Hi, I'm Daniel Lee . Building intelligent systems and exploring the intersection of AI Agents and Multimodal Applications. Currently, I am expanding my research from text-based RAG to Vision-Language Models (VLM) and Graph RAG to solve complex real-world problems.

2025

• Top Excellence Award (1st Prize)
  • KU Industry-Academic Capstone Design Competition | Project: DocScanner - Agentic RAG Legal Assistant
• Top Excellence Award (Institute for Information & Communication Technology Planning & Evaluation Director's Award)
  • 10th SW Talent Festival | Project: Smart Food Research Agent System
• Silver Medal
  • Korea University Uni-con Startup Competition | Project: e:room - AI Roommate Matching & Fraud Detection Platform

• [HCLT 2025] Enhancing Multi-Hop Complex Query Retrieval Efficiency through the Integration of RAG and Graph RAG
  • 1st Author | The 37th Annual Conference on Human and Cognitive Language Technology
  • Proposed a hybrid framework combining RAG and Graph RAG to optimize search efficiency for complex queries.

IP-to-Portrait - High-Fidelity Face Synthesis Pipeline

• Advanced AI Pipeline: End-to-end face synthesis preserving identity, background, and lighting using SDXL Inpainting & IP-Adapter FaceID Plus v2.
• Multimodal Integration: Auto-prompting via Gemini 2.5 Flash VLM and precision masking with BiSeNet & InsightFace.
• Tech: Next.js, FastAPI, Celery, Redis, PyTorch, Diffusers, ONNX Runtime.

GitDeck - Developer Profile & Blog Platform

• GitHub Profile README Editor with real-time preview and bidirectional sync.
• Developer blog platform with social features (follow, like, comments, notifications).
• Tech: Next.js 14, FastAPI, PostgreSQL, CodeMirror 6, BlockNote, Gemini/OpenAI.

Docscanner.ai - Legal Tech Solution

• 🏆 Top Excellence Award (KU Capstone Design Competition)
• Contract Analysis AI: Automatically detects toxic clauses, missing items, and unfair terms in employment contracts.
• Tech: Next.js, FastAPI, Gemini, OpenAI, KURE-v1 (Legal Embedding), Elasticsearch.

Cardealo - Location-based Card Benefit Platform

• KU Software Engineering Course Project
• LBS Real-time Recommendation: Automatically analyzes and recommends the optimal credit card for nearby stores based on location data.
• Tech: React Native, FastAPI, PostgreSQL, Gemini API, Naver Cloud Platform.

Smart Food Research Hub (Crowdworks x KU)

• 🏆 Top Excellence Award (10th SW Talent Festival)
• Developed a Multi-Agent RAG system for the food industry using Crawlers, Graph DB, and Elasticsearch.

Research Focus

• Multimodal AI & Vision-Language Models (VLM)
• Retrieval-Augmented Generation (RAG) & Graph RAG
• Multi-Agent Systems & Legal AI

AI apps, demos & services

Impl of Multimodal model

Scheduling, Logic, Multicycle

Currently Learning: Large Multimodal Models (LMM), Graph Neural Networks, Advanced RAG

"Building AI systems that change the world, one intelligent solution at a time."

Visualizing my coding activity and commits over the last year.

Thanks for visiting!
"Code is like humor. When you have to explain it, it's bad." – Cory House