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), Insole pressure, and mocap data, and develop efficient and robust deep learning models using LLMs/MLLMs.
Learning Debiased and Interpretable Representations via Explanable AI (XAI).
Semantic Segmentation & Object Detection for autonomous driving in various environments (e.g. overcoming limited field-of-view issues & diverse corruptions and weather conditions) with a lightweight model.
Improving accuracy as well as efficiency of a model.
By leveraging topological feature and multimodalities, (language, image, time-series as well as latent representations, etc.) 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.
2026년 개인기초연구(과기정통부)(R&D) 신진연구 유형B - 정밀한 라이프로그 분석을 위한 멀티모달 기반 설명가능 경량 인공지능 연구 (Explainable Lightweight AI Based on Multimodal Data for Precise Life-log Analysis)
전문기관: 한국연구재단
주관기관: 서울과학기술대학교
2026.03.01-2030.02.28
2026년 ST연구진흥 과제 랩투랩 (B유형) - 파운데이션 모델 기반 AI인지능력 개선을 위한 개념적 및 계산적 방법 연구
SeoulTech (2026.03.09-2027.02.28)
Understanding Latent Semantics for Improved Multimodal Analysis
SeoulTech (2026.04.01-2027.03.31)
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
신임교수 Step-UP 연구기자재 지원사업
SeoulTech (2024.11.15-2027.01.15)
Geometric methods for effective model learning in artificial intelligence
SeoulTech (2025.05.01-2026.04.30)
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)