PDE Operator Learning on NS-SL
0.3EGMPP-B
Evaluation results
| Method | Links | ||
|---|---|---|---|
| MPP-BTraining Regime=Pretrained2024.05 | 0.3 | 0.8 | |
| scOTTraining Regime=Trained from Scratch2024.05 | 0.3 | 0.8 | |
| CNO-FMTraining Regime=Pretrained2024.05 | 0.4 | 0.8 | |
| CNOTraining Regime=Trained from Scratch2024.05 | 0.8 | 1.2 | |
| FNOTraining Regime=Trained from Scratch2024.05 | 1 | 1 | |
| DPOTTraining Strategy=From Scratch, Model Size=M, Number of parameters=120 M2024.05 | 2.1 | 1.3 | |
| DPOTTraining Strategy=From Scratch, Model Size=L, Number of parameters=509 M2024.05 | 3 | 1.6 | |
| DPOTTraining Strategy=Finetuned, Model Size=M, Number of parameters=120 M2024.05 | 4.5 | 2.4 | |
| DPOTTraining Strategy=Finetuned, Model Size=L, Number of parameters=509 M2024.05 | 4.7 | 2.4 | |
| POSEIDON-LTraining Regime=Pretrained2024.05 | 21.9 | 5.5 |