Ph.D. Candidate at Seoul National University (SNU)
Dedicated to solving complex, real-world challenges by leveraging mathematical frameworks and advanced computational methods.
I am currently pursuing my Ph.D. at Seoul National University. I am driven by the potential of data and algorithms to create tangible impact and innovation.
- I'm currently working on Medical AI & Industrial AI & Railroad Science & Computer Science
- I'm looking to collaborate on Open Source AI Projects
- Ask me about Python, PyTorch, C++
My focus lies at the intersection of theoretical foundations and high-impact applications, particularly in the following domains:
- Objective: To develop and deploy robust machine learning models that enhance diagnostic accuracy and efficiency in healthcare systems.
- Focus Areas: Medical Imaging Analysis, Predictive Modeling, Clinical Data Mining.
- Objective: To bring vision and multimodal models into real-world industrial environments for safety monitoring, inspection, and quality control.
- Focus Areas:
- Visual Intelligence: Anomaly & Defect Detection, Real-time Multi-channel Inference, Vision-Language Models (VLM) for Safety-Critical Systems.
- Predictive Maintenance, Fault Diagnosis, Time-Series Analysis, Industrial Inspection & Monitoring.
- Objective: To apply data-driven approaches to railway systems and transportation networks for improved safety and efficiency.
- Focus Areas:
- Logistics Optimization: Routing Algorithms, Demand Forecasting, Inventory Management, Network Optimization.
- Supply Chain Management (SCM), Operations Research, Mathematical Modeling.
- Objective: To design efficient algorithmic solutions and deepen understanding of the mathematical principles underlying computation.
- Focus Areas:
- Algorithms: Algorithm Design, Data Structures, Competitive Programming, Computational Complexity.
- Mathematics: Linear Algebra, Optimization Theory, Probability, Discrete Mathematics.
- LOSA-NET: A LOCALIZED AND SCALE-ADAPTIVE NETWORK FOR BOUNDARY-SENSITIVE PREDICTION OF PERINEURAL INVASION IN 3D MRI - IEEE ISBI 2026 (Oral)
- MMA-FORMER: MULTI-WINDOW MIXTURE-OF-HEAD ATTENTION TRANSFORMER FOR ADAPTIVE PNI PREDICTION IN 3D MRI - IEEE ISBI 2026 (Oral)
- NeoNet: An End-to-End 3D MRI-Based Deep Learning Framework for Non-Invasive Prediction of Perineural Invasion via Generation-Driven Classification - Workshop on Health Intelligence (W3PHIAI), AAAI 2026 (Oral)
๐ Full publication list on my Google Scholar.