects

Multimodal & Video Generation

  • Scene Graph to Video Generation with Diffusion (Aug. 2024 ~ Present)
    Machine Intelligence Lab

  • Korean Audio Unit Translation (Sep. 2024 ~ Present)
    Multilingual Hubert, Transformer, and Vocoder - ECE Capstone Design

AI Competitions

  • Analysis and Q&A on South Korean Economic Articles (Jul. 2024 ~ Aug. 2024)
    Korean LLM Fine-tuning - 2024 Inha Artificial Intelligence Challenge

  • Global Wildfire Detection Challenge (Mar. 2024)
    TransUNet, Attention U-Net - AI Spark Challenge

Computer Vision & Robotics

  • Model Ensemble VIT-SSD (Nov. 2023 ~ Dec. 2023)
    Vision Transformer and Single Shot Detection - ECE Deep Learning

  • Real-time Computer Vision using AWS & Raspberry Pi (Mar. 2023 ~ Aug. 2023)
    Hanium ICT Challenge

  • Vision-based Autonomous Human Following Wheeled Mobile Robot (Sep. 2022 ~ Dec. 2022)
    FVE Alpha Project

Entrepreneurship

  • Startup: Product Development and Branding (Jan. 2023 ~ Jul. 2023)
    Gyeonggi Content Agency - 20 Million KRW Funding

  • SeTA (Social Entrepreneurship Team Academy) (Mar. 2022 ~ Jun. 2022)
    SKKU, MTA Korea - Global Entrepreneurship Training Program

더 많은 프로젝트는 Project 섹션에서 확인하실 수 있습니다.


💻 Technical Skills

Programming Languages

  • Python, C, C++, Linux

AI/ML Frameworks

  • PyTorch (Lightning), TensorFlow

Certifications

  • SQLD (SQL Developer)
  • ADSP (Advanced Data Analytics Semi-Professional)

🏆 Awards & Honors

  • Academic Excellence Scholarship, Inha University (Mar. 2024)
  • Encouragement Prize for Convergence Project, Inha University (Dec. 2022)
  • Encouragement Award, Inha University Winter Break Job Analysis Competition (Jan. 2023)

📝 Conference Publications

  1. Jang Ji-hye, Lee Young-jun, Heo Ji-won, Kim Jong-ha
    “Development of an ROS-based Environmental Perception and Decision-making System for Indoor Autonomous Mobile Robots”
    Korean Society of Automotive Engineers (KSAE), Jeju, Korea (Oct. 2022) - Poster Presentation

🎯 Academic Goals

Short-term (Master’s Program)

  • Advance research on Audio-to-Video Generation (Talking Head, Scene Graph to Video) using diffusion and transformer-based architectures
  • Explore Lightweight Multimodal SpeechLLMs for domain-specific applications (Medical ASR, Speech Q&A)
  • Integrate expertise in low-level vision and generative AI to improve synchronization, realism, and efficiency in multimodal generation

Long-term (Career Goal)

  • Become a leading researcher in AI-based Multimodal Generation
  • Pioneer methods that go beyond unimodal AI
  • Contribute impactful research to build AI systems capable of human-like understanding and communication across languages and modalities
  • Publish at top-tier conferences (CVPR, ICCV, ICLR, NeurIPS)

👨‍🏫 Teaching Experience

Teaching Assistant, Inha University
Sep. 2024 ~ Dec. 2024

  • Deep Learning
  • Introduction to Machine Learning

📄 Resume


📞 Contact


🌱 About This Blog

이 블로그는 제가 공부하고 연구한 내용들을 정리하고 공유하는 공간입니다.

  • Paper Review: 최신 논문 리뷰 및 분석
  • ML: 머신러닝 이론 및 실습
  • Project: 진행한 프로젝트 상세 소개
  • Algorithm: 알고리즘 문제 풀이
  • Startup: 창업 및 비즈니스 경험

함께 성장해 나가요! 😊