I build practical multimodal AI systems across visual editing, scene understanding, video understanding, and audio-visual learning.
Hello! I am a master's student in the 3D Vision & Robotics Lab at UNIST, advised by Prof. Kyungdon Joo.
I was a visiting student in the CARTE, MIE, at the University of Toronto through the AI Convergence Program, supported by the IITP, Korean Government.
My research has focused on 3D scene understanding, image manipulation using generative models, video understanding, and visual-language modeling. Currently, I am expanding my research scope to audio-visual modeling, where I am developing and evaluating multimodal learning frameworks.
The Teo Wiki explains my research map, projects, open questions, and public-facing research identity.
Under construction for details. The cards below summarize current and past project directions.
2025 · Diffusion Model · Image Editing
2024 · Video Anomaly Detection · Industrial AI
2024 · Human-Robot Interaction · LeRobot
2024 · Gaussian Splatting · CLIP
2025 · Generative AI · Image Editing
Research, industry, and product-facing work across multimodal AI systems.
University of Toronto · CARTE, MIE
Graduate study and industry-facing research through the AI Convergence Program.
3D Vision & Robotics Lab · UNIST
Research on video understanding, language-guided 3D scene understanding, and practical multimodal AI.
Built product-oriented software and model components for infrastructure diagnostics and community services.
Computer Vision Lab · University of Seoul
Studied representation learning and built AI components for visual analysis in urban forest management.
A compact academic timeline focused on advisors, degree stage, and research direction.
UNIST
University of Seoul