Experience

SAIGE

AI Lab • AI Researcher
2023. 03 - Present
Seoul, South Korea
  • Research on Image Anomaly Detection for industrial inspection.

Artificial Intelligence Institute of Seoul National University (AIIS)

Deep Representation Learning Research Group (DRL) • Research Intern
2020. 07 - 2020. 09
Seoul, South Korea
  • Supervisor: Prof. Wonjong Rhee
  • Research on model interpretability and activation on-off patterns.
  • Reproduce CNN visualization methods, including Grad-CAM, (C)LRP, etc.

Electronics and Telecommunications Research Institute (ETRI)

Artificial Intelligence Research Laboratory • Research Intern
2020. 01 - 2020. 02
Daejeon, South Korea
  • Supervisor: Yoo-mi Park
  • Test and debug ETRI Deep Learning HPC Platform Dashboard.
  • Implement AlexNet and ResNet models with DL-MDL to serve as example deep learning models.
Publications

Conference

Language-Assisted Feature Transformation for Anomaly Detection

EungGu Yun, Heonjin Ha, Yeongwoo Nam, Bryan Dongik Lee
ICLR2025

A simple early exiting framework for accelerated sampling in diffusion models

Taehong Moon, Moonseok Choi, EungGu Yun, Jongmin Yoon, Gayoung Lee, Jaewoong Cho, Juho Lee
ICML2024

Learning Dynamic Brain Connectome with Graph Transformers for Psychiatric Diagnosis Classification

Byung-Hoon Kim, Jungwon Choi, EungGu Yun, Kyungsang Kim, Xiang Li, Juho Lee
IEEE ISBI2024

Probabilistic Imputation for Time-series Classification with Missing Data

SeungHyun Kim*, Hyunsu Kim*, EungGu Yun*, Hwangrae Lee, Jaehun Lee, Juho Lee
ICML2023
*: Equal contribution

Traversing Between Modes in Function Space for Fast Ensembling

EungGu Yun*, Hyungi Lee*, Giung Nam*, Juho Lee
ICML2023
*: Equal contribution

Martingale Posterior Neural Processes

Hyungi Lee, EungGu Yun, Giung Nam, Edwin Fong, Juho Lee
ICLR2023
Spotlight

Scale Mixtures of Neural Network Gaussian Processes

Hyungi Lee, EungGu Yun, Hongseok Yang, Juho Lee
ICLR2022

Workshop

A generative self-supervised framework using functional connectivity in fmri data

Jungwon Choi, Seongho Keum, EungGu Yun, Byung-Hoon Kim, Juho Lee
NeurIPS Workshop on TGL2023

Large-scale graph representation learning of dynamic brain connectome with transformers

Byung-Hoon Kim, Jungwon Choi, EungGu Yun, Kyungsang Kim, Xiang Li, Juho Lee
NeurIPS Workshop on TGL2023

Early exiting for accelerated inference in diffusion models

Taehong Moon, Moonseok Choi, EungGu Yun, Jongmin Yoon, Gayoung Lee, Juho Lee
ICML Workshop on SPIGM2023

Journal

Recent advances of radiative transfer emulator in WRF model

Hwan-Jin Song, Soonyoung Roh, Park Sa Kim, Juho Lee, Giung Nam, EungGu Yun, Jongmin Yoon
KOMES2022

Benefits of stochastic weight averaging in developing neural network radiation scheme for numerical weather prediction

Hwan-Jin Song, Soonyoung Roh, Juho Lee, Giung Nam, EungGu Yun, Jongmin Yoon, Park Sa Kim
JAMES2022

Preprint

arXiv2020
Education

Korea Advanced Institute of Science and Technology (KAIST)

Graduate School of AI • M.S. in Artificial Intelligence
2021. 03 - 2023. 02
Daejeon, South Korea
  • Supervisor: Prof. Juho Lee
  • Lab: Statistical Inference and Machine Learning Lab (SIML)
  • Thesis: Traversing Between Modes in Function Space for Fast Ensembling
  • Research interests: Loss landscape, Neural processes
  • GPA: 4.08 / 4.3

SungKyunKwan University (SKKU)

Department of Computer Science and Engineering • B.S. in Computer Science and Engineering
2017. 03 - 2020. 08
Seoul, South Korea
  • Total GPA: 4.33 / 4.5
  • Major GPA: 4.47 / 4.5
Projects

Bayesian inference for time-series data with missing values

Samsung Research
2022. 08 - 2023. 02
  • Developing a Bayesian deep learning method that can quantify uncertainty within missing values.
  • Propose multivariate time-series classification model using a regularization method called ObsDropout.
  • Validate proposed method on PhysioNet 2012, MIMIC-III, and UCI human activity datasets.

Developing artificial intelligence based emulator for physics processes in numerical models

National Institute of Meteorological Sciences (NIMS)
2021. 05 - 2022. 07
  • Research on the developing alternative techniques of physical processes in the numerical weather prediction (NWP) model based on AI to reduce computational costs and to improve the accuracy of NWP.
Awards and Honors

The National Scholarship for Science and Engineering

Korea Student Aid Foundation (KOSAF)
2019 Spring - 2020 Spring
  • Supports undergraduates with strong academic performance in science and engineering.

SungKyun Software Scholarship

SungKyunKwan University (SKKU)
2017 Spring - 2018 Fall
  • Supports students with an outstanding GPA.

Dean's List Award

College of Computing, SungKyunKwan University (SKKU)
2017 Spring - 2019 Fall
  • In recognition of high scholastic achievement. (6 times)