Home › Code › SelfAttention

SelfAttention

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

SelfAttention appears in the code Syntology harvested for 66 papers, as 74 distinct code bodies found in 74 places (a place is one code body under one paper). At least one of them ran in 48 of the papers; 10 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 SelfAttention 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 53 of the 74 distinct code bodies named SelfAttention; 21 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
53ran
21unverified
10fingerprinted

Licence is a property of each copy, so it is counted per place: 30 of the 74 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

66 papers shown of 66, newest first; 74 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 18 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
RecPFN: Prior-Fitted Networks for In-Context-Based Recommendations added by Syntology 2026-08 (from id) SAP-samples/tabular-ai-recpfn/src/architecture/recpfn.py d769cfcf49ce4a01 unverified Apache-2.0 (permissive)
tFUSOperator: Operator Learning for Transcranial Focused Ultrasound Digital Twins added by Syntology 2026-08 (from id) CMME-Lab/tFUSOperator/models/model.py 5045ed55ca7c16d6 ran · metamorphic tier: deterministic MIT (permissive)
PMDformer: Patch-Mean Decoupling Information Transformer for Long-term Forecasting added by Syntology 2026-06 (from id) aohu1105/PMDformer/model/PMDformer.py a8b5200d1575c3a0 ran · metamorphic tier: deterministic no licence file found · pointer only
Root-Selecting Fixed-Point Inversion for Rectified Flows via Trajectory Straightness added by Syntology 2026-06 (from id) seminkim/selfix/src/flux/sampling.py 0b8453ea4488f39a unverified Apache-2.0 (permissive)
CORE-MTL: Rethinking Gradient Balancing via Causal Orthogonal Representations added by Syntology 2026-06 (from id) Hope-Rita/CORE-MTL/models/causal_model.py 2a237155525da629 ran no licence file found · pointer only
GraphDiffMed: Knowledge-Constrained Differential Attention with Pharmacological Graph Priors for Medication Recommendation added by Syntology 2026-05 (from id) saxenakrati09/GraphDiffMed/src/modules/GraphDiffMed.py cbc1e928132dfbcd ran · metamorphic tier: invariant MIT (permissive)
Visual Implicit Autoregressive Modeling added by Syntology 2026-05 (from id) mobiushy/VIAR/models/basic_var.py 50d550228a616be7 ran MIT (permissive)
M3R: Localized Rainfall Nowcasting with Meteorology-Informed MultiModal Attention added by Syntology 2026-04 (from id) Sanjeev97/M3Rain/models/m3.py c23ad2b0cf64d690 ran · metamorphic tier: deterministic no licence file found · pointer only
Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus added by Syntology 2026-04 (from id) PKU-MARL/Multi-Agent-Transformer/mat/algorithms/mat/algorithm/ma_transformer.py 508634b69e88baa8 ran · metamorphic tier: deterministic no licence file found · pointer only
UNIStainNet: Foundation-Model-Guided Virtual Staining of H&E to IHC added by Syntology 2026-03 (from id) facevoid/UNIStainNet/src/models/generator.py bb1077eb6cfa4df4 ran no licence file found · pointer only
INTERLEAVED RECURSIVE STRUCTURE TRANSFORMER FOR OFFLINE MULTI-TASK MULTI-AGENT REINFORCEMENT LEARNING added by Syntology 2026-03 (from id) Jiwonjeon9603/Stairs-Former/src/utils/transformer.py 678d327a0f9e0478 ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive)
Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding added by Syntology 2026-03 (from id) xmed-lab/SemKey/model/semkey_parallel.py 5fb31b7fb7dcea79 ran MIT (permissive)
A Generative Model for Joint Multiple Intent Detection and Slot Filling added by Syntology 2026-02 (from id) LooperXX/AGIF/models/module.py d3edde00bba31ab3 ran · metamorphic tier: deterministic GPL-2.0 (copyleft) · pointer only
DIAMOND: Directed Inference for Artifact Mitigation in Flow Matching Models added by Syntology 2026-02 (from id) ali-vilab/DiffDoctor/src/flux/sampling.py 64127abf54837b48 ran MIT (permissive)
AROMMA: Unifying Olfactory Embeddings for Single Molecules and Mixtures added by Syntology 2026-01 (from id) DGIST-Distributed-AI-Lab/aromma/src/model/framework.py e0161c37de5bf2da unverified no licence file found · pointer only
JetFormer: A Scalable and Efficient Transformer for Jet Tagging from Offline Analysis to FPGA Triggers added by Syntology 2026-01 (from id) walkieq/JetFormer/transformer/src/net.py 6f17c3b47eab149a ran · metamorphic tier: invariant MIT (permissive)
DOREMI: Optimizing Long Tail Predictions in Document-Level Relation Extraction ⋆ added by Syntology 2026-01 (from id) mntlra/DOREMI/src/models/ContextAware.py 52a0529fb694069e ran · metamorphic tier: invariant MIT (permissive)
HiMaCon: Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal Data added by Syntology 2025-10 (from id) zrllrz/HiMaCon/src/hminfocon.py 13cfb4beb66982da ran Apache-2.0 (permissive)
Less-to-More Generalization: Unlocking More Controllability by In-Context Generation 2 Apr 2025 bytedance/UNO/uno/flux/pipeline.py 3d23efb955326633 unverified Apache-2.0 (permissive)
End-to-End Driving with Online Trajectory Evaluation via BEV World Model 2 Apr 2025 liyingyanucas/wote/navsim/agents/WoTE/WoTE_model.py 0d6f5b6295b5a19c ran Apache-2.0 (permissive)
AdaWorld: Learning Adaptable World Models with Latent Actions 24 Mar 2025 little-podi/adaworld/lam/lam/modules/lam.py b1d5f5dfa4ddac49 unverified Apache-2.0 (permissive)
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning 27 Feb 2025 qxzha/ReCon/models/SGRAF.py d4d6173d6e5117e7 ran Apache-2.0 (permissive)
KV-Edit: Training-Free Image Editing for Precise Background Preservation 24 Feb 2025 Xilluill/KV-Edit/models/kv_edit.py 0c92e50f90ae4f64 ran · metamorphic tier: deterministic Apache-2.0 (permissive)
Neuron Platonic Intrinsic Representation From Dynamics Using Contrastive Learning 6 Feb 2025 ww20hust/NeurPIR/src/models/encoder.py f3a7127917231ebd ran no licence file found · pointer only
ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features 6 Feb 2025 helblazer811/ConceptAttention/concept_attention/flux/dit_block.py 44b8130635f7bada unverified no licence file found · pointer only
LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer 3 Feb 2025 showlab/LayerTracer/library/flux_models.py 597cb2e18f1492d8 ran · metamorphic tier: deterministic MIT (permissive)
NeurOp-Diff:Continuous Remote Sensing Image Super-Resolution via Neural Operator Diffusion 15 Jan 2025 zerono000/NeurOp-Diff/models/diffusion.py c8584d0a7fb92793 ran fingerprinted no licence file found · pointer only
Think While You Generate: Discrete Diffusion with Planned Denoising 8 Oct 2024 liusulin/ddpd/text8/model_planner.py ab7bf8223903c9b6 ran fingerprinted MIT (permissive)
Semantically Guided Representation Learning For Action Anticipation 2 Jul 2024 ADiko1997/S-GEAR/models/base_model_ts.py 4d0ab14d77dfb105 ran Apache-2.0 (permissive)
Towards Scalable and Versatile Weight Space Learning 14 Jun 2024 hsg-aiml/sane/src/SANE/models/def_AE.py e81937cece236ca0 ran no licence file found · pointer only
Simplified and Generalized Masked Diffusion for Discrete Data 6 Jun 2024 google-deepmind/md4/md4/models/diffusion/md4.py daf4ef755a1978a3 unverified Apache-2.0 (permissive)
More Room for Language: Investigating the Effect of Retrieval on Language Models 16 Apr 2024 ltgoslo/more-room-for-language/pretraining/model.py 34fd7ee81a1f04a3 unverified GPL-3.0 (copyleft) · pointer only
Weakly-supervised Audio Separation via Bi-modal Semantic Similarity 2 Apr 2024 microsoft/bimodalaudioseparation/models/cond_unet_attn.py fee297065b6d46a5 ran MIT (permissive)
Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers 19 Feb 2024 mrkshllr/bixt/timm/models/bixt.py 82dbf42759abac64 ran · metamorphic tier: deterministic licence not identified · pointer only
NfgTransformer: Equivariant Representation Learning for Normal-form Games 2024-02 (from id) google-deepmind/nfg_transformer/nfg_transformer/network.py 82aeead71a0a530e unverified Apache-2.0 (permissive)
arXiv:2311.04434 2023-11 (from id) spatialdatasciencegroup/HST/utils/bandLayers.py f9d57ee00ebe68a0 unverified no licence file found · pointer only
Forecasting Tropical Cyclones with Cascaded Diffusion Models 2 Oct 2023 nathzi1505/forecast-diffmodels/imagen/modules.py 9e6b6e12b1ec4d34 ran · metamorphic tier: deterministic no licence file found · pointer only
Generalized Few-Shot Point Cloud Segmentation Via Geometric Words 20 Sep 2023 Pixie8888/GFS-3DSeg_GWs/model/capl.py 2c362a2ad0aa0a9f ran · metamorphic tier: deterministic fingerprinted MIT (permissive)
Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction 17 Aug 2023 MediaBrain-SJTU/AuxFormer/model/model.py 39d376502182d85a ran no licence file found · pointer only
LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation 9 Aug 2023 layoutllm-t2i/layoutllm-t2i/GLIGEN/ldm/modules/diffusionmodules/gligen_combine_layout.py 35a9d16404c55eee ran no licence file found · pointer only
HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution 27 Jun 2023 frederikkemarin/bend/bend/models/hyena_dna.py f745e0dbcc9bb059 ran fingerprinted BSD-3-Clause (permissive)
Hidden Biases of End-to-End Driving Models 13 Jun 2023 autonomousvision/carla_garage/team_code/transfuser.py 85cfd6ab309be0b8 ran MIT (permissive)
MA2CL:Masked Attentive Contrastive Learning for Multi-Agent Reinforcement Learning 3 Jun 2023 ustchlsong/ma2cl/algorithms/ma_transformer.py 4a5fcc8f9eab1543 ran MIT (permissive)
Transformers are Sample-Efficient World Models 1 Sep 2022 eloialonso/iris/src/models/world_model.py f16fd90513419812 unverified GPL-3.0 (copyleft) · pointer only
Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors 24 Mar 2022 CasualGANPapers/Make-A-Scene/models/transformer.py 910b60593238b32f ran MIT (permissive)
Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classification 8 Mar 2022 wzh9969/contrastive-htc/model/contrast.py 985ecde4944a60ab unverified MIT (permissive)
Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding 2 Mar 2022 DQiaole/ZITS_inpainting/src/models/TSR_model.py 96c2a9a4d1843cec ran Apache-2.0 (permissive)
A Consistent and Efficient Evaluation Strategy for Attribution Methods 1 Feb 2022 tleemann/road_evaluation/road/road.py b28b45f46cb768f9 unverified MIT (permissive)
Improving language models by retrieving from trillions of tokens 8 Dec 2021 labmlai/annotated_deep_learning_paper_implementations/labml_nn/transformers/retro/model.py 4c4fa4155f57fc48 ran · metamorphic tier: invariant MIT (permissive)
Hamiltonian latent operators for content and motion disentanglement in image sequences 2 Dec 2021 mdasifkhan/halo/model.py 2c97c8872892a8f0 unverified no licence file found · pointer only
IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning 25 Oct 2021 lupantech/iconqa/models/patch_transformer.py b5225e9c0e0545db ran · metamorphic tier: invariant no licence file found · pointer only
GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer 28 Aug 2021 xueyee/GroupFormer/group/models/cluster_transformer.py 76f9cb9ada2064dc unverified Apache-2.0 (permissive)
Perceiver IO: A General Architecture for Structured Inputs & Outputs 30 Jul 2021 esceptico/perceiver-io/src/perceiver_io/perceiver.py 0a3f8489bfe3c981 ran MIT (permissive)
Conditional GANs with Auxiliary Discriminative Classifier 21 Jul 2021 POSTECH-CVLab/PyTorch-StudioGAN/src/models/big_resnet_deep_studiogan.py a2f89876065d8307 ran licence not identified · pointer only
OadTR: Online Action Detection with Transformers 21 Jun 2021 wangxiang1230/OadTR/transformer_models/Transformer.py 9c45f031bb45ad67 ran MIT (permissive)
Multi-Modal Fusion Transformer for End-to-End Autonomous Driving 19 Apr 2021 Kin-Zhang/mmfn/team_code/benchmarks/transfuser/model.py 6141dbd1107c57fd ran · metamorphic tier: deterministic MIT (permissive)
Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification 17 Jan 2021 ArdhenduBehera/cap/SelfAttention.py 6fa32f316d84dd85 unverified MIT (permissive)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 22 Oct 2020 asyml/vision-transformer-pytorch/src/model.py 3dffc591a6481874 ran Apache-2.0 (permissive)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 22 Oct 2020 s-chh/pytorch-scratch-vision-transformer-vit/model.py af6edd8062f762fa ran · metamorphic tier: invariant MIT (permissive)
ALFWorld: Aligning Text and Embodied Environments for Interactive Learning 8 Oct 2020 alfworld/alfworld/alfworld/agents/modules/model.py 4b8de7bded2e4118 unverified MIT (permissive)
Pre-training via Paraphrasing 26 Jun 2020 lucidrains/marge-pytorch/marge_pytorch/marge_pytorch.py 2420acac5ce29a6d ran · metamorphic tier: invariant fingerprinted MIT (permissive)
Denoising Diffusion Probabilistic Models 19 Jun 2020 CW-Huang/sdeflow-light/lib/models/unet.py acc61062a727fa80 unverified MIT (permissive)
Reasoning with Latent Structure Refinement for Document-Level Relation Extraction 13 May 2020 nanguoshun/LSR/code/models/lsr.py 9002f9968c2d49b3 ran · metamorphic tier: invariant no licence file found · pointer only
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 11 Oct 2018 ShivamRajSharma/Transformer-Architectures-From-Scratch/BERT.py 64910f05f8cd9c7d ran · metamorphic tier: invariant fingerprinted MIT (permissive)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 11 Oct 2018 benywon/ChineseBert/model.py 2fac2c94f3edf404 unverified no licence file found · pointer only
Universal Transformers 10 Jul 2018 cfiken/universal_transformer/model/ut.py 72219f63ad9d256a ran fingerprinted no licence file found · pointer only
DARTS: Differentiable Architecture Search 24 Jun 2018 anonNo2/MulTeacher-KD/models/search_cnn.py 54e27a823121bcae ran no licence file found · pointer only
Attention Is All You Need 12 Jun 2017 Wolfie8935/Implementation-of-Attention-is-all-you-need/transformer_from_scratch.py 59f151a9deed2bf4 ran fingerprinted no licence file found · pointer only
Attention Is All You Need 12 Jun 2017 EmilioTyl/transformers_from_scratch/src/models/transformer_modules.py 138f04131e65c57b ran · metamorphic tier: deterministic licence not identified · pointer only
Attention Is All You Need 12 Jun 2017 jelifysh/Transformers/transformers.py 7171816268dfd8f8 ran fingerprinted no licence file found · pointer only
Attention Is All You Need 12 Jun 2017 adi2103/AML-CoVe/NMT/Encoder.py 41081ea63abf65f1 ran Apache-2.0 (permissive)
Attention Is All You Need 12 Jun 2017 Rami97rgb/French-to-English-Translator/model.py 4c8cf0d91eac07eb ran no licence file found · pointer only
Attention Is All You Need 12 Jun 2017 sarthaxxxxx/Attention-is-all-you-need/Transformer.py 4691e9b9cc4ba615 unverified no licence file found · pointer only
Attention Is All You Need 12 Jun 2017 souvikshanku/translit-former/model.py a8d02586f01c1fcd 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