Skip to content

FAST-Brain: A Flow-Aligned Spatio-Temporal Surrogate Brain Model

Sep 2026 · 0 citations · 63 references
Computer Science Biology

TL;DR

FAST-Brain is proposed, a unified flow-aligned spatio-temporal surrogate brain model that addresses all three challenges of resting-state functional magnetic resonance imaging data, and 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.

View source

Similar papers

Preprint Aug 2026

MnemoDyn: Learning Resting State Dynamics from 40K FMRI sequences

It is shown that MnemoDyn is compute efficient and generalizes very well across diverse populations and scanning protocols, and when benchmarked against current state-of-the-art transformer-based approaches, MnemoDyn consistently delivers superior reconstruction quality.

Sourav Pal, V. Lương, Hoseok Lee et al. · 1 citation
Open access Aug 2026

Frequency-filtered attention for cross-species fMRI time series prediction under small-sample learning

A general fMRI sequence prediction model, the Frequency-Filtered Attention Transformer (FFAformer), which models low-frequency variations in the frequency domain to capture long-range dependencies and incorporates FC consistency constraints to preserve brain network structure.

Chengcheng Du, Fei-Fei Zhao, Yin-Qian Sun et al. · 0 citations
Conference Open access Sep 2026

STCBN-EC: A Spatio-Temporal Constrained Bayesian Causal Network for Multimodal Brain Effective Connectivity Learning

Brain effective connectivity (EC) characterizes directional causal interactions among brain regions. However, learning stable and directionally explicit EC networks from multimodal data remains challenging. In practice, functional magnetic resonance imaging (fMRI) and electroencephalography (EEG) differ substantially i...

Zhi-Hao Su, Jun-Zhong Ji, Min-Qi Yu et al. · 0 citations
#machine learning Preprint Oct 2026

Decoupling Time and Space: A Temporally Conditioned Refinement for EEG Source Imaging

Electroencephalography (EEG) offers millisecond temporal resolution, but inferring underlying neural sources is a severely ill-posed spatial inverse problem. While deep learning has advanced spatial reconstruction, current architectures face a critical dilemma: frame-by-frame models discard vital temporal context, wher...

Marco Morik, Jesse Palarus, C. Vidaurre et al. · 0 citations
Preprint Aug 2026

BrainLinear: A Linear Model for Brain Network Analysis in Sparse Tangent Subspaces

BrainLinear is proposed, a lightweight geometry-aware framework for mining disease-discriminative connectome patterns, and shows that it improves AUC and ACC over the best baseline for each metric by up to $3.54 and $1.39 percentage points, respectively.

Si-Jing Wu, Dong-Yuan Li, Miaoting Huang et al. · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.