Methods › Natural Language Processing › Autoregressive Transformers › Transformer

Transformer

13,999 papers tagged archive 2025-07-28

Introduced by Ashish Vaswani et al. in Attention Is All You Need

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

A Transformer is a model architecture that eschews recurrence and instead relies entirely on an attention mechanism to draw global dependencies between input and output. Before Transformers, the dominant sequence transduction models were based on complex recurrent or convolutional neural networks that include an encoder and a decoder. The Transformer also employs an encoder and decoder, but removing recurrence in favor of attention mechanisms allows for significantly more parallelization than methods like RNNs and CNNs.

PaperSourceSee Code · tunz/transformer-pytorch

In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 593 in the graph, strongest link: official). This answer is about arXiv:1706.03762, the paper the archive credits with this method.

Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.

Origin paper of this answer, arXiv:1706.03762 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified (of 946 harvested samples) · 451 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).

Papers archive 2025-07-28

archive papers tagged: 13,999 · with a code link: 6,572 · where Syntology ran a sample: 2,248 (1,844 with a run with no instrument failure, 404 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (2,248 of 13,999 tagged: 1,844 with a run with no instrument failure, 404 where every run was a failure of Syntology's instrument)

Page 1 of 140: papers 1 to 100 of 13,999, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 2,170 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Language Modelling1,237
Decoder1,068
Language Modeling949
Translation758
Machine Translation718
Semantic Segmentation679
Object Detection552
Image Classification524
Question Answering514
object-detection497
Retrieval455
Sentence454
Segmentation448
Representation Learning428
image-classification414
Large Language Model409
Time Series377
Object352
Text Generation317
Transfer Learning294

Usage over time archive 2025-07-28

Papers per year tagged with Transformer: 2017 to 2025, peak 4,361 4,361 0 2017: 21 papers 2017 2018: 115 papers 2018 2019: 510 papers 2019 2020: 824 papers 2020 2021: 1476 papers 2021 2022: 1883 papers 2022 2023: 3228 papers 2023 2024: 4361 papers 2024 2025: 1581 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (13,999 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Autoregressive TransformersTransformers

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