Long-horizon task chaining on CALVIN (unseen environment D)
96.41 Task Completion RateGeoMoLa
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| GeoMoLaTraining Data=Language-annotated2026.07 | 96.4 | 85.2 | 73 | 59.9 | 47.1 | 3.6 | |
| CloverTraining Data=Language-annotated2026.07 | 96 | 83.5 | 70.8 | 57.5 | 45.4 | 3.53 | |
| 3D Diffuser ActorTraining Data=Language-annotated2026.07 | 93.8 | 80.3 | 66.2 | 53.3 | 41.2 | 3.35 | |
| RVT2Training Data=Language-annotated2026.07 | 90.4 | 76.8 | 61.6 | 50.2 | 39.8 | 3.23 | |
| SuSIETraining Data=All play data2026.07 | 87 | 69 | 49 | 38 | 26 | 2.69 | |
| GR-1Training Data=Language-annotated2026.07 | 85.4 | 71.2 | 59.6 | 49.7 | 40.1 | 3.06 | |
| DP3Training Data=Language-annotated2026.07 | 28.7 | 2.7 | 0 | 0 | 0 | 0.31 |