EungGu Yun

AI Researcher at SAIGE working on industrial computer vision — image anomaly detection, efficient inference, and language-assisted vision systems. Previously studied loss landscapes at KAIST Graduate School of AI.

Seoul, South Korea

EmailGitHubScholarLinkedIn
EungGu Yun

Experience

Mar 2023 – Present

Seoul, South Korea

AI Researcher

SAIGE

AI Lab

  • ›Research on image anomaly detection (IAD) systems for industrial inspection.
  • ›Research language-assisted vision models for data-efficient training.
  • ›Conduct TensorRT-based optimization for real-time inference in object detection and tracking.
  • ›Fine-tune VLMs for context-aware industrial safety monitoring.

Jul 2020 – Sep 2020

Seoul, South Korea

Research Intern

Artificial Intelligence Institute of Seoul National University (AIIS)

Deep Representation Learning Research Group (DRL)

  • ›Supervisor: Prof. Wonjong Rhee
  • ›Research on model interpretability and activation on-off patterns.
  • ›Reproduced CNN visualization methods including Grad-CAM, (C)LRP, etc.

Jan 2020 – Feb 2020

Daejeon, South Korea

Research Intern

Electronics and Telecommunications Research Institute (ETRI)

Artificial Intelligence Research Laboratory

  • ›Supervisor: Yoo-mi Park
  • ›Tested and debugged ETRI Deep Learning HPC Platform Dashboard.
  • ›Implemented AlexNet and ResNet models with DL-MDL.

Education

Mar 2021 – Feb 2023

Daejeon, South Korea

M.S. in Artificial Intelligence

Korea Advanced Institute of Science and Technology (KAIST)

Graduate School of AI

Mar 2017 – Aug 2020

Seoul, South Korea

B.S. in Computer Science and Engineering

SungKyunKwan University (SKKU)

Department of Computer Science and Engineering

  • ›Total GPA: 4.33 / 4.5
  • ›Major GPA: 4.47 / 4.5

Publications

Academic Services

Projects

  • Aug 2022 –Feb 2023

    Bayesian Inference for Time-series Data with Missing Values

    Samsung Research

    • ›Developing a Bayesian deep learning method to quantify uncertainty within missing values.
    • ›Proposed multivariate time-series classification model using ObsDropout regularization.
    • ›Validated on PhysioNet 2012, MIMIC-III, and UCI human activity datasets.

  • May 2021 –Jul 2022

    Developing AI-based Emulator for Physics Processes in Numerical Models

    National Institute of Meteorological Sciences (NIMS)

    • ›Research on alternative techniques of physical processes in numerical weather prediction (NWP) based on AI.
    • ›Goal: reduce computational costs and improve accuracy of NWP.

Awards

Skills

Programming

PythonJavaScriptCC++LaTeX

Deep Learning

PyTorchJAXTPU

Systems

LinuxDockerGoogle Cloud

Languages

Korean (native)English (intermediate)