Papers › History Aware Multimodal Transformer for Vision-and-Language Navigation

History Aware Multimodal Transformer for Vision-and-Language Navigation

25 Oct 2021NeurIPS 2021 12arXiv:2110.13309archive 2025-07-28

ShiZhe Chen, Pierre-Louis Guhur, Cordelia Schmid, Ivan Laptev

Vision-and-language navigation (VLN) aims to build autonomous visual agents that follow instructions and navigate in real scenes. To remember previously visited locations and actions taken, most approaches to VLN implement memory using recurrent states. Instead, we introduce a History Aware Multimodal Transformer (HAMT) to incorporate a long-horizon history into multimodal decision making. HAMT efficiently encodes all the past panoramic observations via a hierarchical vision transformer (ViT), which first encodes individual images with ViT, then models spatial relation between images in a panoramic observation and finally takes into account temporal relation between panoramas in the history. It, then, jointly combines text, history and current observation to predict the next action. We first train HAMT end-to-end using several proxy tasks including single step action prediction and spatial relation prediction, and then use reinforcement learning to further improve the navigation policy. HAMT achieves new state of the art on a broad range of VLN tasks, including VLN with fine-grained instructions (R2R, RxR), high-level instructions (R2R-Last, REVERIE), dialogs (CVDN) as well as long-horizon VLN (R4R, R2R-Back). We demonstrate HAMT to be particularly effective for navigation tasks with longer trajectories.

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 15 code samples harvested from 1 repository linked to this paper: 7 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 15 samples from 1 repository, 7 ran (7 with no instrument failure; 0 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.

cshizhe/vln-hamt mentioned on GitHubpytorchSyntology: 15 samples, 7 ran (0 instrument-failed) · 8 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

15 samples harvested: 7 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 8 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.

7ran
8unverified

Licence: 0 of the 15 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 cshizhe/vln-hamt. “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 2 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.

cshizhe/vln-hamt community (archive-listed) 15 samples, 7 ran (0 instrument-failed) · 8 unverified
BertEmbeddings in 21 papers finetune_src/models/vilmodel_cmt.py ran · metamorphic tier: deterministic MIT (permissive) · 43ea2bbc815e3fd5 · report fixture: returned BertEmbeddings · level recorded 2026-09-22
BertIntermediate in 15 papers finetune_src/models/vilmodel_cmt.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 97d0724e78e93d36 · report fixture: returned BertIntermediate · level recorded 2026-09-22
BertOutput in 13 papers finetune_src/models/vilmodel_cmt.py ran MIT (permissive) · 6c574c57986a3d21 · report fixture: signature hidden_states:Tensor/3/float, input_tensor:Tensor/3/float · returned Tensor · level recorded 2026-09-24
BertSelfOutput in 14 papers finetune_src/models/vilmodel_cmt.py ran MIT (permissive) · 2e4a0b2327855df3 · report fixture: signature hidden_states:Tensor/3/float, input_tensor:Tensor/3/float · returned Tensor · level recorded 2026-09-24
BertXAttention finetune_src/models/vilmodel_cmt.py ran MIT (permissive) · 8a5135e42774f599 · report fixture: signature input_tensor:Tensor/3/float, ctx_tensor:Tensor/3/float, ctx_att_mask:Tensor/4/float · returned tuple · level recorded 2026-09-24
ImageEmbeddings in 7 papers finetune_src/models/vilmodel_cmt.py ran MIT (permissive) · cb7d5749c6b79a1b · report fixture: signature img_feat:Tensor/3/float, ang_feat:Tensor/3/float, type_embeddings:Tensor/3/float, nav_types:Tensor/2/int · returned Tensor · level recorded 2026-09-24
NextActionPrediction finetune_src/models/vilmodel_cmt.py ran · metamorphic tier: deterministic MIT (permissive) · f8175627f6813677 · report fixture: returned NextActionPrediction · level recorded 2026-09-22
BertAttention in 28 papers finetune_src/models/vilmodel_cmt.py unverified MIT (permissive) · 13836f9b26886d79 · report
BertEncoder in 20 papers finetune_src/models/vilmodel_cmt.py unverified MIT (permissive) · 35a750d77f3a1303 · report
BertLayer in 23 papers finetune_src/models/vilmodel_cmt.py unverified MIT (permissive) · 8c82bbeb6226b351 · report
BertSelfAttention in 29 papers finetune_src/models/vilmodel_cmt.py unverified MIT (permissive) · c08a770513cf174b · report
HistoryEmbeddings finetune_src/models/vilmodel_cmt.py unverified MIT (permissive) · 25134291a74bace2 · report
LXRTXLayer in 5 papers finetune_src/models/vilmodel_cmt.py unverified MIT (permissive) · 169082b5fe3d0fbc · report
LxmertEncoder finetune_src/models/vilmodel_cmt.py unverified MIT (permissive) · e60d770a83baf317 · report
NavCMT finetune_src/models/vilmodel_cmt.py unverified MIT (permissive) · c399f3a94801c4fd · 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 History Aware Multimodal Transformer (HAMT) (graph method: History Aware Multimodal Transformer (HAMT)). 18 bricks; individually on a fixture: 10 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

  1. NavCMT entry · level 0 · unverified · c399f3a94801c4fd
  2. BertEmbeddings model · level 1 · ran · 43ea2bbc815e3fd5
  3. HistoryEmbeddings model · level 0 · unverified · 25134291a74bace2
  4. ImageEmbeddings model · level 1 · ran · cb7d5749c6b79a1b
  5. LxmertEncoder helper · level 0 · unverified · e60d770a83baf317
  6. NextActionPrediction model · level 1 · ran · f8175627f6813677
  7. BertEncoder model · level 0 · unverified · 35a750d77f3a1303
  8. BertLayer model · level 0 · unverified · 8c82bbeb6226b351
  9. LXRTXLayer helper · level 0 · unverified · 169082b5fe3d0fbc
  10. BertAttention helper · level 0 · unverified · 13836f9b26886d79
  11. BertIntermediate helper · level 1 · ran · 97d0724e78e93d36
  12. BertOutput helper · level 1 · ran · 6c574c57986a3d21
  13. BertXAttention helper · level 1 · ran · 8a5135e42774f599
  14. BertSelfAttention helper · level 0 · unverified · c08a770513cf174b
  15. BertSelfOutput helper · level 1 · ran · 2e4a0b2327855df3
  16. BertOutAttention helper · level 1 · ran · bfb5cdf1a9ced435
  17. gelu helper · level 1 · ran · honoured contract · fdc64f4c72036ae4
  18. 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="2110.13309") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Decision MakingNavigateRelation PredictionVision and Language Navigation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Vision and Language Navigation RxR HAMT ndtw 59.94 #3 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AWAREAbsolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerVision Transformer

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