Jinuk Kim

Hello! I am a 3rd year PhD student at Seoul National University, Computer Science department, Machine Learning Lab, advised by Hyun Oh Song.

I have worked on ML model (e.g. LLMs and diffusion models) compression and efficiency. Going forward, I aim to build domain-specific LLM agents and tools for hardware design, CUDA programming, and scientific workflows. Refer to my Research Statement for more details.

CV / Scholar / Github / Twitter / Blog / LinkedIn

Updates

Sep 2025 One paper got accepted in NeurIPS 2025 as an oral presentation (KVzip).

Aug 2025 I have been awarded the Youlchon AI Star Scholarship.

Jun 2025 I have been awarded the Presidential Science Scholarship for Graduate Students (full Ph.D.).

May 2025 One paper got accepted in ICML 2025 (GuidedQuant).

Aug 2024 I will be joining Google as a Student Researcher.

May 2024 One paper got accepted in ICML 2024 (LayerMerge).

Apr 2024 I have been awarded the Presidential Science Scholarship for Graduate Students (full M.S.).

Aug 2023 I will be joining Samsung Advanced Institute of Technology as a Research Intern.

May 2023 One paper got accepted in ICML 2023 (Efficient-CNN-Depth-Compression).

May 2022 One paper got accepted in ICML 2022 (Efficient-Dataset-Condensation).

Highlights

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.

Publications

	KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction Jang-Hyun Kim, Jinuk Kim, Sangwoo Kwon, Jae W. Lee, Sangdoo Yun, Hyun Oh Song NeurIPS 2025 Oral Presentation (77/21575=0.35%) *ICML 2025 ES-FoMo-III Workshop* Paper \| Code \| Project page \| Bibtex
	GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance Jinuk Kim, Marwa El Halabi, Wonpyo Park, Clemens JS Schaefer, Deokjae Lee, Yeonhong Park, Jae W. Lee, Hyun Oh Song *ICML 2025* Paper \| Code \| Project page \| Poster \| Bibtex
	LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging Jinuk Kim, Marwa El Halabi, Mingi Ji, Hyun Oh Song *ICML 2024* Paper \| Code \| Project page \| Poster \| Bibtex
	Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming Jinuk Kim, Yeonwoo Jeong, Deokjae Lee, Hyun Oh Song *ICML 2023* Paper \| Code \| Project page \| Bibtex
	Dataset Condensation via Efficient Synthetic-Data Parameterization Jang-Hyun Kim, Jinuk Kim, Seong Joon Oh, Sangdoo Yun, Hwanjun Song, Joonhyun Jeong, Jung-Woo Ha, Hyun Oh Song *ICML 2022* Paper \| Code \| Bibtex

Miscellaneous

I own a SO100 robot, which I sometimes play with and teach to do things.

	Talk-to-President is a service that allows you to chat with AI personas of the presidential candidates in the voice of the candidates.
	VibeCite uses your Claude Code to search and generate bibtex entries from your high-level paper descritions.
	SNU Board is an Android/iOS service which collects notices from website of SNU departments and gather them (Android / Aug 2021 / 100+ MAU / 80+ WAU / 1000+ Downloads).

Academic Services

Conference Reviewer: TMLR 2024-, ICML 2025-, NeurIPS 2025-, ICLR 2026-

Last updated: September 19, 2025. Template based on Jon Barron's website.