Cross-Domain Pretraining for Steady-State Neural CFD Surrogates

Name: Cross-Domain Pretraining for Steady-State Neural CFD Surrogates
Uploaded: 2026-10-17T23:58:21.344740+00:00
Duration: 374 s
Description: Cross-domain pretraining improves zero- and few-shot performance of Computational Fluid Dynamics (CFD) surrogates on unseen datasets. By training models on diverse steady-state CFD data, researchers found that finetuning these models yields 2–3x lower errors and requires 8x fewer samples for deployment compared to training from scratch.

Cross-domain pretraining improves zero- and few-shot performance of Computational Fluid Dynamics (CFD) surrogates on unseen datasets. By training models on diverse steady-state CFD data, researchers found that finetuning these models yields 2–3x lower errors and requires 8x fewer samples for deployment compared to training from scratch.

Open the full episode