Jinuk Kim

Hello! I am a 2nd year PhD student at Seoul National University, Computer Science department, Machine Learning Lab, advised by Hyun Oh Song. My research interests lie in constructing efficient machine learning system by solving tractable discrete and continuous optimization problem. I completed my Bachelors in Statistics from Seoul National University in 2023.

CV   /  Scholar   /  Github   /  Twitter   /  Blog   /  LinkedIn

profile photo

News
  • May 2024 One paper got accepted in ICML 2024. See you in Vienna!

Publications
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

We propose LayerMerge, a novel depth compression method that selects which activation layers and convolution layers to remove, to achieve a desired inference speed-up while minimizing performance loss.

Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming
Jinuk Kim*, Yeonwoo Jeong*, Deokjae Lee, Hyun Oh Song
ICML, 2023
Paper | Code | Blog | Bibtex

We propose a subset selection problem that replaces inefficient activation layers with identity functions and optimally merges consecutive convolution operations into shallow equivalent convolution operations for efficient inference latency.

idc
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

We propose a novel condensation framework that generates multiple synthetic data with a limited storage budget via efficient parameterization considering data regularity and develop an effective optimization technique.


Projects
caricature
SNU Board
Code

Android/iOS service which collects notices from website of SNU departments and gather them (Android / Aug 2021 / 100+ MAU / 80+ WAU / 1000+ Downloads).


Template based on Jon Barron's website.