Jinhyeok Kim

Short Bio

• I am pursuing an Integrated M.S./Ph.D. in Electrical and Computer Engineering at Seoul National University, advised by Prof. Jaeyoung Do. My research focuses on efficient LLM inference and serving, GPU kernel optimization, and algorithm-system co-design for artificial intelligence.

Education

• • Integrated M.S./Ph.D. in Electrical and Computer Engineering, Seoul University(Mar. 2025 - Present)

Advisor: Prof. Jaeyoung Do

• • B.S. in Electrical and Electronic Engineering, Yonsei University (Mar. 2019 - Feb. 2025)

Research Experiences

• • Graduate research asistant at Electrical and Computer Engineering, Seoul National University, AIDAS Lab, Korea (Mar. 2025 - )

  • Research intern at Electrical and Computer Engineering, Seoul National University, AIDAS Lab, Korea (Jul. 2024 - Feb.2025)

• Research intern at Electrical and Electronic Engineering, Yonsei University, Information Communications & Security Lab, Korea (Jan. 2024 - Feb. 2024)

Publication

For details, see my google scholar for a complete publication list.

• • [arXiv] Jaeik Kim, Woojin Kim, Jihwan Hong, Yejoon Lee, Sieun Hyeon, Mintaek Lim, Yunseok Han, Dogeun Kim, Hoeun Lee, Hyunggeun Kim, Jinhyeok Kim, Jaeyoung Do

"Dynin-Omni: Omnimodal Unified Large Diffusion Language Model"

• • [VLDB 2026] Jinhyeok Kim, Yejoon Lee, Jaeyoung Do^

"Unified Static-Dynamic Pruning for Efficient LLM Inference"

Skills and Techniques

• Languages : Verilog, RISC-V, C/C++, CUDA, Python, MATLAB, Bash (Shell script)

• Tools & Libraries : PyTorch, Xilinx Vivado, ModelSim, Design compiler

Contacts

If you want to contact me about anything, feel free to reach out anytime using the information below :)

• Mail : jhkim00@snu.ac.kr

• Github

• Linkedin