Skip to content
View Mephisto405's full-sized avatar
๐ŸŽฏ
Focusing
๐ŸŽฏ
Focusing

Block or report Mephisto405

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
Mephisto405/README.md

In-Young Cho / ์กฐ์ธ์˜

ciy405x@gmail.com / (+82) 10-9504-8680 / Seoul, South Korea / LinkedIn

Machine Learning Engineer with 4 years of experience since 2021.
Focus: 3D Deep Learning, Generative Models, Cross-Platform Systems, Performance Optimization.

Currently building production-ready 3D content generation pipelines based on diffusion and language models.
Main interest: making 3D ML models run faster, cheaper, and more useful for games, graphics, and visual applications.


Selected Projects


Tech Stack

  • Languages: Python, C++, JavaScript
  • Frameworks: PyTorch, TensorFlow, ONNX
  • Graphics: CUDA, OpenGL, WebGL
  • Infra/Tools: Unreal Engine, Blender

Background

  • Current: ML Engineer at KRAFTON (the PUBG company), deploying AI-driven content creation pipelines
  • Previous: ML Engineer at SPACEWALK, optimizing architectural design via reinforcement learning (RL)
  • Education:
    • MS in Computer Science, KAIST
      • Thesis on Monte Carlo rendering denoising
      • GPA 4.25 / 4.30
    • BS in Computer Science and Mathematics, KAIST
      • GPA 4.00 / 4.30
      • Double major
      • Dean's List (Top 3%) for 3 consecutive semesters
    • Most enjoyably immersed courses: Computer Graphics, Operating Systems, Real/Complex/Numerical Analysis, Linear Algebra, Matrix Computation, 3D Machine Learning, and GPU Programming
    • Advised and mentored 50 undergraduate students as a counseling assistant

Pinned Loading

  1. WCMC Public

    Weakly-Supervised Contrastive Learning in Path Manifold for Monte Carlo Image Reconstruction [Cho et al. SIGGRAPH 2021]

    Python 32 3

  2. OptaGen Public

    Optix-based automated data generation tool

    C 2

  3. Learning-Loss-for-Active-Learning Public

    Reproducing experimental results of LL4AL [Yoo et al. 2019 CVPR]

    Python 218 50

  4. Unsupervised-Out-of-Distribution-Detection-by-Maximum-Classifier-Discrepancy Public

    Reproducing experimental results of OOD-by-MCD [Yu and Aizawa et al. ICCV 2019]

    Python 30 3

  5. NeRF-Reproduce Public

    CS492 3D-ML Term Project by In-Young Cho

    Python 5

  6. Accelerated-Ray-Tracing-in-One-Weekend-in-CUDA Public

    Inspired by https://devblogs.nvidia.com/accelerated-ray-tracing-cuda/

    C++