Generative Latent Flow Matching

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

A generative modeling technique that uses continuous normalizing flows guided by a learned trajectory between data distributions for forecasting.

Why It Matters

It is the core methodology for building the generative forecasting model, combining flow matching with a latent predictive structure.

Evidence

we present \textit{Marchuk}, a generative latent flow-matching model for global weather forecasting

Related Papers

• openalex-2603.24428-marchuk-efficient-global-weather-forecasting-from-mid-range