I am an MSc student at KAIST AI. I am broadly interested in how LLMs can stay reliable and personalised as the knowledge they depend on keeps changing. My research interests are retrieval-augmented generation and retrieval methods, memory systems and personalisation for long-term agents, and knowledge editing through RAG to keep models’ factual knowledge up to date.

Before my graduate studies, I spent six years co-founding and building a deep learning startup, working end-to-end across business, research, and engineering. That experience shaped how I think about research. It is not just a technical problem. It has to hold up in the messy, real-world systems where people actually rely on it.

I would like to build LLM-based systems that can remember, retrieve, and update what they know in a way that is both trustworthy and personalised. My personal page is at seokwonjung-jay.github.io.