Papers › General Scene Adaptation for Vision-and-Language Navigation

General Scene Adaptation for Vision-and-Language Navigation

29 Jan 2025arXiv:2501.17403archive 2025-07-28

Haodong Hong, Yanyuan Qiao, Sen Wang, Jiajun Liu, Qi Wu

Vision-and-Language Navigation (VLN) tasks mainly evaluate agents based on one-time execution of individual instructions across multiple environments, aiming to develop agents capable of functioning in any environment in a zero-shot manner. However, real-world navigation robots often operate in persistent environments with relatively consistent physical layouts, visual observations, and language styles from instructors. Such a gap in the task setting presents an opportunity to improve VLN agents by incorporating continuous adaptation to specific environments. To better reflect these real-world conditions, we introduce GSA-VLN, a novel task requiring agents to execute navigation instructions within a specific scene and simultaneously adapt to it for improved performance over time. To evaluate the proposed task, one has to address two challenges in existing VLN datasets: the lack of OOD data, and the limited number and style diversity of instructions for each scene. Therefore, we propose a new dataset, GSA-R2R, which significantly expands the diversity and quantity of environments and instructions for the R2R dataset to evaluate agent adaptability in both ID and OOD contexts. Furthermore, we design a three-stage instruction orchestration pipeline that leverages LLMs to refine speaker-generated instructions and apply role-playing techniques to rephrase instructions into different speaking styles. This is motivated by the observation that each individual user often has consistent signatures or preferences in their instructions. We conducted extensive experiments on GSA-R2R to thoroughly evaluate our dataset and benchmark various methods. Based on our findings, we propose a novel method, GR-DUET, which incorporates memory-based navigation graphs with an environment-specific training strategy, achieving state-of-the-art results on all GSA-R2R splits.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 14 code samples harvested from 1 repository linked to this paper: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 2 ran (1 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

honghd16/gsa-vln officialmentioned in paperpytorchMITSyntology: 14 samples, 2 ran (1 instrument-failed) · 12 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

14 samples harvested: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 12 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
1ran
12unverified

Licence: 0 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from honghd16/gsa-vln. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

honghd16/gsa-vln official repository 14 samples, 2 ran (1 instrument-failed) · 12 unverified
TransformerEncoder in 96 papers GR-DUET/map_nav_src/models/vilmodel.py ran MIT (permissive) · 0feddf62036c64ee · report fixture: returned TransformerEncoder · level recorded 2026-09-22
create_transformer_encoder in 7 papers GR-DUET/map_nav_src/models/vilmodel.py ran · our draft was wrong MIT (permissive) · e421ddf75512f4c4 · report fixture: signature config:Config/0/?, num_layers:int/0/int, norm:bool/0/bool · returned TransformerEncoder · level recorded 2026-09-22
BertAttention in 28 papers GR-DUET/map_nav_src/models/vilmodel.py unverified MIT (permissive) · c35512e4d250fe83 · report
BertEmbeddings in 21 papers GR-DUET/map_nav_src/models/vilmodel.py unverified MIT (permissive) · 66bd358094beb851 · report
BertLayer in 23 papers GR-DUET/map_nav_src/models/vilmodel.py unverified MIT (permissive) · 721f4cb09203dd0a · report
BertSelfAttention in 29 papers GR-DUET/map_nav_src/models/vilmodel.py unverified MIT (permissive) · 50a3d34aac2573cd · report
ClsPrediction GR-DUET/map_nav_src/models/vilmodel.py unverified MIT (permissive) · c26f9faf52e44089 · report
CrossmodalEncoder GR-DUET/map_nav_src/models/vilmodel.py unverified MIT (permissive) · 440e8824b1f7a4cc · report
GlobalMapEncoder GR-DUET/map_nav_src/models/vilmodel.py unverified MIT (permissive) · 62f8ba1805bb2b0d · report
GlocalTextPathNavCMT GR-DUET/map_nav_src/models/vilmodel.py unverified MIT (permissive) · 367e98fa690b6937 · report
GraphLXRTXLayer GR-DUET/map_nav_src/models/vilmodel.py unverified MIT (permissive) · 2445c8cf02121bbf · report
ImageEmbeddings in 7 papers GR-DUET/map_nav_src/models/vilmodel.py unverified MIT (permissive) · 0d0612599d4b8d71 · report
LanguageEncoder GR-DUET/map_nav_src/models/vilmodel.py unverified MIT (permissive) · ec6f57e27634d519 · report
LocalVPEncoder GR-DUET/map_nav_src/models/vilmodel.py unverified MIT (permissive) · 5ddba8a53b37ee6f · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for GR-DUET (graph method: GR-DUET). 27 bricks; individually on a fixture: 12 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 15 unverified. The assembly has not been run end-to-end.

  1. GlocalTextPathNavCMT entry · level 0 · unverified · 367e98fa690b6937
  2. BertEmbeddings model · level 0 · unverified · 66bd358094beb851
  3. ClsPrediction helper · level 0 · unverified · c26f9faf52e44089
  4. GlobalMapEncoder model · level 0 · unverified · 62f8ba1805bb2b0d
  5. ImageEmbeddings model · level 0 · unverified · 0d0612599d4b8d71
  6. LanguageEncoder model · level 0 · unverified · ec6f57e27634d519
  7. LocalVPEncoder model · level 0 · unverified · 5ddba8a53b37ee6f
  8. gen_seq_masks helper · level 1 · ran · our draft was wrong · 68ae8be3692cbbbe
  9. pad_tensors_wgrad helper · level 1 · ran; the contract check could not run · 96c2b643194ca603
  10. CrossmodalEncoder model · level 0 · unverified · 440e8824b1f7a4cc
  11. create_transformer_encoder helper · level 1 · ran · our draft was wrong · e421ddf75512f4c4
  12. BertLayer model · level 0 · unverified · 721f4cb09203dd0a
  13. extend_neg_masks helper · level 1 · ran · our draft was wrong · 455413c9b171cfe7
  14. GraphLXRTXLayer model · level 0 · unverified · 2445c8cf02121bbf
  15. TransformerEncoder helper · level 1 · ran · 0feddf62036c64ee
  16. TransformerEncoderLayer helper · level 1 · ran · fac115820b1e6391
  17. BertAttention model · level 0 · unverified · c35512e4d250fe83
  18. BertIntermediate helper · level 1 · ran · 97d0724e78e93d36
  19. BertOutput helper · level 0 · unverified · aea48c66c585eea7
  20. BertXAttention helper · level 0 · unverified · 6bed46b39566e949
  21. _get_clones helper · level 1 · ran · our draft was wrong · e63e66b61302a7a2
  22. _get_activation_fn helper · level 1 · ran · our draft was wrong · 0bb264f52e707e08
  23. BertSelfAttention helper · level 0 · unverified · 50a3d34aac2573cd
  24. BertSelfOutput helper · level 0 · unverified · 5a3875e5bed5964b
  25. BertOutAttention helper · level 1 · ran · bfb5cdf1a9ced435
  26. gelu helper · level 1 · ran · honoured contract · fdc64f4c72036ae4
  27. swish helper · level 2 · ran · our draft was wrong · 0f786c407fb1ee4c

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2501.17403") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DiversityVision and Language Navigation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections