We are pleased to announce that Professor Seulki Lee has joined the School of Electrical Engineering as of February 4, 2026. We warmly welcome him to our school.
Professor Lee’s office is located in Kim Beang-Ho KIM Sam-Youl ITC B/D (N1). Professor Lee’s research focuses on Embedded AI (On-device AI), real-time, mobile, and sensing systems, AIoT (AI + IoT), intelligent edge systems, and deep learning compilers. He conducts research with the goal of advancing embedded artificial intelligence technologies. His work addresses the challenges of limited memory, computation, and power in embedded environments, with an emphasis on efficient deep learning optimization, on-device neural architecture search, and real-time AI system design.
For more detailed information about Professor Lee’s research, please visit his website below.
Website: https://sites.google.com/view/embeddedai
< Academic and Professional Profile>
Major Field
- Embedded AI (On-device AI)
- Real-time, Mobile and Sensing Systems
- AIoT (AI + IoT) and Intelligent Edge
- Deep Learning Compilers
Educational Background
- Bachelor Degree, 2009, University of Seoul
- Master Degree, 2018, UNC Chapel Hill
- Doctoral Degree, 2021, UNC Chapel Hill
Career
- Aug. 2021 – Aug. 2025: Assistant Professor, UNIST
- Sep. 2025 – Feb. 2026: Associate Professor, UNIST
Publications
- “Bayesian Code Diffusion for Efficient Automatic Deep Learning Program Optimization,”
USENIX Symposium on Operating Systems Design and Implementation (OSDI), 2025 - “AliO: Output Alignment Matters in Long-Term Time Series Forecasting,”
Annual Conference on Neural Information Processing Systems (NeurIPS), 2025 - “SMMF: Square-Matricized Momentum Factorization for Memory-Efficient Optimization,”
Annual AAAI Conference on Artificial Intelligence (AAAI), 2025 - “CAFO: Feature-Centric Explanation on Time Series Classification,”
SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2024 - “On-NAS: On-Device Neural Architecture Search on Memory-Constrained Intelligent Embedded Systems,”
ACM Conference on Embedded Networked Sensor Systems (SenSys), 2023
Assigned Curricular Plan
- EE.40015 Operating Systems and System Programming for Electrical Engineering
- EE.40014 Embedded Systems
- EE.30031 Introduction to Machine Learning
- EE.30012 Introduction to Computer Architecture
- EE.50016 Embedded Software
- EE.50038 Neural Networks
Vision
We make resource-constrained real-time and embedded sensing systems capable of learning, adapting, and evolving, with the aim of enabling Embedded Artificial Intelligence (Embedded AI or On-Device AI).
Research Plan
- We pursue excellence in research on EE, CSE, and AI.
- We make the world a better place by making real impacts with our research.
- We collaborate with and learn from each other when solving challenging problems.
