Publications

International

1st author

Spectral-Temporal State Space Modeling on Functional Brain Networks

Jaeyoon Sim^*, Hoseok Lee^*, Jihwan Park, Seunghun Baek, Yu Zhang, Won Hwa Kim (^*: Equal Contribution)

C International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Strasbourg, France, 2026

Provisional Accept [~9% Acceptance Rate]

Abstract Project Page BibTeX

Resting-state fMRI (rs-fMRI) offers a powerful tool for analyzing functional organization in brain for neurodegenerative and neurodevelopmental disorders. Although graph-based and spatio-temporal models have shown promise, most existing approaches decouple spatial structure from temporal dynamics or rely on predefined temporal windows, limiting the capacity of spatial information to directly modulate temporal processing. To address these limitations, we propose a spectral-temporal state space framework that integrates graph spectral representations with state-space modeling through a spectral-temporal kernel, enabling window-free and frequency-based temporal modeling. Experiments on three rs-fMRI cohorts with 1,926 subjects demonstrate that our method consistently outperforms competitive baselines across diverse conditions, including Parkinson’s disease, autism spectrum disorder, and attention deficit hyperactivity disorder. In addition, we provide interpretable insights into spectral-temporal patterns of brain dysfunction, advancing the characterization and classification of neurodegenerative and neurodevelopmental disorders.

@inproceedings{sim2026spectral,
title={Spectral-Temporal State Space Modeling on Functional Brain Networks},
author={Sim, Jaeyoon and Lee, Hoseok and Park, Jihwan and Baek, Seunghun and Yu Zhang and Kim, Won Hwa},
booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
year={2026}
}

1st author

Learning Multi-Scale Hypergraph for High-Order Brain Connectivity Analysis

Jaeyoon Sim, Soojin Hwang, Seunghun Baek, Gourong Wu, Won Hwa Kim

C International Conference on Machine Learning (ICML), Seoul, South Korea, 2026

Abstract Project Page BibTeX

Understanding complex interactions between brain regions is critical for early neurodegenerative disease classification such as Alzheimer’s Disease (AD) and Parkinson’s Disease (PD). While graph-based models are widely used to analyze brain networks, most existing approaches primarily focus on pairwise interactions between directly connected nodes, limiting their ability to capture higher-order dependencies across multiple regions. Although hypergraph-based methods have been proposed to model higher-order relations, many rely on predefined hyperedges or restrict learning to hyperedge weights, reducing flexibility and limiting their capacity to capture multi-resolution structural patterns. In this regard, we introduce an adaptive multi-scale hyperedge learning framework, i.e., MuHL, which constructs hierarchical node features and dynamically learns high-order interaction through continuous hyper-edge construction over multi-resolution graph signals. Extensive experiments on multiple brain network benchmarks demonstrate that MuHL consistently improves disease classification performance across different stages, and further identifies key regions of interest (ROIs) and their group-wise interactions from the learned hyperedges that are associated with disease progression, highlighting its potential as a powerful tool for brain network analysis with neurodegenerative disorders.

@inproceedings{sim2026learning,
title={Learning Multi-Scale Hypergraph for High-Order Brain Connectivity Analysis},
author={Sim, Jaeyoon and Hwang, Soojin, and Baek, Seunghun and Wu, Guorong and Kim, Won Hwa},
booktitle={Forty-third International Conference on Machine Learning},
year={2026} }

1st author

HiMix : Hierarchical Visual-Textual Mixing Network for Lesion Segmentation

Soojin Hwang^*, Jaeyoon Sim^*, Won Hwa Kim (^*: Equal Contribution)

C IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, Arizona, 2026

W MICCAI Workshop on Emerging LLM/LMM Applications in Medical Imaging (MICCAIW-ELAMI), Daejeon, South Korea, 2025

KSIIM Academic Award - Excellence Prize

Abstract Project Page BibTeX

Lesion segmentation is an essential task in medical imaging to support diagnosis and assessment of pathologies. While deep learning models have shown success in various domains, their reliance on large-scale annotated datasets limits applicability in the medical domain due to labeling cost. To address this issue, recent studies in medical image segmentation have utilized clinical texts as complementary semantic cues without additional annotations. However, most existing methods utilize a single textual embedding and fail to capture hierarchical interactions between language and visual features, which limits their ability to leverage fine-grained cues essential for precise and detailed segmentation. In this regime, we propose Hierarchical Visual-Textual Mixing Network (HiMix), a novel multi-modal segmentation framework that mixes multi-scale image and text representations throughout the mask decoding process. HiMix progressively injects hierarchical text embedding, from high-level semantics to fine-grained spatial details, into corresponding image decoder layers to bridge the modality gap and enhance visual feature refinement at multiple levels of abstraction. Experiments on the QaTa-COV19, MosMedData+ and Kvasir-SEG datasets demonstrate that HiMix consistently outperforms uni-modal and multi-modal methods. Furthermore, HiMix exhibits strong generalization to unstructured textual formats, highlighting its practical applicability in real-world clinical scenarios.

@inproceedings{hwang2026himix,
title={HiMix: Hierarchical Visual-Textual Mixing Network for Lesion Segmentation},
author={Hwang, Soojin and Sim, Jaeyoon and Kim, Won Hwa},
booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
pages={5332--5341},
year={2026}
}

Spectral Graph Autoregressive Modeling for Conditional Brain Network Augmentation

Hayoung Ahn, Seungjoo Lee, Jaeyoon Sim, Yechan Hwang, Hyuna Cho, Guorong Wu, Won Hwa Kim

W MICCAI Workshop on GRaphs in biomedicAl Image anaLysis (MICCAIW-GRAIL), Daejeon, South Korea, 2025

GRAIL Best Paper Award

Abstract Paper BibTeX

We present Spectral Graph AutoRegressive (SGAR) model, a novel conditional node signal synthesis method for brain networks. Unlike conventional generative models, SGAR employs a coarse-to-fine graph generation strategy in the spectral space: it first predicts low-frequency components that capture the global graph structure and then progressively refines high-frequency details to encode local feature dependencies. SGAR leverages Graph Fourier Transform (GFT) to decompose graph signals in the spectral domain and utilizes a conditional autoregressive transformer to generate spectral components based on disease stage labels. The continuous node signals are subsequently reconstructed via Inverse Graph Fourier Transform (IGFT), preserving the overall network topology. Applied to the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, our framework effectively addresses the challenges of data scarcity and label imbalance by augmenting brain networks with realistic, structured node features. Experimental results demonstrate that SGAR improves downstream AD classification performance while maintaining the global structure of brain networks.

@inproceedings{ahn2025spectral,
title={Spectral Graph Autoregressive Modeling for Conditional Brain Network Augmentation},
author={Ahn, Hayoung and Lee, Seungjoo and Sim, Jaeyoon and Hwang, Yechan and Cho, Hyuna and Wu, Guorong and Kim, Won Hwa},
booktitle={International Workshop on Reconstruction and Imaging Motion Estimation},
pages={209--218},
year={2025},
organization={Springer}
}

MNM: Multi-level Neuroimaging Meta-analysis with Hyperbolic Brain-Text Representations

Seunghun Baek, Jaejin Lee, Jaeyoon Sim, Minjae Jung, Won Hwa Kim

C International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Daejeon, South Korea, 2025

Provisional Accept [~9% Acceptance Rate]

Abstract Paper BibTeX

Various neuroimaging studies suffer from small sample size problem which often limit their reliability. Meta-analysis addresses this challenge by aggregating findings from different studies to identify consistent patterns of brain activity. However, traditional approaches based on keyword retrieval or linear mappings often overlook the rich hierarchical structure in the brain. In this work, we propose a novel framework that leverages hyperbolic geometry to bridge the gap between neuroscience literature and brain activation maps. By embedding text from research articles and corresponding brain images into a shared hyperbolic space via the Lorentz model, our method captures both semantic similarity and hierarchical organization inherent in neuroimaging data. In the hyperbolic space, our method performs multi-level neuroimaging meta-analysis (MNM) by 1) aligning brain and text embeddings for semantic correspondence, 2) guiding hierarchy between text and brain activations, and 3) preserving the hierarchical relationships within brain activation patterns. Experimental results demonstrate that our model outperforms baselines, offering a robust and interpretable paradigm of multi-level neuroimaging meta-analysis via hyperbolic brain-text representation.

@inproceedings{baek2025mnm,
title={MNM: Multi-level Neuroimaging Meta-analysis with Hyperbolic Brain-Text Representations},
author={Baek, Seunghun and Lee, Jaejin and Sim, Jaeyoon and Jeong, Minjae and Kim, Won Hwa},
booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
pages={397--406},
year={2025},
organization={Springer}
}

1st author

Multi-Modal Graph Neural Network with Transformer-Guided Adaptive Diffusion for Preclinical Alzheimer Classification

Jaeyoon Sim, Minjae Lee, Guorong Wu, Won Hwa Kim

C International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Marrakesh, Morocco, 2024

Abstract Project Page BibTeX

The graphical representation of the brain offers critical insights into diagnosing and prognosing neurodegenerative disease via relationships between regions of interest (ROIs). Despite recent emergence of various Graph Neural Networks (GNNs) to effectively capture the relational information, there remain inherent limitations in interpreting the brain networks. Specifically, convolutional approaches ineffectively aggregate information from distant neighborhoods, while attention-based methods exhibit deficiencies in capturing node-centric information, particularly in retaining critical characteristics from pivotal nodes. These shortcomings reveal challenges for identifying disease-specific variation from diverse features from different modalities. In this regards, we propose an integrated framework guiding diffusion process at each node by a downstream transformer where both short- and long-range properties of graphs are aggregated via diffusion-kernel and multi-head attention respectively. We demonstrate the superiority of our model by improving performance of pre-clinical Alzheimer’s disease (AD) classification with various modalities. Also, our model adeptly identifies key ROIs that are closely associated with the preclinical stages of AD, marking a significant potential for early diagnosis and prevision of the disease.

@inproceedings{sim2024multi,
title={Multi-modal Graph Neural Network with Transformer-Guided Adaptive Diffusion for Preclinical Alzheimer Classification},
author={Sim, Jaeyoon and Lee, Minjae and Wu, Guorong and Kim, Won Hwa},
booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
pages={511--521},
year={2024},
organization={Springer}
}

1st author

OCL: Ordinal Contrastive Learning for Imputating Features with Progressive Labels

Seunghun Baek^*, Jaeyoon Sim^*, Guorong Wu, Won Hwa Kim (^*: Equal Contribution)

C International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Marrakesh, Morocco, 2024

Provisional Accept [~11% Acceptance Rate]

Abstract Project Page BibTeX

Accurately discriminating progressive stages of Alzheimer’s Disease (AD) is crucial for early diagnosis and prevention. It often involves multiple imaging modalities to understand the complex pathology of AD, however, acquiring a complete set of images is challenging due to high cost and burden for subjects. In the end, missing data become inevitable which lead to limited sample-size and decrease in precision in downstream analyses. To tackle this challenge, we introduce a holistic imaging feature imputation method that enables to leverage diverse imaging features while retaining all subjects. The proposed method comprises two networks: 1) An encoder to extract modality-independent embeddings and 2) A decoder to reconstruct the original measures conditioned on their imaging modalities. The encoder includes a novel ordinal contrastive loss, which aligns samples in the embedding space according to the progression of AD. We also maximize modality-wise coherence of embeddings within each subject, in conjunction with domain adversarial training algorithms, to further enhance alignment between different imaging modalities. The proposed method promotes our holistic imaging feature imputation across various modalities in the shared embedding space. In the experiments, we show that our networks deliver favorable results for statistical analysis and classification against imputation baselines with Alzheimer’s Disease Neuroimaging Initiative (ADNI) study.

@inproceedings{baek2024ocl,
title={OCL: Ordinal Contrastive Learning for Imputating Features with Progressive Labels},
author={Baek, Seunghun and Sim, Jaeyoon and Wu, Guorong and Kim, Won Hwa},
booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
pages={334--344},
year={2024},
organization={Springer}
}

Neurodegenerative Brain Network Classification via Adaptive Diffusion with Temporal Regularization

Hyuna Cho, Jaeyoon Sim, Guorong Wu, Won Hwa Kim

C International Conference on Machine Learning (ICML), Vienna, Austria, 2024

BK21 Outstanding Paper Award - Top Excellence Prize

Abstract Project Page BibTeX

Analysis of neurodegenerative diseases on brain connectomes is important in facilitating early diagnosis and predicting its onset. However, investigation of the progressive and irreversible dynamics of these diseases remains underexplored in cross-sectional studies as its diagnostic groups are considered independent. Also, as in many real-world graphs, brain networks exhibit intricate structures with both homophily and heterophily. To address these challenges, we propose Adaptive Graph diffusion network with Temporal regularization (AGT). AGT introduces node-wise convolution to adaptively capture low (i.e., homophily) and high-frequency (i.e., heterophily) characteristics within an optimally tailored range for each node. Moreover, AGT captures sequential variations within progressive diagnostic groups with a novel temporal regularization, considering the relative feature distance between the groups in the latent space. As a result, our proposed model yields interpretable results at both node-level and group-level. The superiority of our method is validated on two neurodegenerative disease benchmarks for graph classification: Alzheimer’s Disease Neuroimaging Initiative (ADNI) and Parkinson’s Progression Markers Initiative (PPMI) datasets.

@inproceedings{cho2024choneurodegenerative,
title={Neurodegenerative Brain Network Classification via Adaptive Diffusion with Temporal Regularization},
author={Cho, Hyuna and Sim, Jaeyoon and Wu, Guorong and Kim, Won Hwa},
booktitle={Forty-first International Conference on Machine Learning},
year={2024} }

1st author

Modality-Agnostic Style Transfer for Holistic Feature Imputation

Seunghun Baek^*, Jaeyoon Sim^*, Mustafa Dere, Minjeong Kim, Guorong Wu, Won Hwa Kim (^*: Equal Contribution)

C International Symposium on Biomedical Imaging (ISBI), Athens, Greece, 2024

Oral Presentation

Abstract Project Page BibTeX

Characterizing a preclinical stage of Alzheimer’s Disease (AD) via single imaging is difficult as its early symptoms are quite subtle. Therefore, many neuroimaging studies are curated with various imaging modalities, e.g., MRI and PET, however, it is often challenging to acquire all of them from all subjects and missing data become inevitable. In this regards, in this paper, we propose a framework that generates unobserved imaging measures for specific subjects using their existing measures, thereby reducing the need for additional examinations. Our framework transfers modality-specific style while preserving AD-specific content. This is done by domain adversarial training that preserves modality-agnostic but AD-specific information, while a generative adversarial network adds an indistinguishable modality-specific style. Our proposed framework is evaluated on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) study and compared with other imputation methods in terms of generated data quality. Small average Cohen’s d < 0.19 between our generated measures and real ones suggests that the synthetic data are practically usable regardless of their modality type.

@INPROCEEDINGS{10635492,
author={Baek, Seunghun and Sim, Jaeyoon and Dere, Mustafa and Kim, Minjeong and Wu, Guorong and Kim, Won Hwa},
booktitle={2024 IEEE International Symposium on Biomedical Imaging (ISBI)},
title={Modality-Agnostic Style Transfer for Holistic Feature Imputation},
year={2024},
volume={},
number={},
pages={1-5},
keywords={Neuroimaging;Training;Magnetic resonance imaging;Imaging;
Estimation;Biomedical measurement;Generative adversarial networks},
doi={10.1109/ISBI56570.2024.10635492}}

1st author

Learning to Approximate Adaptive Kernel Convolution on Graphs

Jaeyoon Sim, Sooyeon Jeon, InJun Choi, Guorong Wu, Won Hwa Kim

C Association for the Advancement of Artificial Intelligence (AAAI), Vancouver, Canada, 2024

W Image Processing and Image Understanding (IPIU), Jeju, South Korea, 2024

IPIU Outstanding Paper Award - Bronze Prize

BK21 Outstanding Paper Award - Excellence Prize

Abstract Project Page BibTeX

Various Graph Neural Networks (GNNs) have been successful in analyzing data in non-Euclidean spaces, however, they have limitations such as oversmoothing, i.e., information becomes excessively averaged as the number of hidden layers increases. The issue stems from the intrinsic formulation of conventional graph convolution where the nodal features are aggregated from a direct neighborhood per layer across the entire nodes in the graph. As setting different number of hidden layers per node is infeasible, recent works leverage a diffusion kernel to redefine the graph structure and incorporate information from farther nodes. Unfortunately, such approaches suffer from heavy diagonalization of a graph Laplacian or learning a large transform matrix. In this regards, we propose a diffusion learning framework where the range of feature aggregation is controlled by the scale of a diffusion kernel. For efficient computation, we derive closed-form derivatives of approximations of the graph convolution with respect to the scale, so that node-wise range can be adaptively learned.With a downstream classifier, the entire framework is made trainable in an end-to-end manner. Our model is tested on various standard datasets for node-wise classification for the state-of-the-art performance, and it is also validated on a real-world brain network data for graph classifications to demonstrate its practicality for Alzheimer classification.

@inproceedings{sim2024learning,
title={Learning to Approximate Adaptive Kernel Convolution on Graphs},
author={Sim, Jaeyoon and Jeon, Sooyeon and Choi, InJun and Wu, Guorong and Kim, Won Hwa},
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
volume={38},
number={5},
pages={4882--4890},
year={2024}
}

Domestic

AI-Driven BGA Solder Joint Failure Detection of PCB Assembly

Seunghun Baek, Jaeyoon Sim, Siyeon Park, Cheolung Yang, Songyi Jeon, Jongho Song, Won Hwa Kim

C Autumn Annual Conference of the Institute of Electronics and Information Engineers (IEIE), Siheung, South Korea, 2023

C : Conference J : Journal W : Workshop