Home › Code › AttentionLayer

AttentionLayer

Syntologyentry name in harvested coderead from the graph 2026-09-24

AttentionLayer appears in the code Syntology harvested for 30 papers, as 35 distinct code bodies found in 35 places (a place is one code body under one paper). At least one of them ran in 26 of the papers; 2 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named AttentionLayer do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 29 of the 35 distinct code bodies named AttentionLayer; 6 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
0ran · our draft was wrong
0ran · fixture could not drive it
29ran
6unverified
2fingerprinted

Licence is a property of each copy, so it is counted per place: 16 of the 35 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

30 papers shown of 30, newest first; 35 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 8 papers added by Syntology; 1 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
XCTFormer: Leveraging Cross-Channel and Cross-Time Dependencies for Enhanced Time-Series Analysis added by Syntology 2026-05 (from id) azencot-group/XCTFormer/models/XCTFormer.py 5c4ad949268524e4 ran · metamorphic tier: deterministic no licence file found · pointer only
PULSE: Generative Phase Evolution for Non-Stationary Time Series Forecasting added by Syntology 2026-05 (from id) Gemost/PULSE/models/PULSE.py 1337e025505f56d1 ran · metamorphic tier: deterministic no licence file found · pointer only
ROM: Real-time Overthinking Mitigation via Streaming Detection and Intervention added by Syntology 2026-03 (from id) SaFo-Lab/ROM/rom/models.py 279e64cc9defba19 ran MIT (permissive)
Holter-to-Sleep: AI-Enabled Repurposing of Single-Lead ECG for Sleep Phenotyping added by Syntology 2026-03 (from id) xdl1216/Holter-to-Sleep/sleep_staging/cnn/net1d.py 7fdaf9c68e00ba05 ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only
Neural Latent Arbitrary Lagrangian-Eulerian Grids for Fluid-Solid Interaction added by Syntology 2026-03 (from id) therontau0054/Fisale/model/fisale.py 7120dfd0aa412331 ran MIT (permissive)
LEFT: Learnable Fusion of Tri-view Tokens for Unsupervised Time Series Anomaly Detection added by Syntology 2026-02 (from id) DezhengWang/Left/models/Left/LEFT.py 2e1aa8ed829e455e ran no licence file found · pointer only
XLinear: A Lightweight and Accurate MLP-Based Model for Long-Term Time Series Forecasting with Exogenous Inputs added by Syntology 2026-01 (from id) thuml/Time-Series-Library/models/TimeXer.py c72bedae1c2e5af8 ran · metamorphic tier: deterministic MIT (permissive)
Global Regulation and Excitation via Attention Tuning for Stereo Matching added by Syntology 2025-09 (from id) JarvisLee0423/GREAT-Stereo/models/great_stereo/transformers.py 69ddc82d1e9673b9 ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive)
arXiv:2506.05584 2025-06 (from id) microsoft/ticl/ticl/models/tabflex.py 07470eaabe305993 ran Apache-2.0 (permissive)
General Time-series Model for Universal Knowledge Representation of Multivariate Time-Series data 5 Feb 2025 MMTS4All/GTM/models/GTM.py eff770b42c87befc ran MIT (permissive)
FreEformer: Frequency Enhanced Transformer for Multivariate Time Series Forecasting 23 Jan 2025 jackyue1994/FreEformer/model/FrePatchTST3_fre_all.py 9bc6c1a9a4e99258 ran · metamorphic tier: deterministic no licence file found · pointer only
Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera 5 Jan 2025 yuliangguo/depth_any_camera/dac/models/idisc.py 1470abcb2036f263 ran · metamorphic tier: invariant MIT (permissive)
Peri-midFormer: Periodic Pyramid Transformer for Time Series Analysis 7 Nov 2024 WuQiangXDU/Peri-midFormer/model/PerimidFormer.py 4ea975de7e597438 ran · metamorphic tier: deterministic no licence file found · pointer only
Taming the Long Tail in Human Mobility Prediction 19 Oct 2024 yukayo/lotnext/network.py 39ffd4de890cc527 ran · metamorphic tier: deterministic MIT (permissive)
Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent Parametric Partial Differential Equations 6 Jun 2024 jhagnberger/vcnef/vcnef/vcnef_1d.py de193a78579a115b ran MIT (permissive)
End-to-End Real-World Polyphonic Piano Audio-to-Score Transcription with Hierarchical Decoding 22 May 2024 wei-zeng98/piano-a2s/models.py b95d28c25ac2a8e8 unverified Apache-2.0 (permissive)
Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes 6 Apr 2024 zhiyuanYU134/MIRETR/release/robi/modules.py 04845c3650c03509 ran no licence file found · pointer only
OpenSLU: A Unified, Modularized, and Extensible Toolkit for Spoken Language Understanding 17 May 2023 LightChen233/OpenSLU/model/decoder/misca_decoder_1.py 20f9e4ff9f91acdd ran · metamorphic tier: deterministic MIT (permissive)
iDisc: Internal Discretization for Monocular Depth Estimation 13 Apr 2023 SysCV/idisc/idisc/models/id_module.py c2e0047d60b9f291 ran licence not identified · pointer only
First De-Trend then Attend: Rethinking Attention for Time-Series Forecasting 15 Dec 2022 BeBeYourLove/TDformer/model/TDformer.py 626ecbcf3c8c36f8 unverified no licence file found · pointer only
Memorizing Transformers 16 Mar 2022 AIResearchHub/transformergallery/transformer/memorizingtransformer.py 7fd92c090cad8a75 unverified MIT (permissive)
Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations 5 Feb 2022 AdrienC21/CCSD/ccsd/src/models/ScoreNetwork_A.py e3d26a1b52a8e0cd unverified MIT (permissive)
Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations 5 Feb 2022 harryjo97/gdss/models/ScoreNetwork_A.py 4459f5d4f76fdabb unverified no licence file found · pointer only
ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind 15 Oct 2021 unrealtracking/tom2c/model.py d8b62aa6d70f99c7 ran · metamorphic tier: deterministic no licence file found · pointer only
SimCSE: Simple Contrastive Learning of Sentence Embeddings 18 Apr 2021 nlpods/layerattpooler/cl/models.py b949b4980657d9b2 ran no licence file found · pointer only
Robust Point Cloud Registration Framework Based on Deep Graph Matching 7 Mar 2021 zhileichen99/utopic/models/architecture.py f8e8754f133cc766 ran no licence file found · pointer only
Multi-Time Attention Networks for Irregularly Sampled Time Series 25 Jan 2021 WenjieDu/PyPOTS/pypots/nn/modules/imputeformer/attention.py 9438feeabbc94e15 ran · metamorphic tier: invariant BSD-3-Clause (permissive)
Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting 14 Dec 2020 martinwhl/Informer-PyTorch-Lightning/models/informer/model.py e75ce51f514cede4 ran · metamorphic tier: deterministic Apache-2.0 (permissive)
Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting 14 Dec 2020 larsbentsen/fftransformer/models/Informer.py b3037a636b1488b2 ran · metamorphic tier: deterministic no licence file found · pointer only
Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting 14 Dec 2020 AndrzejMiskow/TradeAI/prediction_service/transformers/models.py 959c303f905ec82e ran · metamorphic tier: deterministic MIT (permissive)
Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting 14 Dec 2020 tianhai123/Informer-Tensorflow/models/model.py 2fb65948fb331ab5 ran Apache-2.0 (permissive)
Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting 14 Dec 2020 zhouhaoyi/Informer2020/models/model.py c2ca1cd029bc98bf unverified Apache-2.0 (permissive)
Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks 25 Oct 2020 XuJing1022/HiT-MAC/model.py 2b67cf6350ef19ae ran no licence file found · pointer only
Multi-hop Question Generation with Graph Convolutional Network 19 Oct 2020 HLTCHKUST/MulQG/GPG/encoders/graphfusion_encoder.py 50bbca6431037b3b ran · metamorphic tier: deterministic MIT (permissive)
A Label Attention Model for ICD Coding from Clinical Text 13 Jul 2020 aehrc/LAAT/src/models/attentions/attention_layer.py 4c5d457bd97c1765 ran · metamorphic tier: deterministic licence not identified · pointer only

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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 cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

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