Neuroimaging and Artificial Intelligence for Psychiatry Lab

We are a group of people at Yonsei University College of Medicine interested in integrating three domains of expertise: [🧠 Neuroimaging] - [🤖 Artificial Intelligence] - [🧑🏻‍⚕️ Psychiatry]

for

• promoting human mental health and/or
• revealing the mechanism of the higher cognitive capabilities of the human brain

led by Byung-Hoon Kim.

Our research integrates at least two of the above three keywords, as can be highlighted by some of our recent works:

• [🧠] + [🤖] + [🧑🏻‍⚕️]

  • [ICLR 2026] Stochastic Optimal Control for Continuous-Time fMRI Representation Learning
  • [arXiv 2025] Towards a general-purpose foundation model for fMRI analysis
  • [arXiv 2024] Joint-Embedding Masked Autoencoder for Self-supervised Learning of Dynamic Functional Connectivity from the Human Brain

• [🤖] + [🧑🏻‍⚕️]

  • [arXiv 2026] Anonpsy: A Graph-Based Framework for Structure-Preserving De-identification of Psychiatric Narratives
  • [BJPsych 2025] Promises and pitfalls of large language models in psychiatric diagnosis and knowledge tasks
  • [arXiv 2025] PSYCHE: A Multi-faceted Patient Simulation Framework for Evaluation of Psychiatric Assessment Conversational Agents

• [🧠] + [🧑🏻‍⚕️]

  • [BJPsych Open 2024] North Korean defectors with PTSD and complex PTSD show alterations in default mode network resting-state functional connectivity

• [🧠] + [🤖]

  • [European Radiology 2025] Predicting molecular types of adult-type diffuse gliomas based on MRI reports with large language models
  • [arXiv 2025] ContextMRI: Enhancing Compressed Sensing MRI through Metadata Conditioning
  • [Stroke 2024] On-Device Deep Learning to Detect Carotid Stenosis With Smartphones: Development and Validation
  • [arXiv 2024] Improving Factuality of 3D Brain MRI Report Generation with Paired Image-domain Retrieval and Text-domain Augmentation

Byung-Hoon is also leading a team of AI Researchers and Engineers at EverEx along with Hyungjin Chung, with a focus on realizing [🏃🏻 human motion]-centric vision-language models for healthcare applications:

• [🏃🏻] + [🤖]

  • [CVPR 2026] Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs (Findings)
  • [CVPR 2026] ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding
  • [ICCV 2025] CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models
  • [ICCV 2025] VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling
  • [ICCV 2025] SteerX: Creating Any Camera-Free 3D and 4D Scenes with Geometric Steering

For prospective students and researchers who are interested in joining our lab, please contact ✉️ egyptdj (at) yonsei.ac.kr with your cv.