Vision Language Navigation On Room2Room
Metrics
spl
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | spl |
|---|---|
| tactical-rewind-self-correction-via | 0.41 |
| reinforced-cross-modal-matching-and-self | 0.59 |
| learning-to-navigate-unseen-environments-back | 0.61 |