← Papers
Latent models

G-LED

Generative learning for forecasting the dynamics of high-dimensional complex systems

Paper title Generative learning for forecasting the dynamics of high-dimensional complex systems

Gao et al. (Harvard) · Aero & CFD · General PDEs · Public: code, data

Paper arXiv 2402.17157PDF

The latent state is the simulation snapshot subsampled to a coarse grid, with no trained encoder. An autoregressive attention model advances it in time, and a diffusion model conditioned on the latent state generates the full-resolution fields.

Published
Nature Communications

Share on LinkedIn, X or Bluesky, or or .

Know related work that belongs here?

Something wrong on this page?

More papers

All papers
  1. Latent modelsD-JEPA — One geometry latent, reused across flow conditions and physics
  2. Latent modelsCourant — A state-adaptive Perceiver surrogate with local support
  3. Latent modelsAeroJEPA — Semantic Latent Representations for 3D Aerodynamic Fields