Vision-Language Navigation on R2R 1 (test unseen)
0.76Success RateVER
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| VERReference=[91]2024.10 | 0.76 | 15.23 | 2.74 | 0.66 | |
| VER2026.05 | 0.76 | 15.23 | 2.74 | 0.66 | |
| Uncertainty-Aware Gaussian Map2026.05 | 0.76 | 14.68 | 3.17 | 0.66 | |
| 3DGS-VLN2026.05 | 0.75 | 14.58 | 3.17 | 0.65 | |
| BSGReference=[61]2024.10 | 0.73 | 14.86 | 3.19 | 0.62 | |
| BEVBertReference=[60]2024.10 | 0.73 | — | 3.13 | 0.62 | |
| GridMM2026.05 | 0.73 | 14.43 | 3.35 | 0.62 | |
| BEVBert2026.05 | 0.73 | — | 3.13 | 0.62 | |
| BSG2026.05 | 0.73 | 14.86 | 3.19 | 0.62 | |
| ENP-DUETBackbone=DUET2024.10 | 0.71 | 14.27 | 3.39 | 0.6 | |
| DUETvariant=Imagine2026.05 | 0.71 | 15.35 | 3.52 | 0.6 | |
| COSMO2026.05 | 0.71 | — | 3.43 | 0.58 | |
| DUETReference=[6]2024.10 | 0.69 | 14.73 | 3.65 | 0.59 | |
| DUET2026.05 | 0.69 | 14.73 | 3.65 | 0.59 | |
| TD-STPReference=[89]2024.10 | 0.67 | — | 3.73 | 0.61 | |
| HAMTReference=[5]2024.10 | 0.65 | 12.27 | 3.93 | 0.6 | |
| LANAReference=[90]2024.10 | 0.65 | 12.6 | — | 0.6 | |
| ENP-VLNOBERTBackbone=VLNOBERT2024.10 | 0.65 | 13.12 | 3.91 | 0.59 | |
| HAMT2026.05 | 0.65 | 12.27 | 3.93 | 0.6 | |
| LANA2026.05 | 0.65 | 12.6 | — | 0.6 | |
| HOPReference=[88]2024.10 | 0.64 | 12.68 | 3.83 | 0.59 | |
| VLNOBERTReference=[4]2024.10 | 0.63 | 12.35 | 4.09 | 0.57 | |
| SSMReference=[38]2024.10 | 0.61 | 20.4 | 4.57 | 0.46 | |
| ActiveReference=[87]2024.10 | 0.6 | 21.6 | 4.33 | 0.41 | |
| AuxRNReference=[47]2024.10 | 0.55 | — | 5.15 | 0.51 | |
| ENP-EnvDropBackbone=EnvDrop2024.10 | 0.52 | 10.78 | 5.3 | 0.48 | |
| EnvDropReference=[3]2024.10 | 0.51 | 11.66 | 5.23 | 0.47 | |
| SFReference=[33]2024.10 | 0.35 | 14.82 | 6.62 | 0.28 | |
| Seq2SeqReference=[1]2024.10 | 0.2 | 8.13 | 7.85 | 0.18 |