Home › Code › MultiheadAttention

MultiheadAttention

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

MultiheadAttention appears in the code Syntology harvested for 44 papers, as 48 distinct code bodies found in 48 places (a place is one code body under one paper). At least one of them ran in 28 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 MultiheadAttention 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 48 distinct code bodies named MultiheadAttention; 19 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
19unverified
2fingerprinted

Licence is a property of each copy, so it is counted per place: 19 of the 48 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

44 papers shown of 44, newest first; 48 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 7 papers added by Syntology. 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
Learning task-specific subspaces via interventional post-training of speech foundation models added by Syntology 2026-06 (from id) s3prl/s3prl/s3prl/upstream/distiller/model.py 8ae62a892bc13c8d unverified Apache-2.0 (permissive)
In-Context Multiple Instance Learning added by Syntology 2026-06 (from id) injurise/ICMIL/icmil/models/architecture.py 6882e88420185b2a ran · metamorphic tier: deterministic fingerprinted MIT (permissive)
OmniTabBench: Mapping the Empirical Frontiers of GBDTs, Neural Networks, and Foundation Models for Tabular Data at Scale added by Syntology 2026-04 (from id) yandex-research/rtdl-revisiting-models/package/rtdl_revisiting_models.py 3a561d57f211e806 ran Apache-2.0 (permissive)
TACTIC for Navigating the Unknown: Tabular Anomaly deteCTion via In-Context inference added by Syntology 2026-03 (from id) gmum/TACTIC/tactic/model/tactic.py b3eb71915b80481c ran no licence file found · pointer only
ZeroSyl: Simple Zero-Resource Syllable Tokenization for Spoken Language Modeling added by Syntology 2026-02 (from id) nicolvisser/ZeroSyl/zerosyl/zerosyl.py 11bbf68104c4afcd ran MIT (permissive)
SEMPO: Lightweight Foundation Models for Time Series Forecasting added by Syntology 2025-10 (from id) mala-lab/SEMPO/models/SEMPO.py 716e24f597b6f1ff ran Apache-2.0 (permissive)
Embedding-Based Context-Aware Reranker added by Syntology 2025-10 (from id) BorealisAI/EBCAR/src/model/ebcar_dedicated_attention_model.py 621850593b6a52e8 ran licence not identified · pointer only
Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation 26 Mar 2025 zwyang6/ExCEL/model/model_excel.py 9fec802d480b8213 unverified no licence file found · pointer only
Multimodal Prompt Learning with Missing Modalities for Sentiment Analysis and Emotion Recognition 7 Jul 2024 zrguo/MPLMM/src/model.py 71680f2ec58be898 unverified MIT (permissive)
SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding 3 Jul 2024 WeitaiKang/SegVG/models/SegVG.py d232f407f48ea631 ran · metamorphic tier: deterministic no licence file found · pointer only
Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding 29 Feb 2024 guangyliu/eddpm/Protein/codes/nn/models.py ebbb4cab1eb5afaf ran no licence file found · pointer only
Cross-Modal Translation and Alignment for Survival Analysis 22 Sep 2023 ft-zhou-zzz/cmta/models/cmta/network.py 239d8370d131c65d unverified no licence file found · pointer only
U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Clouds 11 Aug 2023 zhangcyg/u-red/network/deformation_net.py c9afeb7769ae9b17 ran no licence file found · pointer only
Multimodal Optimal Transport-based Co-Attention Transformer with Global Structure Consistency for Survival Prediction 14 Jun 2023 JJ-ZHOU-Code/RobustMultiModel/models/model_coattn.py b3b023b4c6805594 unverified no licence file found · pointer only
ImageBind: One Embedding Space To Bind Them All 9 May 2023 facebookresearch/imagebind/imagebind/models/imagebind_model.py e571e943335367a5 ran licence not identified · pointer only
EvoluNet: Advancing Dynamic Non-IID Transfer Learning on Graphs 1 May 2023 wanghh7/evolunet/model/model.py 0838369745d53cad ran no licence file found · pointer only
Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks 4 Apr 2023 wengsyx/neural-comprehension/NeuralCom/CoNN/modeling_conn.py 3e1a3d7b3bf9ed48 unverified MIT (permissive)
Decoupled Multimodal Distilling for Emotion Recognition 24 Mar 2023 mdswyz/DMD/trains/singleTask/model/dmd.py 89990d89c23c5bfa unverified MIT (permissive)
SmartBERT: A Promotion of Dynamic Early Exiting Mechanism for Accelerating BERT Inference 16 Mar 2023 HuBoren99/SmartBert/models/SmartBert.py a55fea32788cd568 ran · metamorphic tier: deterministic MIT (permissive)
Learning Physical Models that Can Respect Conservation Laws 21 Feb 2023 amazon-science/probconserv/deep_pdes/attentive_neural_process/probconserv.py fc456591ed6ce764 ran Apache-2.0 (permissive)
AQuaMaM: An Autoregressive, Quaternion Manifold Model for Rapidly Estimating Complex SO(3) Distributions 21 Jan 2023 airalcorn2/aquamam/aquamam.py 2a40c453f8215cf1 unverified MIT (permissive)
Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs 15 Nov 2022 NicolasAG/SGinPG/src/model.py 0b4cce6121085c3c unverified BSD-2-Clause (permissive)
EleGANt: Exquisite and Locally Editable GAN for Makeup Transfer 20 Jul 2022 Chenyu-Yang-2000/EleGANt/models/elegant.py 153bf0a3c6aaf0ac ran · metamorphic tier: deterministic licence not identified · pointer only
Linear Complexity Randomized Self-attention Mechanism 10 Apr 2022 hkunlp/efficient-attention/efficient-attention/efficient_attention/lara.py bd857b15ac85b005 ran Apache-2.0 (permissive)
KinyaBERT: a Morphology-aware Kinyarwanda Language Model 16 Mar 2022 anzeyimana/kinyabert-acl2022/code/morpho_model.py 4639b692ef625093 unverified MIT (permissive)
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models 20 Dec 2021 openai/glide-text2im/glide_text2im/text2im_model.py 001daee6f2379723 ran · metamorphic tier: deterministic MIT (permissive)
Conditional Object-Centric Learning from Video 24 Nov 2021 Genera1Z/SAVi-PyTorch/model.py a50cd588d4e75a0a ran no licence file found · pointer only
HRFormer: High-Resolution Transformer for Dense Prediction 18 Oct 2021 HRNet/HRFormer/cls/models/hrt.py 7f956321be67f123 ran · metamorphic tier: deterministic MIT (permissive)
More Identifiable yet Equally Performant Transformers for Text Classification 2 Jun 2021 declare-lab/identifiable-transformers/model_identifiable.py 65062d0b9d191cb5 ran · metamorphic tier: deterministic Apache-2.0 (permissive)
Learning Relation Alignment for Calibrated Cross-modal Retrieval 28 May 2021 lancopku/IAIS/model/attention.py 7a6b1633c8b59698 unverified MIT (permissive)
Neural Machine Translation with Monolingual Translation Memory 24 May 2021 jcyk/copyisallyouneed/generator.py 869a715ba18c9742 unverified no licence file found · pointer only
SimCSE: Simple Contrastive Learning of Sentence Embeddings 18 Apr 2021 jeongukjae/KR-BERT-SimCSE/model.py 0903880703193f2a ran MIT (permissive)
Group-Free 3D Object Detection via Transformers 1 Apr 2021 KookHoiKim/GroupFree3dBaseline/models/detector.py 6bd1a32eae6a6a53 unverified MIT (permissive)
Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking 22 Mar 2021 594422814/TransformerTrack/ltr/models/target_classifier/transformer.py 1b733e1fccc5d345 ran · metamorphic tier: deterministic MIT (permissive)
Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition 11 Mar 2021 topdu/openocr/openrec/modeling/decoders/abinet_decoder.py 5dd87791ac034fb5 ran · metamorphic tier: deterministic Apache-2.0 (permissive)
Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition 11 Mar 2021 FangShancheng/ABINet/modules/model_abinet.py 7c0b340a62978887 unverified licence not identified · pointer only
IOT: Instance-wise Layer Reordering for Transformer Structures 5 Mar 2021 instance-wise-ordered-transformer/IOT/fairseq/modules/transformer_sentence_encoder_layer.py b4aacbb45af4df12 unverified licence not identified · pointer only
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 22 Oct 2020 nateraw/lightning-vision-transformer/vit.py 28d07cea36220258 ran · metamorphic tier: deterministic MIT (permissive)
Query-Key Normalization for Transformers 8 Oct 2020 CyndxAI/QKNorm/QKNorm/layers.py ca45e6f04d39e00c ran Apache-2.0 (permissive)
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech 8 Jun 2020 keonlee9420/Comprehensive-Transformer-TTS/model/transformers/transformer_fs2.py 91289eb6932cf19a ran · metamorphic tier: deterministic MIT (permissive)
AMR Parsing via Graph-Sequence Iterative Inference 12 Apr 2020 bjascob/amrlib/amrlib/models/parse_gsii/modules/parser.py 4b0bd99292baeaff unverified MIT (permissive)
Multimodal Transformer for Unaligned Multimodal Language Sequences 1 Jun 2019 kenford953/graphcage/src/CrossmodalTransformer.py 34e57a8ff4c50a35 unverified no licence file found · pointer only
Multimodal Transformer for Unaligned Multimodal Language Sequences 1 Jun 2019 yaohungt/Multimodal-Transformer/src/models.py a1bae24ff466241b unverified MIT (permissive)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 11 Oct 2018 huanghonggit/Mask-Language-Model/model/bert.py 0d4d097ae7a7f1de ran Apache-2.0 (permissive)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 11 Oct 2018 devJWSong/bert-crf-entity-recognition-pytorch/src/layers.py af47ebae6c05725a ran fingerprinted MIT (permissive)
Universal Transformers 10 Jul 2018 cfiken/universal_transformer/model/ut.py 97703c2875660e0b ran no licence file found · pointer only
Attention Is All You Need 12 Jun 2017 knotgrass/attention/attn/attention.py 6c73a396116acbdd ran no licence file found · pointer only
Attention Is All You Need 12 Jun 2017 abhaskumarsinha/Keras-implementation-of-Transformer-Architecture/Transformer.py bc1bf715a553f14a unverified GPL-3.0 (copyleft) · 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