Hyun Choi

Undergraduate Student · Yonsei University

A portrait of Choi Hyun

Education

Yonsei University
B.S. in Electrical and Electronic Engineering (Expected Aug 2026)
Mar 2020 - Present

Employment

Genoray FlexLab (Medical Imaging Company)
AI Intern - Fine-tuned Segment Anything Model (SAM) for dental X-ray segmentation. Developed LoRA-based tuning strategies and integrated results into a semi-automatic labeling tool.
Jun 2025 - Aug 2025
Seoul, Korea
Reinforcement Learning Tutoring
Tutor at Yonsei University covering key reinforcement learning algorithms and implementation techniques
Mar 2025 - Jun 2025
Yonsei University
SK hynix Volunteer Program
Mentored middle and high school students in basic Python programming and algorithmic thinking
May 2024 - Dec 2024
Seoul, Korea
Math Academy
Assistant Teacher supporting teaching and student management in high school math curriculum
Jan 2020 - Jun 2021, Jan 2023 - Dec 2023
Seoul, Korea

Projects

Portfolio Migration Agent (rewrite-my-report)
H. Choi
PDF 보고서를 포트폴리오용 마크다운으로 재작성하고 Notion에 한 번에 저장하는 에이전트. Upstage Document Parse + Solar LLM, Streamlit UI, Notion API 연동.
Personal Project
Adder Tree (12-input → 4-bit) — Schematic-to-Layout Integration
H. Choi
Tree-based compressor reducing 12 one-bit inputs to 4-bit output using Full Adders and Half Adders. FreePDK45 technology with KLayout/ngspice. DRC PASSED, hierarchical LVS analyzed with improvement plan.
Digital Circuit Design Course Project
AI Agent Orchestrator System
H. Choi, . , . , . , .
🏆 1st Place Winner! MCP and LangGraph-based AI agent orchestration system for centralized personal work information management with automated daily briefing.
Meta x Llama Academy Final Project
SAM Fine-tuning for Medical Imaging
H. Choi, Y. Uhm
Fine-tuned Segment Anything Model (SAM) for dental X-ray segmentation using LoRA-based tuning strategies. Joint first authorship with Yoonhee Uhm.
Genoray FlexLab Internship Project
CIFAR-100 Long-Tail Classification Project
H. Choi
Built hierarchical scheme clustering 100 classes into 20 superclasses with L_class + α·L_superclass. Applied two-stage retraining with class-balanced sampling and LDAM. Results: Overall Top-1 48.8% → 75.7%, Tail 36.6% → 70.3%.
Deep Learning Lab Course Project
차세대 지능형 드론 정비 시스템
H. Choi, S. Seo, D. Kim, S. Lee
🏆 우수상 수상 (43개 팀 중 2등)! MFC 내 드론 자동 정비 시스템 PoC 구현. Elephant Robotics의 MyAGV2023와 Cobot320을 활용한 Smart Factory 및 CMMS 구축.
Robotics Course Project
Speed Estimation from Road Scene Sequences
H. Choi
3D-CNN + LSTM model for 6-frame sequences; ablations on dropout, LR schedulers, test-time normalization; MAE = 1.82.
Introduction to Artificial Intelligence Course Project