Sungju Kim (김성주)

Graduate Research Assistant @ CASLAB, Yonsei University

Education

• Ph.D. Student., Dept. of Electrical and Electronic Engineering, Yonsei University, 2025.03 - Present

  • Advisor : Prof. Daehoon Kim.

• M.S., Dept. of Electrical Engineering and Computer Science(EECS), DGIST, 2025.02 

  • Advisor : Prof. Daehoon Kim.

  • Thesis : MX format Quantization Optimization for Lightning-NeRF

• B.S., School of Transdisciplinary Studies, DGIST, 2022.08

Research Interest

• Computer Architecture and Systems

  • [Security] Rowhammer attack defense.

  • [ML System] Optimization machine learning models for specific HW (e.g., NPU, TPU) with Quantization.

News

• 2025.05.19

  • A paper was accepted at ISLPED, a major conference.

• 2025.03.01

  • I entered the Ph.D. program in Electrical and Electronic Engineering at Yonsei University.

• 2025.02.14 

  •  I graduated from DGIST with a master's degree.

• 2024.11.05

  • I passed my master’s thesis defense.

• 2024.07.09

  • A paper was accepted at PACT 2024, a top-tier conference.

Skills

• C / C++ 

• Python 

• Bash Script ( Shell Script ) 

• ML framework 

  • Pytorch

• Computer Architecture Simulation

  • Ramulator / Ramulator2

Teaching Experience

• Teaching Assistant, GEV6154, Multi-core and GPU, Yonsei University, 2025 Fall

• Teaching Assistant, SYS4211, Advanced Operating Systems, Yonsei University, 2025 Fall

• Teaching Assistant, SYS3209, System Programming, Yonsei University, 2025 Spring

• Teaching Assistant, CSE305 Computer Architecture, DGIST, 2024 Spring

• Teaching Assistant, CSE305 Computer Architecture, DGIST, 2023 Spring

• Teaching Assistant in R&E, DGIST with DAEGU IL SCIENCE HIGH SCHOOL, 2023.03 - 2023.12

Projects

• Industry-Academic Cooperation Project, Samsung Electronics, 2025 

• ML Compiler for On-Device AI, IITP-ETRI, 2025 

• Data Utilization Planning and Verification Project (Fine-tuning and Inference of On-Device Generative Models), NIA, 2024 

• Development of On-Device NPU Architecture for Accelerating Generative AI Models, Samsung Research, 2024 

• AI Training Data Construction Project, NIA, 2023 

• Research on Memory-Centric Next-Generation Computing System Architecture, IITP, 2022

Contact

Email : sungju.kim@yonsei.ac.kr 

Address : Engineering Research Park 212D, Yonsei University, 50, Yonsei-ro, Seodaemun-gu, Seoul, Republic of Korea.

OCRID

Google Scholar

Publication

1. (Domestic) CPU 오프로딩을 통한 NPU 기반 대규모 언어 모델 서비스의 성능 최적화 방안 연구

• KSC(한국소프트웨어종합학술대회), 2025

• 장예원, 정찬섭, 전윤형, 김성주, 김대훈*.

2. (Conference)  Jack Unit: An area- and energy-efficient multiply-accumulate (MAC) unit supporting diverse data formats

• IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED), 2025

• Seock-Hwan Noh, Sungju Kim, Seohyun Kim, Daehoon Kim, Jaeha Kung* and Yeseong Kim*

3. (Domestic) 온디바이스 생성모델 어댑터 기반 파인튜닝 및 추론 성능 분석

• KSC(한국소프트웨어종합학술대회), 2024

• 정예지, 김슬기, 김정보, 유경현, 김성주, 신현균, 오선무, 좌훈승, 김대훈*. 

4. (Conference) vSPACE: Supporting Parallel Network Packet Processing in Virtualized Environments through Dynamic Core Management

• International Conference on Parallel Architectures and Compilation Techniques (PACT), 2024

• Gyeongseo Park, Minho Kim, Ki-Dong Kang, YunHyeong Jeon, Sungju Kim, Hyosang Kim, and Daehoon Kim*.