Human-aware AI / Biometrics
Computer Vision / Image & Video Processing / Time-series Data Analysis
Wearable Sensor and Image Data Analysis
Multimodal Data Analysis (LLM, VLM, LMM, etc.)
Knowledge Distillation / Lightweight Model Development
Semantic Segmentation / Object Detection
Deep Learning Algorithm & Processing
Geometric Approach for ML
Explainable AI (XAI) / Reliable AI
Generative AI
For healthcare (disease diagnosis/prediction, injury prevention), we analyze wearable sensors (IMUs) as well as Insole pressure data, and develop efficient and robust deep learning models.
Learning Debiased and Interpretable Representations via Explanable AI (XAI).
Semantic Segmentation for autonomous driving and overcoming limited field-of-view issues with a lightweight model.
Improving accuracy as well as efficiency of a model.
By leveraging topological feature and multimodalities, an improved and efficient model is developed.
Improving performance of models by leveraging gen AI. (T2I, T23D, etc.)
Improving fidelity with better/controllable gen AI.
Improving performance of reliability for AI models.
Improving model reliability as well as accuracy.
제한된 시야의 도로환경에서 Foundation Model 및 멀티모달 데이터 기반 경량 모델 개발
국가슈퍼컴퓨팅센터 RnD 혁신지원 프로그램 (KISTI) (2026.01.01-2026.12.31)
대형차량 사고예방을 위한 온디바이스 AI 분석 솔루션: LaVODA(Large Vehicle On Device AI)
중소기업기술정보진흥원 - 창업성장기술개발(R&D) (2025.07.01-2026.12.31)
주관기관: (주)엑시온
Geometric methods for effective model learning in artificial intelligence
SeoulTech (2025.05.01-2026.05.31)
신임교수 Step-UP 연구기자재 지원사업
SeoulTech (2024.11.15-2027.01.15)
Robustness of topological persistence in knowledge distillation for wearable sensor data
SeoulTech (2024.10.01-2025.05.30)
신임교수 연구정착비 과제
SeoulTech (2024.11.01-2025.10.31)