Home › Code › scaled_dot_product_attention

scaled_dot_product_attention

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

scaled_dot_product_attention appears in the code Syntology harvested for 43 papers, as 52 distinct code bodies found in 55 places (a place is one code body under one paper). At least one of them ran in 24 of the papers; 13 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 scaled_dot_product_attention 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 32 of the 52 distinct code bodies named scaled_dot_product_attention; 20 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

4ran · honoured contract
4ran · violated contract
8ran · our draft was wrong
6ran · fixture could not drive it
10ran
20unverified
13fingerprinted

Licence is a property of each copy, so it is counted per place: 21 of the 55 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

43 papers shown of 43, newest first; 55 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
SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation added by Syntology 2026-05 (from id) ModelTC/LightX2V/lightx2v/utils/print_atten_score.py 68fcdfd881d93961 ran Apache-2.0 (permissive)
Give it Space! Explicit Disentangling of Positional and Semantic Representations in Encoders added by Syntology 2026-05 (from id) LequeuISIR/DSTG-encoder/src/neobert/model/model.py 13c8fb0873f97a00 ran no licence file found · pointer only
Hypencoder Revisited: Reproducibility and Analysis of Non-Linear Scoring for First-Stage Retrieval added by Syntology 2026-04 (from id) arneeichholtz/Hypencoder-reprod/hypencoder_cb/modeling/hypencoder.py 6e979b51a5011c36 ran MIT (permissive)
DepCap: Adaptive Block-Wise Parallel Decoding for Efficient Diffusion LM Inference added by Syntology 2026-04 (from id) X-Xia0828/DepCap/llada/model/modeling_llada.py a1e20a66389a45ff unverified no licence file found · pointer only
Representation Alignment for Just Image Transformers is not Easier than You Think added by Syntology 2026-03 (from id) kaist-cvml/PixelREPA/model_pixelREPA.py ddbfee8e56c96b9c ran · our draft was wrong MIT (permissive)
ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment added by Syntology 2026-01 (from id) sheriyuo/ETS/llada/model/modeling_llada.py a1e20a66389a45ff unverified no licence file found · pointer only
Neural Emulator Superiority: When Machine Learning for PDEs Surpasses its Training Data added by Syntology 2025-10 (from id) tum-pbs/emulator-superiority/code/experiments/transformer.py f0a2fdc3bd45affc unverified no licence file found · pointer only
ReCon: Region-Controllable Data Augmentation with Rectification and Alignment for Object Detection added by Syntology 2025-10 (from id) haoweiz23/ReCon/models/attention_processor.py f759aa4f93d14c47 unverified no licence file found · pointer only
XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation 26 Jun 2025 bytedance/xverse/src/flux/block.py 75e0eb0c22ca129e unverified Apache-2.0 (permissive)
Mamba Knockout for Unraveling Factual Information Flow 30 May 2025 nirendy/mamba-knockout/src/experiments/knockout/llama/scaled_dot_product_attention.py bec2160c46dd3280 unverified MIT (permissive)
GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control 5 Mar 2025 nv-tlabs/GEN3C/cosmos_predict1/autoregressive/modules/attention.py abc31b2f673701c7 unverified Apache-2.0 (permissive)
Fractal Generative Models 24 Feb 2025 LTH14/fractalgen/models/ar.py d2525f74659345d8 unverified MIT (permissive)
ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features 6 Feb 2025 helblazer811/ConceptAttention/concept_attention/flux/dit_block.py 1af01c699046b8d4 unverified no licence file found · pointer only
Cosmos World Foundation Model Platform for Physical AI 7 Jan 2025 nvidia-cosmos/cosmos-predict1/cosmos_predict1/autoregressive/modules/attention.py abc31b2f673701c7 unverified Apache-2.0 (permissive)
FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models 30 Dec 2024 thu-nics/framefusion/framefusion/utils.py 2e002934a51f4e51 unverified MIT (permissive)
SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction 17 Oct 2024 sail-sg/simlayerkv/LongBench/SimLayerKV_attention_llama.py 15435bf612fd7f6f ran no licence file found · pointer only
SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction 17 Oct 2024 sail-sg/simlayerkv/LongBench/SimLayerKV_attention_qwen.py 996f634b37f61510 ran no licence file found · pointer only
Large Language Models are Strong Audio-Visual Speech Recognition Learners 18 Sep 2024 umbertocappellazzo/llama-avsr/models/Llama_LoRA.py f52b1ca383922f4e ran no licence file found · pointer only
Multi-Grid Graph Neural Networks with Self-Attention for Computational Mechanics 18 Sep 2024 DonsetPG/graph-physics/jraphphysics/models/layers.py 417486e192f1d2e2 ran no licence file found · pointer only
A Neural Column Generation Approach to the Vehicle Routing Problem with Two-Dimensional Loading and Last-In-First-Out Constraints 18 Jun 2024 xyfffff/NCG-for-2L-CVRP/bpp/model.py e799361645d45d27 ran · our draft was wrong no licence file found · pointer only
Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks 4 Jun 2024 ablghtianyi/ICL_Modular_Arithmetic/interpretability/attn_map.py 4f3bdb6c844ac5cc ran · fixture could not drive it fingerprinted MIT (permissive)
LeMeViT: Efficient Vision Transformer with Learnable Meta Tokens for Remote Sensing Image Interpretation 16 May 2024 ViTAE-Transformer/LeMeViT/models/lemevit.py 1a1001adc58b631f ran · fixture could not drive it fingerprinted no licence file found · pointer only
RepEval: Effective Text Evaluation with LLM Representation 30 Apr 2024 shikib/usr/transformers/modeling_ctrl.py 57ebc1447d921c46 ran Apache-2.0 (permissive)
From Numbers to Words: Multi-Modal Bankruptcy Prediction Using the ECL Dataset 2024-01 (from id) henriarnoug/ECL/sentence-attention/model_utils.py 819a93855d130bbc ran · fixture could not drive it no licence file found · pointer only
An Improved Masking Strategy for Self-supervised Masked Reconstruction in Human Activity Recognition 2023-12 (from id) diheal/channle_masking/multiHeadAttention.py 00c2ece4e478acf2 ran no licence file found · pointer only
How Much Temporal Long-Term Context is Needed for Action Segmentation? 22 Aug 2023 ltcontext/ltcontext/ltc/model/attention_utils.py 286e98f2ad765c4b ran licence not identified · pointer only
WIDER & CLOSER: Mixture of Short-channel Distillers for Zero-shot Cross-lingual Named Entity Recognition 7 Dec 2022 mckysse/msd/transformers/modeling_ctrl.py 57ebc1447d921c46 ran Apache-2.0 (permissive)
A Time Series is Worth 64 Words: Long-term Forecasting with Transformers 27 Nov 2022 romilbert/samformer/samformer_pytorch/samformer/samformer.py 21d036b82013b9f5 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
When Multi-Level Meets Multi-Interest: A Multi-Grained Neural Model for Sequential Recommendation 3 May 2022 whuir/mgnm/code/util_se.py 8fe64623b4d2875f unverified MIT (permissive)
Generating Symbolic Reasoning Problems with Transformer GANs 19 Oct 2021 reactive-systems/TGAN-SR/impl/tgan_sr/transformer/attention.py 6e22d18d71e35c49 unverified MIT (permissive)
Towards Automatic Instrumentation by Learning to Separate Parts in Symbolic Multitrack Music 13 Jul 2021 salu133445/arranger/arranger/transformer/model.py cec70fbe641ff7aa unverified MIT (permissive)
Kernel Identification Through Transformers 15 Jun 2021 frgsimpson/kitt/kitt/networks/transformer/set_transformer_blocks.py 66755ac81353d809 ran · our draft was wrong licence not identified · pointer only
A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning 3 Jun 2021 PwnerHarry/CP/components_CP.py cd1c640990b1df7e ran · fixture could not drive it fingerprinted MIT (permissive)
Escaping the Big Data Paradigm with Compact Transformers 12 Apr 2021 Ryul0rd/compact-convolutional-transformer/compact_conv_transformer.py f35b452496f8552c ran · fixture could not drive it fingerprinted no licence file found · pointer only
Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters 19 Aug 2020 safe-graph/dgfraud-tf2/layers/layers.py 00245cbc1ab1f183 unverified Apache-2.0 (permissive)
Teaching Temporal Logics to Neural Networks 6 Mar 2020 reactive-systems/deepltl/deepltl/layers/attention.py 6ac8c2e8189b5ab7 unverified MIT (permissive)
Teaching Temporal Logics to Neural Networks 6 Mar 2020 necrashter/deepltl-pytorch/deepltl/layers/attention.py 73b90c22738f0032 unverified MIT (permissive)
On Layer Normalization in the Transformer Architecture 12 Feb 2020 colorfulscoop/tfdlg/tfdlg/models.py 3864ff9606edf68a unverified MIT (permissive)
Adversarial NLI: A New Benchmark for Natural Language Understanding 31 Oct 2019 tlatkowski/multihead-siamese-nets/layers/attention.py f912d2bb7968ce7f unverified MIT (permissive)
CTRL: A Conditional Transformer Language Model for Controllable Generation 11 Sep 2019 UKPLab/controlled-argument-generation/transformer.py c37ff914e4e7a62e ran · violated contract fingerprinted BSD-3-Clause (permissive)
CTRL: A Conditional Transformer Language Model for Controllable Generation 11 Sep 2019 salesforce/ctrl/pytorch_transformer.py 6da14d7cf9778239 ran · our draft was wrong fingerprinted BSD-3-Clause (permissive)
Generating Long Sequences with Sparse Transformers 23 Apr 2019 wilson1yan/VideoGPT/videogpt/attention.py 9d35276799c65577 ran · our draft was wrong MIT (permissive)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 11 Oct 2018 rajlm10/Chandler/utils.py aa2d3d2c35ae9b63 ran · violated contract fingerprinted no licence file found · pointer only
Attention Is All You Need 12 Jun 2017 anhtu293/transformer_from_scratch/model/transformer.py c7e7c016c66eb84d ran · honoured contract MIT (permissive)
Attention Is All You Need 12 Jun 2017 antoinecollas/transformer_neural_machine_translation/transformer/transformer.py 6aa80807c7eb13aa ran · violated contract fingerprinted MIT (permissive)
Attention Is All You Need 12 Jun 2017 soumik12345/transformer.pytorch/src/model.py 5796ea2aeed41947 ran · our draft was wrong no licence file found · pointer only
Attention Is All You Need 12 Jun 2017 dhiraa/tener/src/tener/models/vanialla_transformer.py 28a1ce930e92de0c ran · honoured contract fingerprinted Apache-2.0 (permissive)
Attention Is All You Need 12 Jun 2017 abhaskumarsinha/MinimalGPT/GPT.py 5d28f773b90ce3af ran · violated contract fingerprinted MIT (permissive)
Attention Is All You Need 12 Jun 2017 abhaskumarsinha/Keras-implementation-of-Transformer-Architecture/Transformer.py 4e705f4378907830 ran · fixture could not drive it fingerprinted GPL-3.0 (copyleft) · pointer only
Attention Is All You Need 12 Jun 2017 Aveek-Saha/Transformer/model.py 547a0b322775d240 ran · honoured contract Apache-2.0 (permissive)
Attention Is All You Need 12 Jun 2017 Maple728/transformer/models/transformer.py 7fe06ef157b00d63 ran · our draft was wrong fingerprinted MIT (permissive)
Attention Is All You Need 12 Jun 2017 Kyubyong/transformer/model.py 0dcc4910e658accc unverified Apache-2.0 (permissive)
Attention Is All You Need 12 Jun 2017 majing2019/transformer/model.py 57e1b33a663f6ac6 unverified no licence file found · pointer only
Get To The Point: Summarization with Pointer-Generator Networks 14 Apr 2017 steph1793/Pointer_Transformer_Generator/transformer.py 70c86dc3686d36b5 ran · honoured contract MIT (permissive)
arXiv:2021.acl-long.390 thunlp/MetaAdaptRank/contrastqg/transformers/modeling_ctrl.py 27e71cce0a74b944 unverified MIT (permissive)

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