Jinha Chung

Ph.D. Candidate

Vertically Integrated Architecture (VIA) Research Group
School of Electrical Engineering
Korea Advanced Institute of Science and Technology (KAIST)

N1 818 @ KAIST jinha.chung@kaist.ac.kr

GitHub LinkedIn

Education

KAIST

Mar. 2021 – Present

Integrated M.S. & Ph.D. in Electrical Engineering

Advisor: Prof. Minsoo Rhu

KAIST

Mar. 2016 – Feb. 2021

B.S. in Electrical Engineering, double major in Mathematical Sciences

Cum Laude

Publications

SpecMoE: A Fast and Efficient Mixture-of-Experts Inference via Self-Assisted Speculative Decoding

Jehyeon Bang, Eunyeong Cho, Ranggi Hwang, Jinha Chung, Minsoo Rhu

The 63rd ACM/ESDA/IEEE Design Automation Conference (DAC-63), Long Beach, CA, Jul. 2026

Acceptance rate: 17% (543/)

The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective

Jiin Kim, Byeongjun Shin, Jinha Chung, Minsoo Rhu

The 32nd IEEE International Symposium on High-Performance Computer Architecture (HPCA-32), Sydney, Australia, Feb. 2026

Acceptance rate: 20% (119/602) · GitHub

SmartSAGE: Training Large-scale Graph Neural Networks Using In-storage Processing Architectures

Yunjae Lee, Jinha Chung, Minsoo Rhu

The 49th International Symposium on Computer Architecture (ISCA-49), New York, NY, Jun. 2022

Acceptance rate: 16% (67/400)

Work Experience

Samsung Advanced Institute of Technology (SAIT)

Jun. 2023 – Sep. 2023

Research Engineer Intern

Exploring various use-cases of CXL-PNM

Mentors: Yong Min Tai and Jinsu Park · Manager: Yeongon Cho

VIA Research Group, KAIST

Mar. 2019 – Feb. 2021

Undergraduate Research Intern

Building a TPU cycle-level simulator (Mar. 2019 – Aug. 2019)
Building recommendation system model accelerators (Jan. 2020 – Feb. 2021)

Mentors: Youngeun Kwon and Yujeong Choi · Advisor: Minsoo Rhu

Teaching

EE209: Programming Structure for Electrical Engineering

Spring 2022 — Head TA, Best TA Award
Fall 2023

EE312: Introduction to Computer Architecture

Fall 2021
Fall 2022
Spring 2024

Skills

Areas of Interest

Computer architecture, AI agents, edge devices

Programming Languages

C/C++, Python, Bash (Shell script)

Frameworks

PyTorch, Hugging Face Transformers, MLX

Languages

Korean (Native)

American English (Fluent)

TOEFL iBT: 119/120 (R 29 / L 30 / S 30 / W 30) — Feb. 23, 2019

Achievements

KAIST URP (Undergraduate Research Participation) Program

2018

Second Place — 2018 Summer/Fall and Long-Term URP Workshop

"Implementing Scalable Peer-to-Peer Network Simulation Framework for Comprehensive Vulnerability Assessment of Bitcoin Network"