Hyunmin Choi

CASYS Lab, KAIST

profile.jpg

E3-1, KAIST, Daejeon, South Korea

hmchoi@casys.kaist.ac.kr

About Me

I am a Ph.D. student in the School of Computing at KAIST, advised by Prof. Jongse Park in CASYS Lab. I received my master’s degree from KAIST in August 2026 and began my Ph.D. in September 2026, continuing in the same lab with Prof. Park.

Research Interests

  • LLM Inference Serving System Acceleration & Optimization
  • Distributed & Large Scale System
  • LLM accelerators (especially NPU, PIM)

Education

2020.03 - 2024.08 : Bachelor’s degree in School of Computing, KAIST

2024.09 - 2026.08 : Master’s degree in School of Computing, KAIST

2026.09 - Present : Ph.D. program in School of Computing, KAIST (Advisor: Prof. Jongse Park, CASYS Lab)

Experiences

  • 2022.8 - 2024.8 : Undergraduate Student Intern, CASYS Lab (Prof. Jongse Park)
  • 2024.2 - 2024.6 : KAIST Undergraduate Research Program (advisor : Prof. Jongse Park)

Publication

Simthesizer: An Agent-Driven Simulation Framework for LLM Serving Systems
Wonung Kim*, Hyunmin Choi*, Minsu Kim, Jaehong Cho, Yeongwook Kim, Jongse Park (*Equal Contribution)
arXiv preprint, 2026 Paper

A Simulator for LLM inference systems exploiting CXL memory pools
Jinghan Huang, Hongkun Zeng, Mike Montano, Jaehong Cho, Hyunmin Choi, Jinin So, Junhyeok Im, Handeok Lee, Jongse Park, Nam Sung Kim
IEEE Computer Architecture Letters (CAL), 2026 Paper

LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure
Jaehong Cho*, Hyunmin Choi\*, Guseul Heo, Jongse Park (*Equal Contribution)
ISPASS, 2026 Paper (Best Paper Award)

LLMServingSim2.0: A Unified Simulator for Heterogeneous Hardware and Serving Techniques in LLM Infrastructure
Jaehong Cho, Hyunmin Choi, Jongse Park
IEEE Computer Architecture Letter (CAL), 2025 Paper

LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale
Jaehong Cho, Minsu Kim, Hyunmin Choi, Guseul Heo, Jongse Park
IISWC, 2024 Paper (Best Paper Award & Distinguished Artifact Award)

LLMServingSim: A Simulation Infrastructure for LLM Inference Serving Systems
Jaehong Cho, Minsu Kim, Hyunmin Choi, Jongse Park
ISCA Workshop on ML for Computer Architecture and Systems (MLArchSys), 2024 Paper

NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing
Guseul Heo, Sangyeop Lee, Jaehong Cho, Hyunmin Choi, Sanghyeon Lee, Hyungkyu Ham, Gwangsun Kim, Divya Mahajan, Jongse Park
ASPLOS, 2024 Paper