aiqbench analysis
FAST-Brain represents a significant methodological advance in applying deep learning architectures, specifically flow-based generative models and Transformers, to model complex neuroimaging data like rs-fMRI. By effectively handling the brain's spatial constraints and long-range temporal dependencies, this approach improves the recovery of functional connectivity metrics beyond current state-of-the-art methods. This work highlights the growing intersection where advanced machine learning techniques are being tailored to solve specialized problems in neuroscience and cognitive science.
FAST-Brain: A Flow-Aligned Spatio-Temporal Surrogate Brain Model
arXiv:2609.34354v1 Announce Type: new Abstract: Modeling resting-state functional magnetic resonance imaging (rs-fMRI) data is crucial for understanding brain-wide neural activity. However, traditional methods struggle to capture complex temporal dynamics over long horizons, to account for the brain's anatomical spatial structure, and to model high-dimensional ambient signals that lie on a low-dimensional intrinsic subspace. We propose FAST-Brain, a unified flow-aligned spatio-temporal surrogate brain model that addresses all three challenges. At its core is a flow-aligned generative framework that directly predicts the clean blood-oxygen-level-dependent (BOLD) signal, paired with a graph convolutional network that captures spatial structural constraints and a Transformer that models long-range temporal dependencies. Theoretically, we show that under a low-dimensional subspace assumption, the approximation error of our model scales with the intrinsic dimension rather than the ambient dimension, which justifies our direct modeling of the BOLD signal. Extensive experiments on synthetic and Human Connectome Project datasets demonstrate that FAST-Brain achieves state-of-the-art performance in recovering functional connectivity, effective connectivity, and the implicit low-dimensional signal subspace.
Abstract:Modeling resting-state functional magnetic resonance imaging (rs-fMRI) data is crucial for understanding brain-wide neural activity. However, traditional methods struggle to capture complex temporal dynamics over long horizons, to account for the brain's anatomical spatial structure, and to model high-dimensional ambient signals that lie on a low-dimensional intrinsic subspace. We propose FAST-Brain, a unified flow-aligned spatio-temporal surrogate brain model that addresses all three challenges. At its core is a flow-aligned generative framework that directly predicts the clean blood-oxygen-level-dependent (BOLD) signal, paired with a graph convolutional network that captures spatial structural constraints and a Transformer that models long-range temporal dependencies. Theoretically, we show that under a low-dimensional subspace assumption, the approximation error of our model scales with the intrinsic dimension rather than the ambient dimension, which justifies our direct modeling of the BOLD signal. Extensive experiments on synthetic and Human Connectome Project datasets demonstrate that FAST-Brain achieves state-of-the-art performance in recovering functional connectivity, effective connectivity, and the implicit low-dimensional signal subspace.
Machine Learning (cs.LG); Neurons and Cognition (q-bio.NC)
arXiv:2609.34354 [cs.LG]
(or arXiv:2609.34354v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.34354 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 257 words
Related coverage
Not All EEG Moments Are Equal: Position-Adaptive Time Scheduling for EEG Generation
arXiv · Aug 5, 2026
Triton-Based Optimization of Video Sparse Attention on ROCm
AMD · Jul 13, 2026
Autoregressive One-Step Generative Modeling for Dynamical System Forecasting
arXiv · Jul 28, 2026
Vessel Traffic Flow Prediction on Sparse Data via Spatio-Temporal Graph Neural Networks with a Learnable Tweedie Head
arXiv · Jun 9, 2026