# Navigation on REVERIE (val seen)

Source: [Navigation on REVERIE (val seen)](<https://www.sota2.com/research/sota/navigation-on-reverie-val-seen>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T06:05:40.769Z

Evaluation of Navigation performance on the REVERIE dataset using the 'val seen' split, reporting Success Rate (SR), Oracle Success Rate (OSR), SPL, and Total Length (TL).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Navigation |
| Dataset (including any stated split) | REVERIE (val seen) |
| Metric | Success Rate (SR) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Success Rate (SR)](<https://www.sota2.com/research/sota/navigation-on-reverie-val-seen.md?metric=Success%20Rate%20(SR)>): Higher is better; unit: PERCENT.

- [Oracle Success Rate (OSR)](<https://www.sota2.com/research/sota/navigation-on-reverie-val-seen.md?metric=Oracle%20Success%20Rate%20(OSR)>): Higher is better; unit: PERCENT.

- [SPL](<https://www.sota2.com/research/sota/navigation-on-reverie-val-seen.md?metric=SPL>): Higher is better; unit: PERCENT.

- [Total Length (TL)](<https://www.sota2.com/research/sota/navigation-on-reverie-val-seen.md?metric=Total%20Length%20(TL)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Success Rate (SR) | Result date | Report paper |
| --- | --- | --- | --- |
| FAST-MATTN | 50.53 | Not recorded | 68fa6a971e209131cea292a3 |
| Rec (Airbert) | 47.01 | Not recorded | 68fa6a971e209131cea292a3 |
| Fine-Tuning | 46.73 | Not recorded | 68fa70661e209131cea4ae7c |
| VLN-PETL | 45.96 | Not recorded | 68fa70661e209131cea4ae7c |
| Rec (ViLBERT) | 43.64 | Not recorded | 68fa6a971e209131cea292a3 |
| LORA | 42.3 | Not recorded | 68fa70661e209131cea4ae7c |
| SMNA | 41.25 | Not recorded | 68fa6a971e209131cea292a3 |
| Rec (VLN-BERT) | 41.11 | Not recorded | 68fa6a971e209131cea292a3 |
| Adapter | 40.76 | Not recorded | 68fa70661e209131cea4ae7c |
| Rec (OSCAR) | 39.85 | Not recorded | 68fa6a971e209131cea292a3 |
| BitFit | 33.52 | Not recorded | 68fa70661e209131cea4ae7c |
| Seq2Seq-SF | 29.59 | Not recorded | 68fa6a971e209131cea292a3 |
| Prompt Tuning | 25.86 | Not recorded | 68fa70661e209131cea4ae7c |
| RCM | 23.33 | Not recorded | 68fa6a971e209131cea292a3 |

### FAST-MATTN

Success Rate (SR): 50.53. Result ID: 699ac5195698665ec453660f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a971e209131cea292a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66e81e209131cea13118.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Rec (Airbert)

Success Rate (SR): 47.01. Result ID: 699ac5195698665ec4536613.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a971e209131cea292a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a971e209131cea292a3.md>)

[Implementation](<https://airbert-vln.github.io/>)

Recorded evaluation configuration: {"mode":"discriminative"}. This record does not assert independent reproduction.

### Fine-Tuning

Success Rate (SR): 46.73. Result ID: 69911c4c3a6c31484905c31b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70661e209131cea4ae7c.md>)

Recorded evaluation configuration: {"Updated Params(%)":"100"}. This record does not assert independent reproduction.

### VLN-PETL

Success Rate (SR): 45.96. Result ID: 69911c4c3a6c31484905c320.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70661e209131cea4ae7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70661e209131cea4ae7c.md>)

[Implementation](<https://github.com/YanyuanQiao/VLN-PETL>)

Recorded evaluation configuration: {"Updated Params(%)":"2.81"}. This record does not assert independent reproduction.

### Rec (ViLBERT)

Success Rate (SR): 43.64. Result ID: 699ac5195698665ec4536611.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a971e209131cea292a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa699f1e209131cea23252.md>)

[Implementation](<https://github.com/YicongHong/Recurrent-VLN-BERT>)

Recorded evaluation configuration: {"mode":"discriminative"}. This record does not assert independent reproduction.

### LORA

Success Rate (SR): 42.3. Result ID: 69911c4c3a6c31484905c31e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70661e209131cea4ae7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b121e209131cea2bf59.md>)

[Implementation](<https://github.com/microsoft/LoRA>)

Recorded evaluation configuration: {"Updated Params(%)":"3.33"}. This record does not assert independent reproduction.

### SMNA

Success Rate (SR): 41.25. Result ID: 699ac5195698665ec453660e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a971e209131cea292a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65381e209131cea09123.md>)

[Implementation](<https://github.com/chihyaoma/selfmonitoring-agent>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Rec (VLN-BERT)

Success Rate (SR): 41.11. Result ID: 699ac5195698665ec4536612.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a971e209131cea292a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa699f1e209131cea23252.md>)

[Implementation](<https://github.com/YicongHong/Recurrent-VLN-BERT>)

Recorded evaluation configuration: {"mode":"discriminative"}. This record does not assert independent reproduction.

### Adapter

Success Rate (SR): 40.76. Result ID: 69911c4c3a6c31484905c31f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70661e209131cea4ae7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65e31e209131cea0d324.md>)

[Implementation](<https://github.com/google-research/adapter-bert>)

Recorded evaluation configuration: {"Updated Params(%)":"3.39"}. This record does not assert independent reproduction.

### Rec (OSCAR)

Success Rate (SR): 39.85. Result ID: 699ac5195698665ec4536610.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a971e209131cea292a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa699f1e209131cea23252.md>)

[Implementation](<https://github.com/YicongHong/Recurrent-VLN-BERT>)

Recorded evaluation configuration: {"mode":"discriminative"}. This record does not assert independent reproduction.

### BitFit

Success Rate (SR): 33.52. Result ID: 69911c4c3a6c31484905c31c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70661e209131cea4ae7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d5a1e209131cea39632.md>)

[Implementation](<https://www.github.com/benzakenelad/BitFit>)

Recorded evaluation configuration: {"Updated Params(%)":"0.80"}. This record does not assert independent reproduction.

### Seq2Seq-SF

Success Rate (SR): 29.59. Result ID: 699ac5195698665ec453660c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a971e209131cea292a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa642d1e209131cea032de.md>)

[Implementation](<https://bringmeaspoon.org/>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Prompt Tuning

Success Rate (SR): 25.86. Result ID: 69911c4c3a6c31484905c31d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70661e209131cea4ae7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6aa51e209131cea296c9.md>)

Recorded evaluation configuration: {"Updated Params(%)":"0.71"}. This record does not assert independent reproduction.

### RCM

Success Rate (SR): 23.33. Result ID: 699ac5195698665ec453660d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a971e209131cea292a3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa658b1e209131cea0b005.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
