Skip to content

Autoregressive Flow Matching

Home / Concepts / Autoregressive Flow Matching

Autoregressive Flow Matching

Auto-generated stub. Edit this file to add more details.

A generative modeling framework that combines flow matching with autoregressive conditioning to learn the conditional distribution of future states in time-evolving systems.

Why It Matters

Core methodology proposed for temporal generative modeling of neural data, extending transport-based generative models to autoregressive settings.

Evidence

we introduce a generative forecasting framework for modeling neural dynamics based on autoregressive flow matching (AFM)

Metadata & Links