Papers › Grounded Entity-Landmark Adaptive Pre-training for Vision-and-Language Navigation

Grounded Entity-Landmark Adaptive Pre-training for Vision-and-Language Navigation

24 Aug 2023ICCV 2023 1arXiv:2308.12587archive 2025-07-28

Yibo Cui, Liang Xie, Yakun Zhang, Meishan Zhang, Ye Yan, Erwei Yin

Cross-modal alignment is one key challenge for Vision-and-Language Navigation (VLN). Most existing studies concentrate on mapping the global instruction or single sub-instruction to the corresponding trajectory. However, another critical problem of achieving fine-grained alignment at the entity level is seldom considered. To address this problem, we propose a novel Grounded Entity-Landmark Adaptive (GELA) pre-training paradigm for VLN tasks. To achieve the adaptive pre-training paradigm, we first introduce grounded entity-landmark human annotations into the Room-to-Room (R2R) dataset, named GEL-R2R. Additionally, we adopt three grounded entity-landmark adaptive pre-training objectives: 1) entity phrase prediction, 2) landmark bounding box prediction, and 3) entity-landmark semantic alignment, which explicitly supervise the learning of fine-grained cross-modal alignment between entity phrases and environment landmarks. Finally, we validate our model on two downstream benchmarks: VLN with descriptive instructions (R2R) and dialogue instructions (CVDN). The comprehensive experiments show that our GELA model achieves state-of-the-art results on both tasks, demonstrating its effectiveness and generalizability.

PaperPDFConference PDFCodeCode 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 30 code samples harvested from 1 repository linked to this paper: 23 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 30 samples from 1 repository, 23 ran (20 with no instrument failure; 3 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

csir1996/vln-gela officialmentioned in papermentioned on GitHubpytorchSyntology: 30 samples, 23 ran (3 instrument-failed) · 7 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

30 samples harvested: 23 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 3 where Syntology's instrument failed) · 7 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.

3ran · our draft was wrong
20ran
7unverified

Licence: 30 of the 30 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 csir1996/vln-gela. “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”. For 12 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

csir1996/vln-gela official repository 30 samples, 23 ran (3 instrument-failed) · 7 unverified
BboxPrediction ada_pretrain_src/model/pretrain_cmt.py ran no licence file found · pointer only · 3372a10f9d714c01 · report fixture: returned BboxPrediction · level recorded 2026-09-22
BertAttention in 28 papers ada_pretrain_src/model/pretrain_cmt.py ran fingerprinted no licence file found · pointer only · f11fe3d331f06585 · report fixture: signature input_tensor:Tensor/3/float, attention_mask:Tensor/4/float, head_mask:NoneType/0/? · returned tuple · level recorded 2026-09-24
BertEmbeddings in 21 papers ada_pretrain_src/model/pretrain_cmt.py ran no licence file found · pointer only · e11f492583515dc1 · report fixture: returned BertEmbeddings · level recorded 2026-09-22
BertIntermediate in 15 papers ada_pretrain_src/model/pretrain_cmt.py ran fingerprinted no licence file found · pointer only · 80fb8132656f0023 · report fixture: returned BertIntermediate · level recorded 2026-09-22
BertLMPredictionHead in 10 papers ada_pretrain_src/model/pretrain_cmt.py ran fingerprinted no licence file found · pointer only · 6ef8a8f38e5061ea · report fixture: returned BertLMPredictionHead · level recorded 2026-09-22
BertLayer in 23 papers ada_pretrain_src/model/pretrain_cmt.py ran no licence file found · pointer only · cae60f381a5d3991 · report fixture: signature hidden_states:Tensor/3/float, attention_mask:Tensor/4/float · returned tuple · level recorded 2026-09-24
BertOnlyMLMHead ada_pretrain_src/model/pretrain_cmt.py ran no licence file found · pointer only · 2076765f9269ebfb · report fixture: returned BertOnlyMLMHead · level recorded 2026-09-22
BertOutAttention ada_pretrain_src/model/pretrain_cmt.py ran no licence file found · pointer only · c6b2b7a8ef4effa8 · report fixture: returned BertOutAttention · level recorded 2026-09-22
BertOutput in 13 papers ada_pretrain_src/model/pretrain_cmt.py ran no licence file found · pointer only · 6b2df70e78c4e5e8 · report fixture: returned BertOutput · level recorded 2026-09-22
BertPredictionHeadTransform in 10 papers ada_pretrain_src/model/pretrain_cmt.py ran fingerprinted no licence file found · pointer only · a1405b4b0349031c · report fixture: returned BertPredictionHeadTransform · level recorded 2026-09-22
BertSelfOutput in 14 papers ada_pretrain_src/model/pretrain_cmt.py ran no licence file found · pointer only · d50e815eff85ec2b · report fixture: signature hidden_states:Tensor/3/float, input_tensor:Tensor/3/float · returned Tensor · level recorded 2026-09-24
BertXAttention ada_pretrain_src/model/pretrain_cmt.py ran fingerprinted no licence file found · pointer only · e438c17327d8794a · report fixture: signature input_tensor:Tensor/3/float, ctx_tensor:Tensor/3/float, ctx_att_mask:Tensor/4/float · returned Tensor · level recorded 2026-09-24
GIoU_Loss ada_pretrain_src/model/pretrain_cmt.py ran · our draft was wrong fingerprinted no licence file found · pointer only · f1ea5386ce472284 · report fixture: signature boxes1:Tensor/2/float, boxes2:Tensor/2/float, size:int/0/int · returned Tensor · level recorded 2026-09-22
ImageEmbeddings in 7 papers ada_pretrain_src/model/pretrain_cmt.py ran no licence file found · pointer only · 910bb71e7ef2b112 · report fixture: signature img_feat:Tensor/2/float, ang_feat:Tensor/2/float, type_embeddings:Tensor/2/float, nav_types:Tensor/1/int · returned Tensor · level recorded 2026-09-24
ItmPrediction ada_pretrain_src/model/pretrain_cmt.py ran no licence file found · pointer only · 698a681ee3009703 · report fixture: returned ItmPrediction · level recorded 2026-09-22
NextActionPrediction ada_pretrain_src/model/pretrain_cmt.py ran no licence file found · pointer only · 2c41dd19d952d068 · report fixture: returned NextActionPrediction · level recorded 2026-09-22
NextActionRegression ada_pretrain_src/model/pretrain_cmt.py ran no licence file found · pointer only · e35313209150244f · report fixture: returned NextActionRegression · level recorded 2026-09-22
Reg_Loss ada_pretrain_src/model/pretrain_cmt.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 33a4a4477537ad1c · report fixture: signature output:Tensor/2/float, target:Tensor/2/float · returned Tensor · level recorded 2026-09-22
RegionClassification ada_pretrain_src/model/pretrain_cmt.py ran no licence file found · pointer only · db3b410d57d99c4c · report fixture: returned RegionClassification · level recorded 2026-09-22
SoftDotAttention ada_pretrain_src/model/pretrain_cmt.py ran fingerprinted no licence file found · pointer only · 37cdafb5cc664e9a · report fixture: signature h:Tensor/2/float, context:Tensor/3/float, mask:Tensor/2/bool, output_tilde:bool/0/bool, output_prob:bool/0/bool · returned tuple · level recorded 2026-09-24
SpanPrediction ada_pretrain_src/model/pretrain_cmt.py ran no licence file found · pointer only · eda2157dc8f3fd1d · report fixture: returned SpanPrediction · level recorded 2026-09-22
SpatialRelRegression ada_pretrain_src/model/pretrain_cmt.py ran no licence file found · pointer only · b3f29a55ce1e133c · report fixture: returned SpatialRelRegression · level recorded 2026-09-22
xyxy2xywh in 19 papers ada_pretrain_src/model/pretrain_cmt.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 3d629255e4cf4ea2 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
BertEncoder in 20 papers ada_pretrain_src/model/pretrain_cmt.py unverified no licence file found · pointer only · 8654eadc64d1d6d9 · report
BertSelfAttention in 29 papers ada_pretrain_src/model/pretrain_cmt.py unverified no licence file found · pointer only · 181a8da7e0d87dd3 · report
HistoryEmbeddings ada_pretrain_src/model/pretrain_cmt.py unverified no licence file found · pointer only · ed5264df2e315411 · report
LXRTXLayer in 5 papers ada_pretrain_src/model/pretrain_cmt.py unverified no licence file found · pointer only · 3f87e422545347a0 · report
LxmertEncoder ada_pretrain_src/model/pretrain_cmt.py unverified no licence file found · pointer only · d236f85a9fdbe5cd · report
MultiStepNavCMTPreTraining ada_pretrain_src/model/pretrain_cmt.py unverified no licence file found · pointer only · b473bd940f0c9a55 · report
NavPreTrainedModel ada_pretrain_src/model/pretrain_cmt.py unverified no licence file found · pointer only · dda880a7d9edaf1b · 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 GELA (graph method: GELA). 32 bricks; individually on a fixture: 25 ran (of which 14 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 0 violated, 20 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. MultiStepNavCMTPreTraining entry · level 0 · unverified · b473bd940f0c9a55
  2. BboxPrediction model · level 1 · ran · 3372a10f9d714c01
  3. BertOnlyMLMHead helper · level 1 · ran · 2076765f9269ebfb
  4. GIoU_Loss loss · level 1 · ran · our draft was wrong · f1ea5386ce472284
  5. ItmPrediction model · level 1 · ran · 698a681ee3009703
  6. NavPreTrainedModel helper · level 0 · unverified · dda880a7d9edaf1b
  7. NextActionPrediction model · level 1 · ran · 2c41dd19d952d068
  8. NextActionRegression model · level 1 · ran · e35313209150244f
  9. Reg_Loss loss · level 1 · ran · our draft was wrong · 33a4a4477537ad1c
  10. RegionClassification model · level 1 · ran · db3b410d57d99c4c
  11. SoftDotAttention model · level 1 · ran · 37cdafb5cc664e9a
  12. SpanPrediction model · level 1 · ran · eda2157dc8f3fd1d
  13. SpatialRelRegression model · level 1 · ran · b3f29a55ce1e133c
  14. xyxy2xywh helper · level 1 · ran · our draft was wrong · 3d629255e4cf4ea2
  15. BertLMPredictionHead helper · level 1 · ran · 6ef8a8f38e5061ea
  16. BertEmbeddings helper · level 1 · ran · e11f492583515dc1
  17. HistoryEmbeddings model · level 0 · unverified · ed5264df2e315411
  18. ImageEmbeddings model · level 1 · ran · 910bb71e7ef2b112
  19. LxmertEncoder helper · level 0 · unverified · d236f85a9fdbe5cd
  20. BertPredictionHeadTransform helper · level 1 · ran · a1405b4b0349031c
  21. BertEncoder model · level 0 · unverified · 8654eadc64d1d6d9
  22. BertLayer model · level 1 · ran · cae60f381a5d3991
  23. LXRTXLayer helper · level 0 · unverified · 3f87e422545347a0
  24. BertAttention helper · level 1 · ran · f11fe3d331f06585
  25. BertIntermediate helper · level 1 · ran · 80fb8132656f0023
  26. BertOutput helper · level 1 · ran · 6b2df70e78c4e5e8
  27. BertXAttention helper · level 1 · ran · e438c17327d8794a
  28. BertSelfAttention helper · level 0 · unverified · 181a8da7e0d87dd3
  29. BertSelfOutput helper · level 1 · ran · d50e815eff85ec2b
  30. BertOutAttention helper · level 1 · ran · c6b2b7a8ef4effa8
  31. gelu helper · level 1 · ran · honoured contract · c2f0705ed8e6f7e6
  32. 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="2308.12587") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DescriptiveVision and Language Navigationcross-modal alignment

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