mlsanityData to 14 Oct 2026

M3D-BFS: a Multi-stage Dynamic Fusion Strategy for Sample-Adaptive Multi-Modal Brain Network Analysis

arXiv 2604.01667 ↗First posted 2 Apr 2026cs.AI cs.CVcited by 1

On the map: Mixture-of-experts → Medical and biomedical MoE

Abstract (arXiv)

Multi-modal fusion is of great significance in neuroscience which integrates information from different modalities and can achieve better performance than uni-modal methods in downstream tasks. Current multi-modal fusion methods in brain networks, which mainly focus on structural connectivity (SC) and functional connectivity (FC) modalities, are static in nature. They feed different samples into the same model with identical computation, ignoring inherent difference between input samples. This lack of sample adaptation hinders model's further performance. To this end, we innovatively propose a multi-stage dynamic fusion strategy (M3D-BFS) for sample-adaptive multi-modal brain network analysis. Unlike other static fusion methods, we design different mixture-of-experts (MoEs) for uni- and multi-modal representations where modules can adaptively change as input sample changes during inference. To alleviate issue of MoE where training of experts may be collapsed, we divide our method into 3 stages. We first train uni-modal encoders respectively, then pretrain single experts of MoEs before finally finetuning the whole model. A multi-modal disentanglement loss is designed to enhance the final representations. To the best of our knowledge, this is the first work for dynamic fusion for multi-modal brain network analysis. Extensive experiments on different real-world datasets demonstrates the superiority of M3D-BFS.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Medical and biomedical MoE, one of 12 directions in Mixture-of-experts. Builds on 14 of its 34 references that are in the map. First posted on arXiv 2 Apr 2026.

Builds on

14 of 34 references.

References · 14

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  3. 2024MoE-LLaVA: Mixture of Experts for Large Vision-Language Modelscited by 300
  4. 2022Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Expertscited by 203
  5. 2022On the Representation Collapse of Sparse Mixture of Expertscited by 157
  6. 2024Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Expertscited by 108
  7. 2023Provable Dynamic Fusion for Low-Quality Multimodal Datacited by 82
  8. 2022Dynamic Multimodal Fusioncited by 55
  9. 2023Multi-modal Gated Mixture of Local-to-Global Experts for Dynamic Image Fusioncited by 54
  10. 2023On Uni-Modal Feature Learning in Supervised Multi-Modal Learningcited by 53
  11. 2023EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoEcited by 25
  12. 2023BrainNPT: Pre-training of Transformer networks for brain network classificationcited by 9
2 more
  1. 2024NeuroPath: A Neural Pathway Transformer for Joining the Dots of Human Connectomescited by 6
  2. 2022Modeling Multiple Views via Implicitly Preserving Global Consistency and Local Complementaritycited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026When Language Models Meet NeuroGraphs: Exploring Enhanced Agentic LLM Framework Towards Brain Network Analysiscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025BrainCSD: A Hierarchical Consistency-Driven MoE Foundation Model for Unified Connectome Synthesis and Multitask Brain Trait Prediction
  2. 2025BRIEF: BRain-Inspired network connection search with Extensive temporal feature Fusion enhances disease classification
  3. 2023BrainNetDiff: Generative AI Empowers Brain Network Generation via Multimodal Diffusion Model
  4. 2026Structural-Functional Brain Connectivity Generation via Multimodal Hypergraph-based Flow Matching
  5. 2026Exploring Diffusion Transformers for Cross-Modal Augmentation in Multimodal Brain State Decoding
  6. 2025Bridging Foundation Models and Efficient Architectures: A Modular Brain Imaging Framework with Local Masking and Pretrained Representation Learning
  7. 2025NeuroMoE: A Transformer-Based Mixture-of-Experts Framework for Multi-Modal Neurological Disorder Classification
  8. 2026STEAM: A Spatio-TEmporal Alignment Mixture-of-Experts Model with Hierarchical Pre-training for EEG Decoding