- Fundamentals of Deep Learning by NVIDIA
- Transformer Based Natural Language Processing Models by NVIDIA
- Microsoft Certified: Azure AI Fundamentals by Microsoft
- Microsoft Certified: Azure Data Fundamentals by Microsoft
- Received a B.S. degree in Artificial Intelligence from Jeonju University, Jeonju, Korea, in 2025.
- Pursuing an M.S. degree in Agro AI at Jeonju University, Jeonju, Korea, in 2024 ~ Present.
- Completed an education certificate program at the University of Toronto's C-MORE Lab.
- Worked as a Research Intern at Dareesoft through the WEMEET program.
- Worked as a Research Intern at the Rural Development Administration through the WEMEET program.
-
Graph-based AI & Knowledge Integration
- Knowledge Graph Embedding (TransE, RotatE, DistMult)
- Graph Neural Networks (GNN, Graph Transformer)
- Graph-based Retrieval Augmented Generation (GraphRAG)
- Multi-hop reasoning over structured knowledge
-
Small Language Model (SLM) Optimization
- Lightweight model design for on-device / edge environments
- Parameter-Efficient Fine-Tuning (PEFT, LoRA)
- Efficient inference and memory optimization
- Retrieval and reasoning optimization for compact models
-
Multi-Agent Systems (A2A / LLM Agents)
- Agent-to-Agent (A2A) communication frameworks
- Task decomposition and cooperative reasoning
- Multi-agent orchestration using LLMs
- Integration of external tools and knowledge sources
-
Large Language Model (LLM) Optimization
- Retrieval-Augmented Generation (RAG)
- Prompt engineering and structured output generation
- Model efficiency and scaling strategies
-
Generative Models using Deep Learning
- GAN, VAE, Diffusion Models (DDPM, Score-based)
-
Computer Vision & Medical AI
- Image Segmentation (U-Net, DeepLab, Mask R-CNN)
- Medical Image Analysis (Brain Tumor Segmentation)
- Anomaly Detection (OOD, Reconstruction-based)
- Code for Research
- Knowledge Graph Large Language Model (KG-LLM) for Link Prediction
- Knowledge Graphs as Context Sources for LLM-Based Explanations of Learning Recommendations
- Generate-on-Graph: Treat LLM as both Agent and KG for Incomplete Knowledge Graph Question Answering
- Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
- A Survey of Methods for Brain Tumor Segmentation Based on MRI Images
- Edge U-Net: Brain Tumor Segmentation Using MRI Based on Deep U-Net Model with Boundary Information
- FU-net: Multi-class Image Segmentation Using Feedback Weighted U-net
- Using a Generative Adversarial Network to Generate Synthetic MRI Images for Multi-class Automatic Segmentation of Brain Tumors
- Edge-Boosted U-Net for 2D Medical Image Segmentation
- A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking
Β
- linkedin: https://www.linkedin.com/in/yurim-oh-96709516a/
- email: [email protected]
- Python
- Jupyter Notebook
- PyTorch
- TensorFlow
- Keras
- Pandas
- NumPy
- Scikit-learn (sklearn)
- OpenCV (cv2)
- Ultralytics
- LangChain
- LlamaIndex
- Docker
- Kubernetes
- vLLM (LLM Serving)
- OpenWebUI (LLM Interface)
- LangGraph (Agent Workflow)
- Neo4j (Graph Database)
- SQL (SQLGate)
- Jenkins
- Nexus (Artifact Repository)
- Linux Server Environment
- Nginx (Reverse Proxy)
- WebSocket / API Integration