Finetuned physics foundation model generalizes zero-shot from few DNS runs to laboratory RTI data, matching experimental mixing growth rates and handling unseen stable stratification.
Learning turbulent flows with generative models: Super-resolution, forecasting, and sparse flow reconstruction.arXiv preprint arXiv:2509.08752, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.flu-dyn 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Emergent Transfer of a Physics Foundation Model from Simulation to Laboratory Turbulence
Finetuned physics foundation model generalizes zero-shot from few DNS runs to laboratory RTI data, matching experimental mixing growth rates and handling unseen stable stratification.