Papers › VD-BERT: A Unified Vision and Dialog Transformer with BERT

VD-BERT: A Unified Vision and Dialog Transformer with BERT

28 Apr 2020EMNLP 2020 11arXiv:2004.13278archive 2025-07-28

Yue Wang, Shafiq Joty, Michael R. Lyu, Irwin King, Caiming Xiong, Steven C. H. Hoi

Visual dialog is a challenging vision-language task, where a dialog agent needs to answer a series of questions through reasoning on the image content and dialog history. Prior work has mostly focused on various attention mechanisms to model such intricate interactions. By contrast, in this work, we propose VD-BERT, a simple yet effective framework of unified vision-dialog Transformer that leverages the pretrained BERT language models for Visual Dialog tasks. The model is unified in that (1) it captures all the interactions between the image and the multi-turn dialog using a single-stream Transformer encoder, and (2) it supports both answer ranking and answer generation seamlessly through the same architecture. More crucially, we adapt BERT for the effective fusion of vision and dialog contents via visually grounded training. Without the need of pretraining on external vision-language data, our model yields new state of the art, achieving the top position in both single-model and ensemble settings (74.54 and 75.35 NDCG scores) on the visual dialog leaderboard. Our code and pretrained models are released at https://github.com/salesforce/VD-BERT.

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 11 code samples harvested from 1 repository linked to this paper: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 11 samples from 1 repository, 2 ran (2 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.

salesforce/VD-BERT officialmentioned in paperpytorchSyntology: 11 samples, 2 ran (0 instrument-failed) · 9 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

11 samples harvested: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 9 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.

2ran
9unverified

Licence: 0 of the 11 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 salesforce/VD-BERT. “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.

salesforce/VD-BERT official repository 11 samples, 2 ran (0 instrument-failed) · 9 unverified
BertConfig in 14 papers pytorch_pretrained_bert/modeling.py ran MIT (permissive) · 270c717db63a62be · report fixture: returned BertConfig · level recorded 2026-09-22
BertSelfAttention in 29 papers pytorch_pretrained_bert/modeling.py ran MIT (permissive) · 39133fc31b6e7ba0 · report fixture: signature hidden_states:Tensor/3/float, attention_mask:Tensor/4/float, history_states:NoneType/0/? · returned Tensor · level recorded 2026-09-24
BertAttention in 28 papers pytorch_pretrained_bert/modeling.py unverified MIT (permissive) · a37aa2973e8e5c9f · report
BertEmbeddings in 21 papers pytorch_pretrained_bert/modeling.py unverified MIT (permissive) · d128e762e565e2bb · report
BertEncoder in 20 papers pytorch_pretrained_bert/modeling.py unverified MIT (permissive) · 3001206d0b79eb22 · report
BertLayer in 23 papers pytorch_pretrained_bert/modeling.py unverified MIT (permissive) · 9f308c4ca55ba13a · report
BertModel in 16 papers pytorch_pretrained_bert/modeling.py unverified MIT (permissive) · b76586b7d7a5e61f · report
BertModelIncr pytorch_pretrained_bert/modeling.py unverified MIT (permissive) · 4339e883ae5cd42b · report
BertOutput in 13 papers pytorch_pretrained_bert/modeling.py unverified MIT (permissive) · 4a7f9dbc40aaed5d · report
BertSelfOutput in 14 papers pytorch_pretrained_bert/modeling.py unverified MIT (permissive) · 3b0ae0e2b34fdf2e · report
PreTrainedBertModel pytorch_pretrained_bert/modeling.py unverified MIT (permissive) · 6d0e6e5f9872487f · 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 VD-BERT (graph method: VD-BERT). 23 bricks; individually on a fixture: 10 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified. The assembly has not been run end-to-end.

  1. BertModelIncr entry · level 0 · unverified · 4339e883ae5cd42b
  2. BertModel helper · level 0 · unverified · b76586b7d7a5e61f
  3. BertEmbeddings model · level 0 · unverified · d128e762e565e2bb
  4. BertEncoder model · level 0 · unverified · 3001206d0b79eb22
  5. BertPooler helper · level 1 · ran · 8f1a0b9437ccc562
  6. PreTrainedBertModel helper · level 0 · unverified · 6d0e6e5f9872487f
  7. BertLayer model · level 0 · unverified · 9f308c4ca55ba13a
  8. BertConfig helper · level 1 · ran · 270c717db63a62be
  9. cached_path helper · level 1 · ran · our draft was wrong · 534dfe582037c26b
  10. BertAttention helper · level 0 · unverified · a37aa2973e8e5c9f
  11. BertIntermediate helper · level 1 · ran · 9597f5146c4fa55c
  12. BertOutput helper · level 0 · unverified · 4a7f9dbc40aaed5d
  13. get_from_cache helper · level 0 · unverified · e25398920d88eec3
  14. BertSelfAttention model · level 1 · ran · 39133fc31b6e7ba0
  15. BertSelfOutput helper · level 0 · unverified · 3b0ae0e2b34fdf2e
  16. http_get helper · level 0 · unverified · 20bb0eaadd1d38ce
  17. s3_etag helper · level 0 · unverified · 43b164ab6ace951e
  18. s3_get helper · level 0 · unverified · d3da3cf9bfe8b9a5
  19. url_to_filename helper · level 1 · ran · our draft was wrong · af64ec220e8bcdbc
  20. s3_request helper · level 1 · ran · our draft was wrong · d03f582131d8575c
  21. split_s3_path helper · level 1 · ran · our draft was wrong · 1f8e0d57a93f2b98
  22. gelu helper · level 1 · ran · honoured contract · 40e9fee2e0b7e278
  23. 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="2004.13278") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Answer GenerationVisual Dialog

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionAttention DropoutBERTBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionSoftmaxTransformerWeight DecayWordPiece

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