Jinuk Kim (Justin Jinuk Kim)

Hello! I am a 4th year PhD student in the Department of Computer Science and Engineering at Seoul National University, Machine Learning Lab, advised by Hyun Oh Song. I am currently an Applied Scientist Intern at Amazon on the Annapurna Science team. I previously interned at Google in 2024 and Samsung Advanced Institute of Technology (SAIT) in 2023. My PhD research is supported by the Apple Scholars in AIML PhD Fellowship and the Presidential Science Scholarship for Graduate Students.

I work on resource-aware LLM development, spanning pretraining, post-training, and agentic systems, with an emphasis on building capable models and tools under practical compute, memory, and deployment constraints. Previously, I worked on LLM agents for semiconductor design rule checking, as well as post-training LLM quantization, KV-cache compression, neural network depth compression, and dataset condensation.

Refer to my Research Statement for more details.

CV   /  Scholar   /  Github   /  Twitter   /  Blog   /  LinkedIn

• Rule2DRC introduced a benchmark for domain-specific DRC script coding agents in chip design and SplitTester, an execution-guided test generation agent for program selection.

• GuidedQuant proposed an improved objective function and quantization method for large language models.

• LayerMerge and Efficient-CNN-Depth-Compression introduced novel depth compression methods to accelerate inference of CNN and diffusion model.

• Conference Reviewer: TMLR 2024-, ICML 2025-, NeurIPS 2025-, ICLR 2026-
• Acknowledged in: Neural Relation Graph, DICP, and Q-Palette

Last updated: July 2, 2026. Template based on Jon Barron's website.