Papers › SimVLM: Simple Visual Language Model Pretraining with Weak Supervision

SimVLM: Simple Visual Language Model Pretraining with Weak Supervision

24 Aug 2021ICLR 2022 4arXiv:2108.10904archive 2025-07-28

ZiRui Wang, Jiahui Yu, Adams Wei Yu, Zihang Dai, Yulia Tsvetkov, Yuan Cao

With recent progress in joint modeling of visual and textual representations, Vision-Language Pretraining (VLP) has achieved impressive performance on many multimodal downstream tasks. However, the requirement for expensive annotations including clean image captions and regional labels limits the scalability of existing approaches, and complicates the pretraining procedure with the introduction of multiple dataset-specific objectives. In this work, we relax these constraints and present a minimalist pretraining framework, named Simple Visual Language Model (SimVLM). Unlike prior work, SimVLM reduces the training complexity by exploiting large-scale weak supervision, and is trained end-to-end with a single prefix language modeling objective. Without utilizing extra data or task-specific customization, the resulting model significantly outperforms previous pretraining methods and achieves new state-of-the-art results on a wide range of discriminative and generative vision-language benchmarks, including VQA (+3.74% vqa-score), NLVR2 (+1.17% accuracy), SNLI-VE (+1.37% accuracy) and image captioning tasks (+10.1% average CIDEr score). Furthermore, we demonstrate that SimVLM acquires strong generalization and transfer ability, enabling zero-shot behavior including open-ended visual question answering and cross-modality transfer.

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 37 code samples harvested from 2 repositories linked to this paper: 22 ran (of which 8 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 3 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 15 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 37 samples from 2 repositories, 22 ran (16 with no instrument failure; 6 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 22 samples that ran has no recorded date.

FerryHuang/SimVLM mentioned on GitHubpytorchSyntology: 28 samples, 14 ran (4 instrument-failed) · 14 unverified report
yulong-XJTU/SimVLM mentioned on GitHubpytorchMITSyntology: 9 samples, 8 ran (2 instrument-failed) · 1 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

37 samples harvested: 22 ran (of which 8 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 3 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 15 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 · honoured contract
3ran · violated contract
5ran · our draft was wrong
1ran; the contract check could not run
12ran
15unverified

Licence: 32 of the 37 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

FerryHuang/SimVLM community (archive-listed) 28 samples, 14 ran (4 instrument-failed) · 14 unverified
BottleneckBlock in 5 papers simvlm/modeling_simvlm.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 325812bbd82c157f · report fixture: returned BottleneckBlock · level recorded 2026-09-22
CNNBlockBase simvlm/modeling_simvlm.py ran · metamorphic tier: deterministic no licence file found · pointer only · 38a875bbe943570b · report fixture: returned CNNBlockBase · level recorded 2026-09-22
Conv2d in 43 papers
census: 7 implementations from 7 papers, 6 distinct outputs on one shared input
simvlm/modeling_simvlm.py ran · metamorphic tier: deterministic no licence file found · pointer only · 15258dcfb20b4488 · report fixture: returned Conv2d · level recorded 2026-09-22
FrozenBatchNorm2d simvlm/modeling_simvlm.py ran · metamorphic tier: deterministic no licence file found · pointer only · af6a9f58115fe4d6 · report fixture: returned FrozenBatchNorm2d · level recorded 2026-09-22
SimVLMAttention simvlm/modeling_simvlm.py ran · metamorphic tier: deterministic no licence file found · pointer only · 1150381a8d9193ec · report fixture: returned SimVLMAttention · level recorded 2026-09-22
SimVLMConfig simvlm/modeling_simvlm.py ran · metamorphic tier: deterministic no licence file found · pointer only · 7bb4727aca21db84 · report fixture: returned SimVLMConfig · level recorded 2026-09-22
SimVLMEncoder simvlm/modeling_simvlm.py ran · metamorphic tier: deterministic no licence file found · pointer only · 71c5d4fa9540b172 · report fixture: returned SimVLMEncoder · level recorded 2026-09-22
SimVLMIntermediate simvlm/modeling_simvlm.py ran · metamorphic tier: deterministic no licence file found · pointer only · 81921e47a333c79d · report fixture: returned SimVLMIntermediate · level recorded 2026-09-22
batch_input simvlm/modeling_simvlm.py ran · honoured contract fingerprinted no licence file found · pointer only · f6f30fe91451a8e9 · report fixture: signature input_tensor:Tensor/2/float · returned Tensor · level recorded 2026-09-22
find_pruneable_heads_and_indices in 19 papers simvlm/modeling_simvlm.py ran · our draft was wrong no licence file found · pointer only · a98857f046bfe3d9 · report fixture: signature heads:list/1/int, n_heads:int/0/int, head_size:int/0/int, already_pruned_heads:set/0/? · returned tuple · level recorded 2026-09-22
get_norm in 48 papers simvlm/modeling_simvlm.py ran · our draft was wrong no licence file found · pointer only · 7934a70c6ec449cd · report fixture: signature norm:str/0/str, out_channels:int/0/int · returned FrozenBatchNorm2d · level recorded 2026-09-22
pad_with_id simvlm/modeling_simvlm.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · cddcbab01417b2c1 · report fixture: signature input_ids:Tensor/2/int, max_len:int/0/int, pad_token_id:int/0/int · returned Tensor · level recorded 2026-09-22
prune_linear_layer in 40 papers simvlm/modeling_simvlm.py ran · our draft was wrong no licence file found · pointer only · 52de2aaa15da0643 · report fixture: signature layer:callable/0/?, index:Tensor/1/int, dim:int/0/int · returned Linear · level recorded 2026-09-22
subsequent_mask in 38 papers simvlm/modeling_simvlm.py ran · violated contract no licence file found · pointer only · a9e07bbdd8c03e94 · report fixture: signature size:int/0/int · returned Tensor · level recorded 2026-09-22
SimVLMCrossAttention simvlm/modeling_simvlm.py unverified no licence file found · pointer only · 0ac4351224f69633 · report
SimVLMDecoder simvlm/modeling_simvlm.py unverified no licence file found · pointer only · e21d8701f32d884a · report
SimVLMDecoderLayer simvlm/modeling_simvlm.py unverified no licence file found · pointer only · d5689e71173b58c7 · report
SimVLMEmbeddings simvlm/modeling_simvlm.py unverified no licence file found · pointer only · 5e83675c723559e7 · report
SimVLMEncoderLayer simvlm/modeling_simvlm.py unverified no licence file found · pointer only · 6560411928394c1b · report
SimVLMModel simvlm/modeling_simvlm.py unverified no licence file found · pointer only · aed65580e72ec1ea · report
SimVLMOutput simvlm/modeling_simvlm.py unverified no licence file found · pointer only · bf481d655ef58d6c · report
SimVLMPatchEmbeddings simvlm/modeling_simvlm.py unverified no licence file found · pointer only · 2a710d51d64808b5 · report
SimVLMSelfAttention simvlm/modeling_simvlm.py unverified no licence file found · pointer only · e1e1e84518402f22 · report
SimVLMSelfOutput simvlm/modeling_simvlm.py unverified no licence file found · pointer only · 679fbced2dad1b6f · report
SimVLMTextEmbeddings simvlm/modeling_simvlm.py unverified no licence file found · pointer only · 3e24126396b28223 · report
SimVLMToLogits simvlm/modeling_simvlm.py unverified no licence file found · pointer only · bd7c399bd6fdf0f2 · report
c2_msra_fill simvlm/modeling_simvlm.py unverified no licence file found · pointer only · a3a75620f09b426d · report
yulong-XJTU/SimVLM community (archive-listed) 9 samples, 8 ran (2 instrument-failed) · 1 unverified
basic_clean in 217 papers model/tokenizer.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 98f385d847636a3e · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
clone in 7 papers model/SimVLM.py ran MIT (permissive) · f7592e6aa673ef9a · report fixture: signature module:callable/0/?, N:int/0/int · returned ModuleList · level recorded 2026-09-24
encoder in 30 papers model/torch_transformer.py ran MIT (permissive) · 053efec6ba1e990f · report fixture: signature d_model:int/0/int, nhead:int/0/int, depth:int/0/int, dim_feedforward:int/0/int, dropout:float/0/float, activation:str/0/str · returned TransformerEncoder · level recorded 2026-09-24
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
train_simVLM.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · aa5486a3650902d8 · report fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded
generate_square_subsequent_mask in 30 papers model/SimVLM.py ran · violated contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 32b567f5aaaa591d · report fixture: signature sz:int/0/int · returned Tensor · level recorded 2026-09-22
get_norm in 48 papers model/resblock.py ran MIT (permissive) · 3d914d6f21ea094c · report fixture: signature norm:str/0/str, out_channels:int/0/int · returned FrozenBatchNorm2d · level recorded 2026-09-24
get_pairs in 260 papers model/tokenizer.py ran MIT (permissive) · b50994ad24f6d583 · report fixture: signature word:str/0/str · returned set · level recorded 2026-09-25
whitespace_clean in 230 papers model/tokenizer.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 9542161e9640b858 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
decoder in 19 papers model/torch_transformer.py unverified MIT (permissive) · beb8f635f68b899d · 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 SimVLM (graph method: SimVLM). 28 bricks; individually on a fixture: 14 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 14 unverified. The assembly has not been run end-to-end.

  1. SimVLMModel entry · level 0 · unverified · aed65580e72ec1ea
  2. SimVLMConfig helper · level 1 · ran · 7bb4727aca21db84
  3. SimVLMDecoder model · level 0 · unverified · e21d8701f32d884a
  4. SimVLMEmbeddings helper · level 0 · unverified · 5e83675c723559e7
  5. SimVLMEncoder model · level 1 · ran · 71c5d4fa9540b172
  6. SimVLMToLogits helper · level 0 · unverified · bd7c399bd6fdf0f2
  7. batch_input helper · level 1 · ran · honoured contract · f6f30fe91451a8e9
  8. pad_with_id helper · level 1 · ran; the contract check could not run (RAISES) · cddcbab01417b2c1
  9. subsequent_mask helper · level 1 · ran · violated contract · a9e07bbdd8c03e94
  10. SimVLMDecoderLayer helper · level 0 · unverified · d5689e71173b58c7
  11. SimVLMPatchEmbeddings model · level 0 · unverified · 2a710d51d64808b5
  12. SimVLMTextEmbeddings model · level 0 · unverified · 3e24126396b28223
  13. SimVLMEncoderLayer helper · level 0 · unverified · 6560411928394c1b
  14. SimVLMCrossAttention model · level 0 · unverified · 0ac4351224f69633
  15. SimVLMIntermediate model · level 1 · ran · 81921e47a333c79d
  16. SimVLMOutput model · level 0 · unverified · bf481d655ef58d6c
  17. SimVLMSelfAttention model · level 0 · unverified · e1e1e84518402f22
  18. ResBlock helper · level 0 · unverified · cb7f9fd225d85d47
  19. SimVLMAttention helper · level 1 · ran · 1150381a8d9193ec
  20. BottleneckBlock helper · level 1 · ran · 325812bbd82c157f
  21. Conv2d helper · level 1 · ran · 15258dcfb20b4488
  22. SimVLMSelfOutput helper · level 0 · unverified · 679fbced2dad1b6f
  23. find_pruneable_heads_and_indices helper · level 1 · ran · our draft was wrong · a98857f046bfe3d9
  24. prune_linear_layer helper · level 1 · ran · our draft was wrong · 52de2aaa15da0643
  25. CNNBlockBase helper · level 1 · ran · 38a875bbe943570b
  26. c2_msra_fill helper · level 0 · unverified · a3a75620f09b426d
  27. get_norm helper · level 1 · ran · our draft was wrong · 7934a70c6ec449cd
  28. FrozenBatchNorm2d helper · level 1 · ran · af6a9f58115fe4d6

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="2108.10904") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image CaptioningLanguage ModelingLanguage ModellingQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Captioning COCO Captions SimVLM BLEU-4 40.6 #17 of 41 Archive leaderboard report
Image Captioning COCO Captions SimVLM CIDER 143.3 #17 of 41 Archive leaderboard report
Image Captioning COCO Captions SimVLM METEOR 33.4 #17 of 41 Archive leaderboard report
Image Captioning COCO Captions SimVLM SPICE 25.4 #17 of 41 Archive leaderboard report
Image Captioning nocaps entire Single Model B1 83.78 #6 of 39 Archive leaderboard report
Image Captioning nocaps entire Single Model B2 68.86 #6 of 39 Archive leaderboard report
Image Captioning nocaps entire Single Model B3 51.06 #6 of 39 Archive leaderboard report
Image Captioning nocaps entire Single Model B4 32.2 #6 of 39 Archive leaderboard report
Image Captioning nocaps entire Single Model CIDEr 110.31 #6 of 39 Archive leaderboard report
Image Captioning nocaps entire Single Model METEOR 30.55 #6 of 39 Archive leaderboard report
Image Captioning nocaps entire Single Model ROUGE-L 59.86 #6 of 39 Archive leaderboard report
Image Captioning nocaps entire Single Model SPICE 14.49 #6 of 39 Archive leaderboard report
Image Captioning nocaps in-domain Single Model B1 84.64 #7 of 41 Archive leaderboard report
Image Captioning nocaps in-domain Single Model B2 70.0 #7 of 41 Archive leaderboard report
Image Captioning nocaps in-domain Single Model B3 52.96 #7 of 41 Archive leaderboard report
Image Captioning nocaps in-domain Single Model B4 34.66 #7 of 41 Archive leaderboard report
Image Captioning nocaps in-domain Single Model CIDEr 108.98 #7 of 41 Archive leaderboard report
Image Captioning nocaps in-domain Single Model METEOR 31.97 #7 of 41 Archive leaderboard report
Image Captioning nocaps in-domain Single Model ROUGE-L 61.01 #7 of 41 Archive leaderboard report
Image Captioning nocaps in-domain Single Model SPICE 14.6 #7 of 41 Archive leaderboard report
Image Captioning nocaps near-domain Single Model B1 84.36 #6 of 40 Archive leaderboard report
Image Captioning nocaps near-domain Single Model B2 69.83 #6 of 40 Archive leaderboard report
Image Captioning nocaps near-domain Single Model B3 52.42 #6 of 40 Archive leaderboard report
Image Captioning nocaps near-domain Single Model B4 33.74 #6 of 40 Archive leaderboard report
Image Captioning nocaps near-domain Single Model CIDEr 110.76 #6 of 40 Archive leaderboard report
Image Captioning nocaps near-domain Single Model METEOR 30.97 #6 of 40 Archive leaderboard report
Image Captioning nocaps near-domain Single Model ROUGE-L 60.46 #6 of 40 Archive leaderboard report
Image Captioning nocaps near-domain Single Model SPICE 14.61 #6 of 40 Archive leaderboard report
Image Captioning nocaps out-of-domain Single Model B1 80.89 #6 of 40 Archive leaderboard report
Image Captioning nocaps out-of-domain Single Model B2 64.21 #6 of 40 Archive leaderboard report
Image Captioning nocaps out-of-domain Single Model B3 44.38 #6 of 40 Archive leaderboard report
Image Captioning nocaps out-of-domain Single Model B4 24.47 #6 of 40 Archive leaderboard report
Image Captioning nocaps out-of-domain Single Model CIDEr 109.49 #6 of 40 Archive leaderboard report
Image Captioning nocaps out-of-domain Single Model METEOR 27.91 #6 of 40 Archive leaderboard report
Image Captioning nocaps out-of-domain Single Model ROUGE-L 56.69 #6 of 40 Archive leaderboard report
Image Captioning nocaps out-of-domain Single Model SPICE 13.89 #6 of 40 Archive leaderboard report
Image Captioning nocaps-val-in-domain SimVLM CIDEr 113.7 #6 of 11 Archive leaderboard report
Image Captioning nocaps-val-in-domain SimVLM Pre-train (#images) 1.8B #6 of 11 Archive leaderboard report
Image Captioning nocaps-val-in-domain SimVLM SPICE - #6 of 11 Archive leaderboard report
Image Captioning nocaps-val-near-domain SimVLM CIDEr 110.9 #6 of 10 Archive leaderboard report
Image Captioning nocaps-val-near-domain SimVLM Pre-train (#images) 1.8B #6 of 10 Archive leaderboard report
Image Captioning nocaps-val-near-domain SimVLM SPICE - #6 of 10 Archive leaderboard report
Image Captioning nocaps-val-out-domain SimVLM CIDEr 115.2 #5 of 10 Archive leaderboard report
Image Captioning nocaps-val-out-domain SimVLM Pretrain (#images) 1.8B #5 of 10 Archive leaderboard report
Image Captioning nocaps-val-out-domain SimVLM SPICE - #5 of 10 Archive leaderboard report
Image Captioning nocaps-val-overall SimVLM CIDEr 112.2 #6 of 11 Archive leaderboard report
Image Captioning nocaps-val-overall SimVLM Pretrain (#images) 1.8B #6 of 11 Archive leaderboard report
Image Captioning nocaps-val-overall SimVLM SPICE - #6 of 11 Archive leaderboard report
Visual Entailment SNLI-VE test SimVLM Accuracy 86.32 #4 of 8 Archive leaderboard report
Visual Entailment SNLI-VE val SimVLM Accuracy 86.21 #4 of 9 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-dev SimVLM Accuracy 80.03 #14 of 56 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-std SimVLM overall 80.34 #6 of 38 Archive leaderboard report
Visual Reasoning NLVR2 Dev SimVLM Accuracy 84.53 #8 of 15 Archive leaderboard report
Visual Reasoning NLVR2 Test SimVLM Accuracy 85.15 #7 of 14 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

Introduced by this paper: SimVLM

SimVLM

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