About
I'm a first-year Master's student at KAIST's School of Computing, working in the Collaborative Social Technologies Lab under Prof. Joseph Seering. I hold a B.S. in Electrical Engineering from KAIST (Magna Cum Laude, GPA 3.88/4.3).
My research investigates multi-agent LLM dialogue systems—specifically, why AI agents with distinct personalities gradually converge to similar responses during extended conversations, and how cognitive psychology can inform better architectures for genuine collective intelligence.
Before graduate school, I spent 7 months at Samsung Electronics' Device Solution Division developing LLM-enhanced RAG systems, and explored computer vision research including GAN-based image manipulation and audio anomaly detection.
I'm driven by the belief that building better AI systems requires deeply understanding both the technology and the humans who interact with it.
Research Interests
Current
Multi-Agent LLM Dialogue Systems
Why AI agents with distinct personalities converge during extended conversations, and how cognitive psychology informs architectures for genuine collective intelligence.
Collaborative Interaction Analysis
Audio-to-text dataset construction pipelines for analyzing group collaboration, with enhanced speaker diarization through parallelization and speaker embedding.
Previous
LLM & RAG System Optimization
Prompt-Induced Reasoning based query decomposition, relevance checking, and Korean-optimized LLM prompt engineering at Samsung Electronics.
Computer Vision
StyleCLIP-based localized image editing in GAN latent space, audio anomaly detection, and CNN architecture optimization.
Education
March 2026 – Present
Master of Science in School of Computing
Korea Advanced Institute of Science and Technology (KAIST) · Collaborative Social Technologies Lab · Advisor: Prof. Joseph Seering
CurrentMarch 2020 – February 2026
Bachelor of Science in Electrical Engineering
Korea Advanced Institute of Science and Technology (KAIST) · GPA: 3.88/4.3 (95.80/100) · Magna Cum Laude
Tools & Technologies
Python · PyTorch · TypeScript · Next.js · LLM Prompt Engineering · RAG Systems · Framer Motion · Speaker Diarization · GAN-based Image Editing · Data Visualization