Neuroimaging & AI
for Psychiatry Lab
We are a group of researchers interested in integrating three domains of expertise: 🧠 Neuroimaging 🤖 AI 🧑🏻⚕️ Psychiatry
for promoting human mental health and revealing the mechanisms of higher cognitive capabilities of the human brain, led by Byung-Hoon Kim.
News
Paper accepted at Journal of Medical Internet Research: Model and Task-Aware Test-Time Scaling Strategies for Large Language and Vision-Language Models in Medicine: Evaluation Study.
Paper accepted at MICCAI 2026: Improving Factuality of 3D Brain MRI Report Generation with Paired Image-Domain Retrieval and Text-Domain Augmentation.
Paper accepted at IEEE Journal of Biomedical and Health Informatics: AutoMedic: An Automated Evaluation Framework for Clinical Conversational Agents with Medical Dataset Grounding.
New grant awarded — IITP: Development of an Integrated Sensory AI Model Based on Brain Neural Principles. ₩751.25M (~$545K). (Co-PI)
Paper accepted at Nature Biomedical Engineering: Towards a General-Purpose Foundation Model for fMRI Analysis.
Paper accepted at Psychiatry Research: Characteristics of subjective well-being and communication in individuals with social anxiety disorder assessed through virtual reality tasks.
Paper accepted at ACL 2026: Anonpsy: A Graph-Based Framework for Structure-Preserving De-identification of Psychiatric Narratives.
Contact
Location
For prospective graduate students and researchers interested in joining our lab, please contact ✉️ egyptdj (at) yonsei.ac.kr with your CV.
Relevant backgrounds include, but are not limited to, computer science, neuroscience, signal processing, and clinical psychology.