Memory-Efficient Foundation Model Inference
Designing memory-efficient ML algorithms and software systems for inference in foundation models, including large language models and diffusion models.
I am an M.S. candidate in the Department of Computer Science and Engineering at Seoul National University. I am fortunate to be advised by Prof. Jae W. Lee, Director of the AI Institute of Seoul National University, and am a member of the Architecture and Code Optimization (ARC) Lab. I also collaborate with Prof. Sehoon Kim, an Assistant Professor at KAIST AI, who co-advises my current research in ML systems.
I am interested in efficient computing through the co-design of algorithms, systems, and architectures. My current research focuses on improving foundation model inference across transformer, diffusion, and linear-attention architectures. I aim to build highly efficient ML systems that bridge the gap between foundation models and the practical constraints of their underlying hardware.
Designing memory-efficient ML algorithms and software systems for inference in foundation models, including large language models and diffusion models.
Designing memory and storage architectures for efficient computing, in collaboration with Samsung and SK hynix to address real-world industry challenges.
2026-09 — present
Advanced Computer Architecture (4190.571)
2023-09 — 2025-06
Introduction to Algorithms, Computer Organization and Design, Digital System Design, and Microelectronics.
2021-05 — 2023-02
2025-09 — present
2019-03 — 2025-08
2017-03 — 2019-03
For research discussions and collaborations, email me at om0127@snu.ac.kr.