Vision Language Navigation On Room2Room
Metriken
spl
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | spl |
|---|---|
| tactical-rewind-self-correction-via | 0.41 |
| reinforced-cross-modal-matching-and-self | 0.59 |
| learning-to-navigate-unseen-environments-back | 0.61 |