Papers › Multi-stage Pre-training over Simplified Multimodal Pre-training Models

Multi-stage Pre-training over Simplified Multimodal Pre-training Models

22 Jul 2021ACL 2021 5arXiv:2107.14596archive 2025-07-28

Tongtong Liu, Fangxiang Feng, Xiaojie Wang

Multimodal pre-training models, such as LXMERT, have achieved excellent results in downstream tasks. However, current pre-trained models require large amounts of training data and have huge model sizes, which make them difficult to apply in low-resource situations. How to obtain similar or even better performance than a larger model under the premise of less pre-training data and smaller model size has become an important problem. In this paper, we propose a new Multi-stage Pre-training (MSP) method, which uses information at different granularities from word, phrase to sentence in both texts and images to pre-train the model in stages. We also design several different pre-training tasks suitable for the information granularity in different stage in order to efficiently capture the diverse knowledge from a limited corpus. We take a Simplified LXMERT (LXMERT- S), which has only 45.9% parameters of the original LXMERT model and 11.76% of the original pre-training data as the testbed of our MSP method. Experimental results show that our method achieves comparable performance to the original LXMERT model in all downstream tasks, and even outperforms the original model in Image-Text Retrieval task.

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 9 code samples harvested from 1 repository linked to this paper: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 9 samples from 1 repository, 3 ran (3 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

lttsmn/LXMERT-S officialmentioned in papermentioned on GitHubpytorchSyntology: 9 samples, 3 ran (0 instrument-failed) · 6 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

9 samples harvested: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. “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
6unverified

Licence: 9 of the 9 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 lttsmn/LXMERT-S. “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 1 sample 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.

lttsmn/LXMERT-S official repository 9 samples, 3 ran (0 instrument-failed) · 6 unverified
BertEmbeddings in 21 papers Desktop/LXMERT_S/src/lxrt/modeling.py ran no licence file found · pointer only · 4f3d156722ae6484 · report fixture: returned BertEmbeddings · level recorded 2026-09-22
BertPreTrainingHeads in 5 papers Desktop/LXMERT_S/src/lxrt/modeling.py ran no licence file found · pointer only · b73e9276dedf22b1 · report fixture: returned BertPreTrainingHeads · level recorded 2026-09-22
BertVisualObjHead Desktop/LXMERT_S/src/lxrt/modeling.py ran no licence file found · pointer only · 56de2614fb65d900 · report fixture: returned BertVisualObjHead · level recorded 2026-09-22
BertPooler_f Desktop/LXMERT_S/src/lxrt/modeling.py unverified no licence file found · pointer only · d5dc0e31d63ec9e0 · report
BertPreTrainedModel in 7 papers Desktop/LXMERT_S/src/lxrt/modeling.py unverified no licence file found · pointer only · 189cb1190e0c5d7f · report
LXRTEncoder Desktop/LXMERT_S/src/lxrt/modeling.py unverified no licence file found · pointer only · c28fb0dede8ddf0e · report
LXRTModel Desktop/LXMERT_S/src/lxrt/modeling.py unverified no licence file found · pointer only · 0d7751185daf9729 · report
LXRTPretraining Desktop/LXMERT_S/src/lxrt/modeling.py unverified no licence file found · pointer only · 2956eeaed8f53a22 · report
load_tf_weights_in_bert in 135 papers Desktop/LXMERT_S/src/lxrt/modeling.py unverified no licence file found · pointer only · fc89e34806bd2562 · 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 Multi-stage Pre-training (graph method: Multi-stage Pre-training). 35 bricks; individually on a fixture: 20 ran (of which 13 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 0 violated, 16 with no contract checked; 3 where Syntology's instrument failed) · 15 unverified. The assembly has not been run end-to-end.

  1. LXRTPretraining entry · level 0 · unverified · 2956eeaed8f53a22
  2. BertPreTrainedModel helper · level 0 · unverified · 189cb1190e0c5d7f
  3. BertPreTrainingHeads model · level 1 · ran · b73e9276dedf22b1
  4. BertVisualAnswerHead helper · level 1 · ran · 2c8c022f71d9ae6e
  5. BertVisualObjHead model · level 1 · ran · 56de2614fb65d900
  6. LXRTModel model · level 0 · unverified · 0d7751185daf9729
  7. BertConfig helper · level 1 · ran · 5324d31f8ea9ca59
  8. cached_path helper · level 0 · unverified · a4e8483353cec520
  9. load_tf_weights_in_bert helper · level 0 · unverified · fc89e34806bd2562
  10. BertLMPredictionHead helper · level 0 · unverified · 77ff902ef6858211
  11. GeLU helper · level 1 · ran · ce655ad320784ce8
  12. BertPredictionHeadTransform helper · level 1 · ran · 2ba3b1dfb07ba4b1
  13. BertEmbeddings helper · level 1 · ran · 4f3d156722ae6484
  14. BertPooler helper · level 1 · ran · 8f1a0b9437ccc562
  15. BertPooler_f helper · level 0 · unverified · d5dc0e31d63ec9e0
  16. LXRTEncoder helper · level 0 · unverified · c28fb0dede8ddf0e
  17. get_from_cache helper · level 0 · unverified · 242c3c3d7e930e18
  18. gelu helper · level 1 · ran · honoured contract · fdc64f4c72036ae4
  19. BertLayer helper · level 0 · unverified · 2f7d2c26e185cb3f
  20. LXRTXLayer helper · level 0 · unverified · 0b1bea7c4d0afd60
  21. VisualFeatEncoder helper · level 1 · ran · 62eb6af27b771c4f
  22. http_get helper · level 0 · unverified · 18f49ada16168f38
  23. s3_etag helper · level 0 · unverified · 51dd06ec77c8a8d1
  24. s3_get helper · level 0 · unverified · 1079045e75efbf23
  25. url_to_filename helper · level 1 · ran · our draft was wrong · 5eff22fa0a651276
  26. BertIntermediate helper · level 1 · ran · c7123d4962da3767
  27. BertOutput helper · level 1 · ran · 61f383a856ac089e
  28. BertSelfattLayer helper · level 1 · ran · 9c6012122feb6f81
  29. BertCrossattLayer helper · level 1 · ran · 0e0a344be52d2fdc
  30. s3_request helper · level 1 · ran · our draft was wrong · 7661139be003d514
  31. split_s3_path helper · level 0 · unverified · d3852f416bfe86c3
  32. BertAttOutput helper · level 1 · ran · 5ccefc0113e7b26e
  33. BertAttention helper · level 1 · ran · b8c495ff176f844a
  34. VisualConfig helper · level 1 · ran · 3644fb46790a5387
  35. 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="2107.14596") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image-text RetrievalRetrievalSentenceText Retrieval

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

LXMERT

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