Skip to content
View gyoenge's full-sized avatar

Organizations

@Gist-Cactus @EC3102-Mobilex-Chunsik @tave-16th-medivision

Block or report gyoenge

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.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
gyoenge/README.md

Huigyeong Son

GIST Undergraduate, Electrical Engineering and Computer Science (2022–Present)

저는 AI 기술을 활용해 현실 세계의 다양한 문제를 해결하는 것에 관심을 가지고 있습니다.

주요 관심 분야는 Multimodal AI으로, Vision-Language Model (VLM)과 Large Language Model (LLM)을 공부하고 있습니다.

현재 GIST AI-MED Lab에서 학부연구생으로 활동하며 의료 데이터를 활용한 AI 연구를 수행하고 있습니다.

특히 병리 이미지와 유전자 발현 시퀀스 데이터를 다루며 데이터 처리, 구축 및 학습 파이프라인 설계 경험을 쌓고 있습니다.

새로운 도메인에 대한 이해를 바탕으로 문제를 정의하고 해결 전략을 설계하는 과정에 흥미를 가지고 있습니다.

Interests

  • Multimodal AI
  • Representation Learning
  • Domain-specific ・ Real-world AI Application
  • Machine Learning ・ Deep Learning ・ Data Engineering

Tech Stack

Category Stack
AI / ML Python · PyTorch · Transformers · Hugging Face
Data NumPy · Pandas · Medical Data Processing · Image Processing
Tools Linux · Docker · Git · GitHub

Pinned Loading

  1. STaRN STaRN Public

    [Updating] STaRN: Summary Table Representation Learning with Semantic Neighborhood Distillation. Learning spatially coherent radiomics representations from pathology neighborhoods using foundation …

    Python 1

  2. hest-radiomics hest-radiomics Public

    Radiomics-based feature extraction pipeline for the HEST dataset using PyRadiomics and CellViT, supporting intensity, texture, cell-shape, and cell-composition descriptors.

    Python 2

  3. vlm-paper-review-ko vlm-paper-review-ko Public

    📑 VLM (Vision-Language Model) ・ LLM ・ VLA 등 멀티모달 AI와 에이전트 AI 분야의 주요 논문을 한국어로 리뷰하고 정리하는 저장소입니다. 모든 리뷰는 Read the Docs를 기반으로 문서화하고 관리합니다.

    1

  4. 3DMedSAM-FDA 3DMedSAM-FDA Public

    Forked from tave-16th-medivision/3DMedSAM-FDA

    3D SAM with FDA(Frequency-based Dual-path Adapter) for Prompt-based Volumetric Medical Image Segmentation

    Jupyter Notebook 1

  5. scpc-gallery-vqa scpc-gallery-vqa Public

    DACON 2025 AI SCPC(Samsung Collegiate Programming Challenge). Developing a multimodal AI model to understand everyday photos in smartphone user galleries.

    Python 1

  6. robust-photometric-stereo robust-photometric-stereo Public

    Coding Assignment 1 of GIST Computer Vision course (EC4216). Robust Photometric Stereo with RPCA and photometric factor weighting for accurate surface normal estimation and relighting.

    Python 2