Vision and Language Navigation
Papers
No papers found.
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | human | success | 0.86 | — | Unverified |
| 2 | Lily | success | 0.79 | — | Unverified |
| 3 | Airbert | success | 0.78 | — | Unverified |
| 4 | Global Normalization | success | 0.74 | — | Unverified |
| 5 | explore@40 beam-search | success | 0.74 | — | Unverified |
| 6 | BEVBert | success | 0.73 | — | Unverified |
| 7 | GMap | success | 0.73 | — | Unverified |
| 8 | VLN-Bert | success | 0.73 | — | Unverified |
| 9 | Gloabl Normalization pre-explore | success | 0.73 | — | Unverified |
| 10 | FOAM-Beam Search | success | 0.72 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | FLAME | Task Completion (TC) | 40.2 | — | Unverified |
| 2 | ORAR + junction type + heading delta | Task Completion (TC) | 29.1 | — | Unverified |
| 3 | ORAR | Task Completion (TC) | 24.2 | — | Unverified |
| 4 | ARC + L2STOP | Task Completion (TC) | 16.68 | — | Unverified |
| 5 | VLN Transformer +M-50 +style | Task Completion (TC) | 16.2 | — | Unverified |
| 6 | VLN Transformer | Task Completion (TC) | 14.9 | — | Unverified |
| 7 | ARC | Task Completion (TC) | 14.13 | — | Unverified |
| 8 | Retouch-RConcat | Task Completion (TC) | 12.8 | — | Unverified |
| 9 | Gated Attention (GA) | Task Completion (TC) | 11.9 | — | Unverified |
| 10 | RConcat | Task Completion (TC) | 11.8 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | MARVAL | ndtw | 66.76 | — | Unverified |
| 2 | EnvEdit-PT | ndtw | 64.61 | — | Unverified |
| 3 | HAMT | ndtw | 59.94 | — | Unverified |
| 4 | CLEAR-CLIP | ndtw | 53.69 | — | Unverified |
| 5 | Monolingual Baseline | ndtw | 41.05 | — | Unverified |
| 6 | Multilingual Baseline | ndtw | 36.81 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | FLAME | Task Completion (TC) | 52.44 | — | Unverified |
| 2 | ORAR + junction type + heading delta | Task Completion (TC) | 46.7 | — | Unverified |
| 3 | ORAR | Task Completion (TC) | 45.1 | — | Unverified |
| 4 | Gated Attention | Task Completion (TC) | 17 | — | Unverified |
| 5 | Rconcat | Task Completion (TC) | 14.7 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | R2R+EnvDrop | spl | 0.61 | — | Unverified |
| 2 | RCM + SIL | spl | 0.59 | — | Unverified |
| 3 | Tactical Rewind - short | spl | 0.41 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Hierarchical Cross-Modal Agent | SPL (Sucess Weighted by Path Length) | 0.4 | — | Unverified |