Probabilistic Prediction of Neural Dynamics via Autoregressive Flow Matching

TL;DR

This paper introduces a novel autoregressive flow matching framework for probabilistic forecasting of neural activity, outperforming baseline models in predicting short-term brain responses from multimodal sensory input.

Contribution

The authors develop a generative modeling approach that explicitly captures the temporal evolution of neural activity conditioned on past dynamics and sensory input.

Findings

AFM outperforms baseline models in predicting BOLD activity.

Access to past neural dynamics significantly improves prediction accuracy.

Autoregressive factorization provides consistent gains in short-horizon predictions.

Abstract

Forecasting neural activity in response to naturalistic stimuli remains a key challenge for understanding brain dynamics and enabling downstream neurotechnological applications. Here, we introduce a generative forecasting framework for modeling neural dynamics based on autoregressive flow matching (AFM). Building on recent advances in transport-based generative modeling, our approach probabilistically predicts neural responses at scale from multimodal sensory input. Specifically, we learn the conditional distribution of future neural activity given past neural dynamics and concurrent sensory input, explicitly modeling neural activity as a temporally evolving process in which future states depend on recent neural history. We evaluate our framework on the Algonauts project 2025 challenge functional magnetic resonance imaging dataset using subject-specific models. AFM significantly outperforms both a non-autoregressive flow-matching baseline and the official challenge general linear model baseline in predicting short-term parcel-wise blood oxygenation level-dependent (BOLD) activity, demonstrating improved generalization and widespread cortical prediction performance. Ablation analyses show that access to past BOLD dynamics is a dominant driver of performance, while autoregressive factorization yields consistent, modest gains under short-horizon, context-rich conditions. Together, these findings position autoregressive flow-based generative modeling as an effective approach for short-term probabilistic forecasting of neural dynamics with promising applications in closed-loop neurotechnology.