Rollout Prediction on Rayleigh Benard (test)
0.05CRPSOurs (CRPS)
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Ours (CRPS)Backbone=Walrus, Training Mode=CRPS retrofitted2026.03 | 0.05 | 0.558 | 0.9 | |
| Ours (CRPS)Backbone=Lola, Training Mode=CRPS retrofitted2026.03 | 0.055 | 0.632 | 0.957 | |
| Ours (CRPS)Backbone=Poseidon, Training Mode=CRPS retrofitted2026.03 | 0.071 | 0.713 | 1.615 | |
| Deterministic (Base)Backbone=Walrus, Training Mode=Deterministic baseline2026.03 | 0.087 | 0.698 | — | |
| Deterministic (FT)Backbone=Walrus, Training Mode=Fine-tuned with pre-training loss2026.03 | 0.09 | 0.697 | — | |
| Deterministic (FT)Backbone=Poseidon, Training Mode=Fine-tuned with pre-training loss2026.03 | 0.095 | 0.74 | — | |
| Deterministic (Base)Backbone=Poseidon, Training Mode=Deterministic baseline2026.03 | 0.1 | 0.77 | — | |
| Deterministic (FT)Backbone=Lola, Training Mode=Fine-tuned with pre-training loss2026.03 | 0.101 | 0.807 | — | |
| Deterministic (Base)Backbone=Lola, Training Mode=Deterministic baseline2026.03 | 0.105 | 0.812 | — |