Daeun Kyung

Daeun Kyung is a Ph.D. student at KAIST AI, advised by Prof. Edward Choi. Her research focuses on large language models (LLMs) and multimodal learning, with a particular emphasis on healthcare applications. She is interested in building and evaluating AI systems that work reliably in real-world settings, spanning dataset curation and model development. Most recently, she has been exploring how LLMs can enable more realistic and grounded clinical interactions. As part of this effort, she developed PatientSim, a persona-driven framework for simulating realistic doctor-patient conversations grounded in real medical records, which was accepted as a Spotlight at NeurIPS 2025 Datasets and Benchmarks. Her work has also appeared at ICLR, CHIL, and ICASSP, where she received the Best Student Paper Award in 2023.