CV
Contact Information
| Name | Minkyu Park |
| Professional Title | Research Intern, CSArch Lab, Korea University |
| parkparkmk@gmail.com |
Experience
-
2026 - Present Research Intern
CSArch Lab, Korea University
Advisor: Prof. Gunjae Koo.
- Research intern working on computer architecture, memory systems, and energy-efficient system design.
-
2026 - 2026 Research Intern
PSAL, POSTECH
Advisor: Prof. Gwangsun Kim.
- Implemented support for a new ATen operator in PyTorchSim by defining custom lowerings and MLIR-based execution paths.
- Designed and documented an end-to-end contributor tutorial as a GitHub Wiki for extending MLIR-backed ATen operator support.
-
2024 - 2026 Undergraduate Researcher
AIAC Lab, Hallym University
Advisor: Prof. Jeong-Gun Lee.
- Conducted research on Edge AI inference performance modeling, predicting delay, power, energy, and EDP using regression-based approaches.
- Built an experimental measurement pipeline on Jetson Orin Nano for collecting fine-grained runtime and power data.
Education
-
2020 - 2026 B.S.
Hallym University
Big Data
- Cumulative GPA: 4.06 / 4.5
- Junior/Senior GPA: 4.24 / 4.5
- Full Tuition Scholarship, awarded upon admission (4 semesters)
- Full Tuition Scholarship, top-ranked undergraduate student (1st place), Spring 2025
Awards
-
2025 Grand Prize (Minister of Science and ICT Award)
2025 National ICT Smart Device Competition, hosted by the Ministry of Science and ICT
-
2024 2nd Prize
SW Capstone Design Competition, Hallym University, sponsored by the Ministry of Science and ICT
-
2024 3rd Prize & Popularity Award
2024 SW-Central University Digital Competition, hosted by the Ministry of Science and ICT
Publications
-
2026 Predicting Delay, Power, and Energy of Edge AI Inference with Ridge Regression
IEEE International Conference on Consumer Electronics (ICCE 2026)
First-author paper proposing a ridge-regression framework for predicting delay, power, and energy of edge AI inference.
-
2025 Performance and Energy Consumption Analysis of Deep Learning Models on Edge GPU Systems
Proceedings of the Annual Conference of KIPS (ASK 2025), Vol.32 No.1
Analysis of performance and energy consumption characteristics of deep learning models on edge GPU systems.
Languages
English : Proficient (TOEIC 855)
Korean : Native