Skip to content
Connectome Lab
서울대학교

논문

연구 논문, 2008–2026

뇌의 연결이 마음과 정신건강을 어떻게 만들어 가는지를, 유전체와 뇌영상, 계산 모형을 엮어 물어 온 연구의 기록입니다.

외부 프로필: Google Scholar

게재 유형
77 / 77
2026학회#Quantum ML

Hybrid Quantum Temporal Convolutional Networks

Junghoon Park, Maria Pak, Sebin Lee, Samuel Yen-Chi Chen, Shinjae Yoo, Huan-Hsin Tseng, Jiook Cha

2026 International Conference on Quantum Communications, Networking, and Computing (QCNC)

논문
2026저널#Neuroscience#Psychiatry/Clinical Psychology

Learning brain dynamics across distinct scaling regimes reveals psychiatric signatures

Sangyoon Bae, Junbeom Kwon, Shinjae Yoo, Jiook Cha

Communications Biology

Introduces Multi-Band Brain Net (MBBN), a transformer-based framework that decomposes fMRI signals into biologically grounded frequency bands, achieving state-of-the-art prediction of psychiatric and cognitive outcomes (major depressive disorder, ADHD, autism spectrum disorder) across 49,673 individuals from UK Biobank, ABCD, and ABIDE.

논문
2025워크숍ICML 2025 Workshop Spotlight#AI & Foundation Models#Neuroscience

DIVER-0: A Fully Channel Equivariant EEG Foundation Model

Dong Yeop Han, Ahhyun Lee, Taeyang Lee, Sebin Lee, Jiook Cha

ICML 2025 Workshop on Generative Biology (Spotlight)

We introduce DIVER-0, a novel channel-equivariant foundation model for electroencephalography (EEG). By enforcing strict spatial permutation and continuous coordinate equivariance, DIVER-0 natively handles heterogeneous montage configurations without requiring spatial interpolation or channel re-referencing.

2025저널Molecular Psychiatry 2025#Genetics#Psychiatry/Clinical Psychology

Polygenic scores for psychiatric traits mediate the impact of multigenerational history of depression on offspring psychopathology

Eunji Lee, Milenna T. van Dijk, Bogyeom Kim, Gakyung Kim, Eleanor Murphy, Ardesheer Talati, Yoonjung Yoonie Joo, Myrna M. Weissman, Jiook Cha

Molecular Psychiatry

This study demonstrates how psychiatric polygenic risk profiles functionally mediate the transgenerational transmission of major depressive disorder across family lineages, shaping neurodevelopmental risk pathways in youth.

논문
2025워크숍NeurIPS 2025 Workshop Spotlight#AI & Foundation Models#Neuroscience

NeuroMamba: A State-Space Foundation Model for Functional MRI

Jubin Choi, Jungwoo Seo, Dong Yeop Han, Jiook Cha

NeurIPS 2025 Workshop on Foundation Models for the Brain and Body (Spotlight)

Functional MRI yields high-dimensional 4D spatiotemporal brain recordings that are computationally intractable for quadratic self-attention transformers at scale. We present NeuroMamba, the first selective state-space foundation model architecture for 4D fMRI sequences, enabling linear computational scaling with respect to scan duration and superior transferability across diverse cognitive decoding benchmarks.

논문
2023학회#AI & Foundation Models#Neuroscience

SwiFT: Swin 4D fMRI Transformer

Peter Kim, Junbeom Kwon, Sunghwan Joo, Sangyoon Bae, Donggyu Lee, Yoonho Jung, Shinjae Yoo, Jiook Cha, Taesup Moon

Advances in Neural Information Processing Systems 36

논문