{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/transformerencoderlayer","entry":"TransformerEncoderLayer","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":90,"n_papers_ran":58,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":100,"n_samples_ran":63,"n_samples_fingerprinted":10,"n_places":100,"n_places_pointer_only":38,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":63,"unverified":37},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2608.14211","paper":"/paper/arxiv-2608-14211","title":"Training Fair Tabular Foundation Models","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"patrikken/FairTFM-inference","path":"fairtfm/model.py","file_url":"https://github.com/patrikken/FairTFM-inference/blob/HEAD/fairtfm/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ba660ff73020eb6c","mcp_get_code":{"code_sha256":"ba660ff73020eb6c"}},{"arxiv_id":"2607.13164","paper":"/paper/arxiv-2607-13164","title":"Text2Sign: A Single-GPU Diffusion Baseline for Text-to-Sign Language Video Generation","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"xiaruize0911/text2sign","path":"pipeline.py","file_url":"https://github.com/xiaruize0911/text2sign/blob/HEAD/pipeline.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dc6f452194c57e32","mcp_get_code":{"code_sha256":"dc6f452194c57e32"}},{"arxiv_id":"2606.30258","paper":"/paper/arxiv-2606-30258","title":"KnowsTFM: Knowledge-Informed Fine-Tuning of Small Tabular Foundation Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"automl/TFM-Playground","path":"tfmplayground/interface.py","file_url":"https://github.com/automl/TFM-Playground/blob/HEAD/tfmplayground/interface.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"19718d01dfd3f3c5","mcp_get_code":{"code_sha256":"19718d01dfd3f3c5"}},{"arxiv_id":"2606.06458","paper":"/paper/arxiv-2606-06458","title":"In-Context Multiple Instance Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"injurise/ICMIL","path":"icmil/models/architecture.py","file_url":"https://github.com/injurise/ICMIL/blob/HEAD/icmil/models/architecture.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e0a4bd1effc6c391","mcp_get_code":{"code_sha256":"e0a4bd1effc6c391"}},{"arxiv_id":"2605.15488","paper":"/paper/arxiv-2605-15488","title":"SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"rgklab/SurvivalPFN","path":"survivalpfn/models/icl_model.py","file_url":"https://github.com/rgklab/SurvivalPFN/blob/HEAD/survivalpfn/models/icl_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"79a4260cd65e423b","mcp_get_code":{"code_sha256":"79a4260cd65e423b"}},{"arxiv_id":"2605.15133","paper":"/paper/arxiv-2605-15133","title":"Causal Foundation Models with Continuous Treatments","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"layer6ai-labs/CCPFN-inference","path":"src/ccpfn/models/continuous_icl_model.py","file_url":"https://github.com/layer6ai-labs/CCPFN-inference/blob/HEAD/src/ccpfn/models/continuous_icl_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0b8a82e2f7ecf3f0","mcp_get_code":{"code_sha256":"0b8a82e2f7ecf3f0"}},{"arxiv_id":"2603.29946","paper":"/paper/arxiv-2603-29946","title":"Real-Time Explanations for Tabular Foundation Models","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"kunumi/ShapPFN","path":"src/models/shappfn.py","file_url":"https://github.com/kunumi/ShapPFN/blob/HEAD/src/models/shappfn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c3101b1ec0ec2d3b","mcp_get_code":{"code_sha256":"c3101b1ec0ec2d3b"}},{"arxiv_id":"2602.03018","paper":"/paper/arxiv-2602-03018","title":"From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detection","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"psorus/Outformer","path":"pfns/transformer.py","file_url":"https://github.com/psorus/Outformer/blob/HEAD/pfns/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"73c323342a7ad01a","mcp_get_code":{"code_sha256":"73c323342a7ad01a"}},{"arxiv_id":"2510.06691","paper":"/paper/arxiv-2510-06691","title":"Latent Representation Learning in Heavy-Ion Collisions with MaskPoint Transformer","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"Giovanni-Sforza/MaskPoint-AMPT","path":"models/MaskPoint.py","file_url":"https://github.com/Giovanni-Sforza/MaskPoint-AMPT/blob/HEAD/models/MaskPoint.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"9d0fd8709fbd6207","mcp_get_code":{"code_sha256":"9d0fd8709fbd6207"}},{"arxiv_id":"2506.06039","paper":null,"title":"arXiv:2506.06039","date":null,"month_inferred_from_arxiv_id":"2025-06","title_source":null,"repo":"jr2021/Do-PFN","path":"model/transformer.py","file_url":"https://github.com/jr2021/Do-PFN/blob/HEAD/model/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1dabe5224805f198","mcp_get_code":{"code_sha256":"1dabe5224805f198"}},{"arxiv_id":"2505.19525","paper":"/paper/rethinking-gating-mechanism-in-sparse-moe","title":"Rethinking Gating Mechanism in Sparse MoE: Handling Arbitrary Modality Inputs with Confidence-Guided Gate","date":"2025-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"icuraslw/official-repository-of-confsmoe","path":"models.py","file_url":"https://github.com/icuraslw/official-repository-of-confsmoe/blob/HEAD/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3c8b32bf9f9c0e48","mcp_get_code":{"code_sha256":"3c8b32bf9f9c0e48"}},{"arxiv_id":"2505.10704","paper":"/paper/2505-10704","title":"ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data","date":"2025-05-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gmum/zeus","path":"zeus/model/zeus.py","file_url":"https://github.com/gmum/zeus/blob/HEAD/zeus/model/zeus.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"df4358779e4de127","mcp_get_code":{"code_sha256":"df4358779e4de127"}},{"arxiv_id":"2503.09402","paper":"/paper/vlog-video-language-models-by-generative","title":"VLog: Video-Language Models by Generative Retrieval of Narration Vocabulary","date":"2025-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"showlab/VLog","path":"VLog/model/models.py","file_url":"https://github.com/showlab/VLog/blob/HEAD/VLog/model/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f33ffe92f2473798","mcp_get_code":{"code_sha256":"f33ffe92f2473798"}},{"arxiv_id":"2502.08958","paper":"/paper/biologically-plausible-brain-graph","title":"Biologically Plausible Brain Graph Transformer","date":"2025-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pcyyyy/BioBGT","path":"Model/models.py","file_url":"https://github.com/pcyyyy/BioBGT/blob/HEAD/Model/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2e5155ad75dd2c22","mcp_get_code":{"code_sha256":"2e5155ad75dd2c22"}},{"arxiv_id":"2412.07236","paper":"/paper/cbramod-a-criss-cross-brain-foundation-model","title":"CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding","date":"2024-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wjq-learning/cbramod","path":"models/cbramod.py","file_url":"https://github.com/wjq-learning/cbramod/blob/HEAD/models/cbramod.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2eb20bea3af6aa67","mcp_get_code":{"code_sha256":"2eb20bea3af6aa67"}},{"arxiv_id":"2411.01409","paper":"/paper/classifier-guided-gradient-modulation-for","title":"Classifier-guided Gradient Modulation for Enhanced Multimodal Learning","date":"2024-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zrguo/cggm","path":"src/foodtrain.py","file_url":"https://github.com/zrguo/cggm/blob/HEAD/src/foodtrain.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3dfcc20147c77637","mcp_get_code":{"code_sha256":"3dfcc20147c77637"}},{"arxiv_id":"2410.08245","paper":"/paper/flex-moe-modeling-arbitrary-modality","title":"Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts","date":"2024-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"unites-lab/flex-moe","path":"models.py","file_url":"https://github.com/unites-lab/flex-moe/blob/HEAD/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"40e694fe9ff5b31a","mcp_get_code":{"code_sha256":"40e694fe9ff5b31a"}},{"arxiv_id":"2410.08021","paper":"/paper/oneref-unified-one-tower-expression-grounding","title":"OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling","date":"2024-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"linhuixiao/hivg","path":"models/HiVG.py","file_url":"https://github.com/linhuixiao/hivg/blob/HEAD/models/HiVG.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f003917559e3b08b","mcp_get_code":{"code_sha256":"f003917559e3b08b"}},{"arxiv_id":"2410.05016","paper":"/paper/t-jepa-augmentation-free-self-supervised","title":"T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Data","date":"2024-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jose-melo/t-jepa","path":"src/encoder.py","file_url":"https://github.com/jose-melo/t-jepa/blob/HEAD/src/encoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9a5b310fb0c45b61","mcp_get_code":{"code_sha256":"9a5b310fb0c45b61"}},{"arxiv_id":"2407.05374","paper":"/paper/multimodal-prompt-learning-with-missing","title":"Multimodal Prompt Learning with Missing Modalities for Sentiment Analysis and Emotion Recognition","date":"2024-07-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zrguo/MPLMM","path":"src/model.py","file_url":"https://github.com/zrguo/MPLMM/blob/HEAD/src/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"29e314f7b8ab4b4c","mcp_get_code":{"code_sha256":"29e314f7b8ab4b4c"}},{"arxiv_id":"2407.04619","paper":"/paper/countgd-multi-modal-open-world-counting","title":"CountGD: Multi-Modal Open-World Counting","date":"2024-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"niki-amini-naieni/CountGD","path":"models/GroundingDINO/groundingdino.py","file_url":"https://github.com/niki-amini-naieni/CountGD/blob/HEAD/models/GroundingDINO/groundingdino.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57469407352666b4","mcp_get_code":{"code_sha256":"57469407352666b4"}},{"arxiv_id":"2407.03200","paper":"/paper/segvg-transferring-object-bounding-box-to","title":"SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding","date":"2024-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WeitaiKang/SegVG","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"11325595a1e21029","mcp_get_code":{"code_sha256":"11325595a1e21029"}},{"arxiv_id":"2406.12454","paper":"/paper/a-neural-column-generation-approach-to-the","title":"A Neural Column Generation Approach to the Vehicle Routing Problem with Two-Dimensional Loading and Last-In-First-Out Constraints","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xyfffff/NCG-for-2L-CVRP","path":"bpp/model.py","file_url":"https://github.com/xyfffff/NCG-for-2L-CVRP/blob/HEAD/bpp/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9eae5bacb6b4d773","mcp_get_code":{"code_sha256":"9eae5bacb6b4d773"}},{"arxiv_id":"2406.08173","paper":"/paper/semi-supervised-spoken-language","title":"Semi-Supervised Spoken Language Glossification","date":"2024-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yaohj11/S3LG","path":"model/seq2seq/encoder.py","file_url":"https://github.com/yaohj11/S3LG/blob/HEAD/model/seq2seq/encoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"63d68ab12286b7a4","mcp_get_code":{"code_sha256":"63d68ab12286b7a4"}},{"arxiv_id":"2406.03919","paper":"/paper/vectorized-conditional-neural-fields-a","title":"Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent Parametric Partial Differential Equations","date":"2024-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jhagnberger/vcnef","path":"vcnef/vcnef_1d.py","file_url":"https://github.com/jhagnberger/vcnef/blob/HEAD/vcnef/vcnef_1d.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"87230930da2c54a6","mcp_get_code":{"code_sha256":"87230930da2c54a6"}},{"arxiv_id":"2406.03044","paper":"/paper/population-transformer-learning-population","title":"Population Transformer: Learning Population-level Representations of Neural Activity","date":"2024-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"czlwang/populationtransformer","path":"models/pt_model_custom.py","file_url":"https://github.com/czlwang/populationtransformer/blob/HEAD/models/pt_model_custom.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0245cc2a22d47844","mcp_get_code":{"code_sha256":"0245cc2a22d47844"}},{"arxiv_id":"2404.16622","paper":"/paper/dave-a-detect-and-verify-paradigm-for-low","title":"DAVE -- A Detect-and-Verify Paradigm for Low-Shot Counting","date":"2024-04-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jerpelhan/dave","path":"models/dave.py","file_url":"https://github.com/jerpelhan/dave/blob/HEAD/models/dave.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"07e1f3797315c793","mcp_get_code":{"code_sha256":"07e1f3797315c793"}},{"arxiv_id":"2404.13999","paper":"/paper/cofinal-enhancing-action-quality-assessment","title":"CoFInAl: Enhancing Action Quality Assessment with Coarse-to-Fine Instruction Alignment","date":"2024-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhouKanglei/CoFInAl_AQA","path":"models/model.py","file_url":"https://github.com/ZhouKanglei/CoFInAl_AQA/blob/HEAD/models/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a78727691a69cd7f","mcp_get_code":{"code_sha256":"a78727691a69cd7f"}},{"arxiv_id":"2404.10241","paper":"/paper/vision-and-language-navigation-via-causal","title":"Vision-and-Language Navigation via Causal Learning","date":"2024-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CrystalSixone/VLN-GOAT","path":"map_nav_src/models/vilmodel_GOAT.py","file_url":"https://github.com/CrystalSixone/VLN-GOAT/blob/HEAD/map_nav_src/models/vilmodel_GOAT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"810d160bafcc6c89","mcp_get_code":{"code_sha256":"810d160bafcc6c89"}},{"arxiv_id":"2403.09805","paper":"/paper/on-the-utility-of-3d-hand-poses-for-action","title":"On the Utility of 3D Hand Poses for Action Recognition","date":"2024-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"s-shamil/HandFormer","path":"HandFormer/models/hf_pose.py","file_url":"https://github.com/s-shamil/HandFormer/blob/HEAD/HandFormer/models/hf_pose.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f8f7be5c3f791c68","mcp_get_code":{"code_sha256":"f8f7be5c3f791c68"}},{"arxiv_id":"2402.15591","paper":"/paper/recwizard-a-toolkit-for-conversational","title":"RecWizard: A Toolkit for Conversational Recommendation with Modular, Portable Models and Interactive User Interface","date":"2024-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"McAuley-Lab/RecWizard","path":"src/recwizard/modules/kbrd/transformer_encoder_decoder.py","file_url":"https://github.com/McAuley-Lab/RecWizard/blob/HEAD/src/recwizard/modules/kbrd/transformer_encoder_decoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"12632be7c4bebde1","mcp_get_code":{"code_sha256":"12632be7c4bebde1"}},{"arxiv_id":"2402.11137","paper":"/paper/tunetables-context-optimization-for-scalable","title":"TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks","date":"2024-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"penfever/tunetables","path":"tunetables/transformer.py","file_url":"https://github.com/penfever/tunetables/blob/HEAD/tunetables/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3ca52e651c5bddce","mcp_get_code":{"code_sha256":"3ca52e651c5bddce"}},{"arxiv_id":"2310.19089","paper":"/paper/pushdown-layers-encoding-recursive-structure","title":"Pushdown Layers: Encoding Recursive Structure in Transformer Language Models","date":"2023-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MurtyShikhar/Pushdown-Layers","path":"models/pushdown_transformer_lm.py","file_url":"https://github.com/MurtyShikhar/Pushdown-Layers/blob/HEAD/models/pushdown_transformer_lm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cd05f27177c97848","mcp_get_code":{"code_sha256":"cd05f27177c97848"}},{"arxiv_id":"2310.16898","paper":"/paper/mcuformer-deploying-vision-tranformers-on-1","title":"MCUFormer: Deploying Vision Transformers on Microcontrollers with Limited Memory","date":"2023-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liangyn22/mcuformer","path":"model/supernet_transformer.py","file_url":"https://github.com/liangyn22/mcuformer/blob/HEAD/model/supernet_transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a115d422c7fbcbe2","mcp_get_code":{"code_sha256":"a115d422c7fbcbe2"}},{"arxiv_id":"2310.07096","paper":"/paper/sparse-universal-transformer","title":"Sparse Universal Transformer","date":"2023-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"willGuimont/transformers","path":"nnet/transformers.py","file_url":"https://github.com/willGuimont/transformers/blob/HEAD/nnet/transformers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8b47279d7dccc00f","mcp_get_code":{"code_sha256":"8b47279d7dccc00f"}},{"arxiv_id":"2308.10310","paper":"/paper/dvgaze-dual-view-gaze-estimation","title":"DVGaze: Dual-View Gaze Estimation","date":"2023-08-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yihuacheng/DVGaze","path":"Code/eth/transformer.py","file_url":"https://github.com/yihuacheng/DVGaze/blob/HEAD/Code/eth/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f632b3589956e8e9","mcp_get_code":{"code_sha256":"f632b3589956e8e9"}},{"arxiv_id":"2308.09351","paper":"/paper/rlipv2-fast-scaling-of-relational-language","title":"RLIPv2: Fast Scaling of Relational Language-Image Pre-training","date":"2023-08-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jacobyuan7/rlip","path":"models/ParSetransformer.py","file_url":"https://github.com/jacobyuan7/rlip/blob/HEAD/models/ParSetransformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"107ffdb07dbd2f9d","mcp_get_code":{"code_sha256":"107ffdb07dbd2f9d"}},{"arxiv_id":"2308.04352","paper":"/paper/3d-vista-pre-trained-transformer-for-3d","title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","date":"2023-08-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"3d-vista/3D-VisTA","path":"model/vision/unified_encoder.py","file_url":"https://github.com/3d-vista/3D-VisTA/blob/HEAD/model/vision/unified_encoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8f3dbe47a6eb7b40","mcp_get_code":{"code_sha256":"8f3dbe47a6eb7b40"}},{"arxiv_id":"2307.10543","paper":"/paper/trea-tree-structure-reasoning-schema-for","title":"TREA: Tree-Structure Reasoning Schema for Conversational Recommendation","date":"2023-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WindyLee0822/TREA","path":"model.py","file_url":"https://github.com/WindyLee0822/TREA/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b4cc671d07639f90","mcp_get_code":{"code_sha256":"b4cc671d07639f90"}},{"arxiv_id":"2305.19271","paper":"/paper/concise-answers-to-complex-questions","title":"Concise Answers to Complex Questions: Summarization of Long-form Answers","date":"2023-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"acpotluri/lfqa_summary","path":"model/PreSumm/src/models/encoder.py","file_url":"https://github.com/acpotluri/lfqa_summary/blob/HEAD/model/PreSumm/src/models/encoder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"270439c03d883b4c","mcp_get_code":{"code_sha256":"270439c03d883b4c"}},{"arxiv_id":"2305.17535","paper":"/paper/pfns-are-flexible-models-for-real-world","title":"PFNs4BO: In-Context Learning for Bayesian Optimization","date":"2023-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"automl/pfns4bo","path":"pfns4bo/transformer.py","file_url":"https://github.com/automl/pfns4bo/blob/HEAD/pfns4bo/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a5e5843ed74ae0a8","mcp_get_code":{"code_sha256":"a5e5843ed74ae0a8"}},{"arxiv_id":"2305.03602","paper":"/paper/a-dual-semantic-aware-recurrent-global","title":"A Dual Semantic-Aware Recurrent Global-Adaptive Network For Vision-and-Language Navigation","date":"2023-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CrystalSixone/DSRG","path":"finetune_src/models/vilmodel.py","file_url":"https://github.com/CrystalSixone/DSRG/blob/HEAD/finetune_src/models/vilmodel.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fac115820b1e6391","mcp_get_code":{"code_sha256":"fac115820b1e6391"}},{"arxiv_id":"2304.14636","paper":"/paper/prenas-preferred-one-shot-learning-towards","title":"PreNAS: Preferred One-Shot Learning Towards Efficient Neural Architecture Search","date":null,"month_inferred_from_arxiv_id":"2023-04","title_source":"archive","repo":"tinyvision/prenas","path":"model/supernet_transformer.py","file_url":"https://github.com/tinyvision/prenas/blob/HEAD/model/supernet_transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a17eb310e7b4dff6","mcp_get_code":{"code_sha256":"a17eb310e7b4dff6"}},{"arxiv_id":"2304.04997","paper":"/paper/relational-context-learning-for-human-object","title":"Relational Context Learning for Human-Object Interaction Detection","date":"2023-04-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OreoChocolate/MUREN","path":"models/muren.py","file_url":"https://github.com/OreoChocolate/MUREN/blob/HEAD/models/muren.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7f8a75d5cc8739af","mcp_get_code":{"code_sha256":"7f8a75d5cc8739af"}},{"arxiv_id":"2304.03307","paper":"/paper/vita-clip-video-and-text-adaptive-clip-via","title":"Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting","date":"2023-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TalalWasim/Vita-CLIP","path":"training/VitaCLIP_model.py","file_url":"https://github.com/TalalWasim/Vita-CLIP/blob/HEAD/training/VitaCLIP_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"efd12a8a6dd436d0","mcp_get_code":{"code_sha256":"efd12a8a6dd436d0"}},{"arxiv_id":"2304.01665","paper":"/paper/neural-comprehension-language-models-with","title":"Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks","date":"2023-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wengsyx/neural-comprehension","path":"NeuralCom/CoNN/modeling_conn.py","file_url":"https://github.com/wengsyx/neural-comprehension/blob/HEAD/NeuralCom/CoNN/modeling_conn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"17a235d61eb3ac7a","mcp_get_code":{"code_sha256":"17a235d61eb3ac7a"}},{"arxiv_id":"2303.13802","paper":"/paper/decoupled-multimodal-distilling-for-emotion","title":"Decoupled Multimodal Distilling for Emotion Recognition","date":"2023-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mdswyz/DMD","path":"trains/singleTask/model/dmd.py","file_url":"https://github.com/mdswyz/DMD/blob/HEAD/trains/singleTask/model/dmd.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7b9d2681c13f15dc","mcp_get_code":{"code_sha256":"7b9d2681c13f15dc"}},{"arxiv_id":"2303.05725","paper":"/paper/cvt-slr-contrastive-visual-textual","title":"CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition with Variational Alignment","date":"2023-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"binbinjiang/CVT-SLR","path":"cvtslr_model.py","file_url":"https://github.com/binbinjiang/CVT-SLR/blob/HEAD/cvtslr_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f3ab8e695d75d895","mcp_get_code":{"code_sha256":"f3ab8e695d75d895"}},{"arxiv_id":"2301.08838","paper":"/paper/aquamam-an-autoregressive-quaternion-manifold","title":"AQuaMaM: An Autoregressive, Quaternion Manifold Model for Rapidly Estimating Complex SO(3) Distributions","date":"2023-01-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"airalcorn2/aquamam","path":"aquamam.py","file_url":"https://github.com/airalcorn2/aquamam/blob/HEAD/aquamam.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a26e8bdd622e3a7","mcp_get_code":{"code_sha256":"8a26e8bdd622e3a7"}},{"arxiv_id":"2212.11972","paper":"/paper/scalable-adaptive-computation-for-iterative","title":"Scalable Adaptive Computation for Iterative Generation","date":"2022-12-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/pix2seq","path":"architectures/transformers.py","file_url":"https://github.com/google-research/pix2seq/blob/HEAD/architectures/transformers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e730a175de3303f8","mcp_get_code":{"code_sha256":"e730a175de3303f8"}},{"arxiv_id":"2212.09877","paper":"/paper/layoutdetr-detection-transformer-is-a-good","title":"LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer","date":"2022-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/layoutdetr","path":"training/detr_transformer.py","file_url":"https://github.com/salesforce/layoutdetr/blob/HEAD/training/detr_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b2bdd3331ef62a51","mcp_get_code":{"code_sha256":"b2bdd3331ef62a51"}},{"arxiv_id":"2209.13508","paper":"/paper/motion-transformer-with-global-intention","title":"Motion Transformer with Global Intention Localization and Local Movement Refinement","date":"2022-09-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sshaoshuai/mtr","path":"mtr/models/model.py","file_url":"https://github.com/sshaoshuai/mtr/blob/HEAD/mtr/models/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7e91726a274c25bd","mcp_get_code":{"code_sha256":"7e91726a274c25bd"}},{"arxiv_id":"2208.03550","paper":"/paper/frozen-clip-models-are-efficient-video","title":"Frozen CLIP Models are Efficient Video Learners","date":"2022-08-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenGVLab/efficient-video-recognition","path":"model.py","file_url":"https://github.com/OpenGVLab/efficient-video-recognition/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"827c460499de0c70","mcp_get_code":{"code_sha256":"827c460499de0c70"}},{"arxiv_id":"2207.14012","paper":"/paper/video-mask-transfiner-for-high-quality-video","title":"Video Mask Transfiner for High-Quality Video Instance Segmentation","date":"2022-07-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SysCV/vmt","path":"models/segmentation.py","file_url":"https://github.com/SysCV/vmt/blob/HEAD/models/segmentation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ed01e90c38f337c9","mcp_get_code":{"code_sha256":"ed01e90c38f337c9"}},{"arxiv_id":"2207.13820","paper":"/paper/cross-attention-of-disentangled-modalities","title":"Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers","date":"2022-07-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"postech-ami/fastmetro","path":"src/modeling/model/modeling_fastmetro.py","file_url":"https://github.com/postech-ami/fastmetro/blob/HEAD/src/modeling/model/modeling_fastmetro.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"81cad16cd0d5efb1","mcp_get_code":{"code_sha256":"81cad16cd0d5efb1"}},{"arxiv_id":"2207.10273","paper":"/paper/don-t-forget-me-accurate-background-recovery","title":"Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Context","date":"2022-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lcy0604/CTRNet","path":"models_CTRNet.py","file_url":"https://github.com/lcy0604/CTRNet/blob/HEAD/models_CTRNet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8432e0f043a686c3","mcp_get_code":{"code_sha256":"8432e0f043a686c3"}},{"arxiv_id":"2207.09644","paper":"/paper/hierarchically-self-supervised-transformer","title":"Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning","date":"2022-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuxiaochen1103/Hi-TRS","path":"model/Hi_TRS.py","file_url":"https://github.com/yuxiaochen1103/Hi-TRS/blob/HEAD/model/Hi_TRS.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"057b6db36bc7752b","mcp_get_code":{"code_sha256":"057b6db36bc7752b"}},{"arxiv_id":"2207.06405","paper":"/paper/masked-autoencoders-that-listen","title":"Masked Autoencoders that Listen","date":"2022-07-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/multimodal","path":"torchmultimodal/models/masked_auto_encoder/model.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/masked_auto_encoder/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"7a00feceab29852a","mcp_get_code":{"code_sha256":"7a00feceab29852a"}},{"arxiv_id":"2207.02777","paper":"/paper/don-t-pay-attention-to-the-noise-learning","title":"Don't Pay Attention to the Noise: Learning Self-supervised Representations of Light Curves with a Denoising Time Series Transformer","date":"2022-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mariomorvan/denoising-time-series-transformer","path":"models/models.py","file_url":"https://github.com/mariomorvan/denoising-time-series-transformer/blob/HEAD/models/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"82ac7fddfe86c023","mcp_get_code":{"code_sha256":"82ac7fddfe86c023"}},{"arxiv_id":"2206.10436","paper":"/paper/transformer-based-multi-modal-proposal-and-re","title":"Transformer-Based Multi-modal Proposal and Re-Rank for Wikipedia Image-Caption Matching","date":"2022-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"towhee-io/towhee","path":"towhee/models/coformer/transformer.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/coformer/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5f606c3ea722baea","mcp_get_code":{"code_sha256":"5f606c3ea722baea"}},{"arxiv_id":"2206.03789","paper":"/paper/language-bridged-spatial-temporal-interaction-1","title":"Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation","date":"2022-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dzh19990407/lbdt","path":"models/LBDT_4.py","file_url":"https://github.com/dzh19990407/lbdt/blob/HEAD/models/LBDT_4.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aa29d774bf09ba34","mcp_get_code":{"code_sha256":"aa29d774bf09ba34"}},{"arxiv_id":"2206.03687","paper":"/paper/a-unified-model-for-multi-class-anomaly","title":"A Unified Model for Multi-class Anomaly Detection","date":"2022-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhiyuanyou/uniad","path":"models/reconstructions/uniad.py","file_url":"https://github.com/zhiyuanyou/uniad/blob/HEAD/models/reconstructions/uniad.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4b270121cf640133","mcp_get_code":{"code_sha256":"4b270121cf640133"}},{"arxiv_id":"2205.14022","paper":"/paper/future-transformer-for-long-term-action","title":"Future Transformer for Long-term Action Anticipation","date":"2022-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gongda0e/futr","path":"model/futr.py","file_url":"https://github.com/gongda0e/futr/blob/HEAD/model/futr.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"a7e05a9a7dd57fe6","mcp_get_code":{"code_sha256":"a7e05a9a7dd57fe6"}},{"arxiv_id":"2203.15143","paper":"/paper/towards-end-to-end-unified-scene-text","title":"Towards End-to-End Unified Scene Text Detection and Layout Analysis","date":"2022-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chend-vl/instructocr","path":"models/transformer_decoder.py","file_url":"https://github.com/chend-vl/instructocr/blob/HEAD/models/transformer_decoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3150b099aa49e716","mcp_get_code":{"code_sha256":"3150b099aa49e716"}},{"arxiv_id":"2203.13296","paper":"/paper/raytran-3d-pose-estimation-and-shape","title":"RayTran: 3D pose estimation and shape reconstruction of multiple objects from videos with ray-traced transformers","date":"2022-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"likojack/ODAM","path":"src/models/transformer.py","file_url":"https://github.com/likojack/ODAM/blob/HEAD/src/models/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"110d117a309e1201","mcp_get_code":{"code_sha256":"110d117a309e1201"}},{"arxiv_id":"2203.13250","paper":"/paper/global-tracking-transformers","title":"Global Tracking Transformers","date":"2022-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xingyizhou/GTR","path":"gtr/modeling/roi_heads/transformer.py","file_url":"https://github.com/xingyizhou/GTR/blob/HEAD/gtr/modeling/roi_heads/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6f47261ee5162e04","mcp_get_code":{"code_sha256":"6f47261ee5162e04"}},{"arxiv_id":"2203.09388","paper":"/paper/a-text-attention-network-for-spatial","title":"A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution","date":"2022-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mjq11302010044/TATT","path":"model/transformerSR.py","file_url":"https://github.com/mjq11302010044/TATT/blob/HEAD/model/transformerSR.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5d4de4fe8da8b3bc","mcp_get_code":{"code_sha256":"5d4de4fe8da8b3bc"}},{"arxiv_id":"2203.08459","paper":"/paper/kinyabert-a-morphology-aware-kinyarwanda-1","title":"KinyaBERT: a Morphology-aware Kinyarwanda Language Model","date":"2022-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anzeyimana/kinyabert-acl2022","path":"code/morpho_model.py","file_url":"https://github.com/anzeyimana/kinyabert-acl2022/blob/HEAD/code/morpho_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"820fca5082f9435e","mcp_get_code":{"code_sha256":"820fca5082f9435e"}},{"arxiv_id":"2203.04229","paper":"/paper/neural-face-identification-in-a-2d-wireframe-1","title":"Neural Face Identification in a 2D Wireframe Projection of a Manifold Object","date":"2022-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"manycore-research/faceformer","path":"faceformer/models/model.py","file_url":"https://github.com/manycore-research/faceformer/blob/HEAD/faceformer/models/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"000429586ff77403","mcp_get_code":{"code_sha256":"000429586ff77403"}},{"arxiv_id":"2110.04722","paper":"/paper/transformer-based-dual-relation-graph-for-1","title":"Transformer-based Dual Relation Graph for Multi-label Image Recognition","date":"2021-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iCVTEAM/TDRG","path":"models/TDRG.py","file_url":"https://github.com/iCVTEAM/TDRG/blob/HEAD/models/TDRG.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4a32b2ac8f43376e","mcp_get_code":{"code_sha256":"4a32b2ac8f43376e"}},{"arxiv_id":"2109.04080","paper":"/paper/low-resource-dialogue-summarization-with","title":"Low-Resource Dialogue Summarization with Domain-Agnostic Multi-Source Pretraining","date":"2021-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RowitZou/DAMS","path":"src/models/dams.py","file_url":"https://github.com/RowitZou/DAMS/blob/HEAD/src/models/dams.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f11d3b7655768e5b","mcp_get_code":{"code_sha256":"f11d3b7655768e5b"}},{"arxiv_id":"2108.10723","paper":"/paper/improving-3d-object-detection-with-channel","title":"Improving 3D Object Detection with Channel-wise Transformer","date":"2021-08-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hlsheng1/ct3d","path":"pcdet/models/roi_heads/ct3d_head.py","file_url":"https://github.com/hlsheng1/ct3d/blob/HEAD/pcdet/models/roi_heads/ct3d_head.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9f90c23222eb4bbf","mcp_get_code":{"code_sha256":"9f90c23222eb4bbf"}},{"arxiv_id":"2108.07084","paper":"/paper/learning-canonical-view-representation-for-3d","title":"Learning Canonical View Representation for 3D Shape Recognition with Arbitrary Views","date":"2021-08-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weixmath/CVR","path":"models/Vit.py","file_url":"https://github.com/weixmath/CVR/blob/HEAD/models/Vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d1dcc3143bcaa503","mcp_get_code":{"code_sha256":"d1dcc3143bcaa503"}},{"arxiv_id":"2108.00202","paper":"/paper/hift-hierarchical-feature-transformer-for","title":"HiFT: Hierarchical Feature Transformer for Aerial Tracking","date":"2021-07-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vision4robotics/HiFT","path":"pysot/models/utile/utile.py","file_url":"https://github.com/vision4robotics/HiFT/blob/HEAD/pysot/models/utile/utile.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4119dfc79a334f6d","mcp_get_code":{"code_sha256":"4119dfc79a334f6d"}},{"arxiv_id":"2107.12309","paper":"/paper/spatial-temporal-transformer-for-dynamic","title":"Spatial-Temporal Transformer for Dynamic Scene Graph Generation","date":"2021-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lunaproject22/aar","path":"lib/transformer.py","file_url":"https://github.com/lunaproject22/aar/blob/HEAD/lib/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cf0d96423bcfe244","mcp_get_code":{"code_sha256":"cf0d96423bcfe244"}},{"arxiv_id":"2107.02960","paper":"/paper/glit-neural-architecture-search-for-global","title":"GLiT: Neural Architecture Search for Global and Local Image Transformer","date":"2021-07-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lpxtt/simtrack","path":"lib/models/stark/transformer.py","file_url":"https://github.com/lpxtt/simtrack/blob/HEAD/lib/models/stark/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0fa568810a644276","mcp_get_code":{"code_sha256":"0fa568810a644276"}},{"arxiv_id":"2105.11601","paper":"/paper/personalized-transformer-for-explainable","title":"Personalized Transformer for Explainable Recommendation","date":"2021-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lileipisces/PETER","path":"module.py","file_url":"https://github.com/lileipisces/PETER/blob/HEAD/module.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4a897ddcb771b965","mcp_get_code":{"code_sha256":"4a897ddcb771b965"}},{"arxiv_id":"2103.12236","paper":"/paper/instance-level-image-retrieval-using","title":"Instance-level Image Retrieval using Reranking Transformers","date":"2021-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uvavision/RerankingTransformer","path":"RRT_GLD/models/matcher.py","file_url":"https://github.com/uvavision/RerankingTransformer/blob/HEAD/RRT_GLD/models/matcher.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"04562f302b992df4","mcp_get_code":{"code_sha256":"04562f302b992df4"}},{"arxiv_id":"2103.11681","paper":"/paper/transformer-meets-tracker-exploiting-temporal","title":"Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking","date":"2021-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"594422814/TransformerTrack","path":"ltr/models/target_classifier/transformer.py","file_url":"https://github.com/594422814/TransformerTrack/blob/HEAD/ltr/models/target_classifier/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"81d1975ee00caff6","mcp_get_code":{"code_sha256":"81d1975ee00caff6"}},{"arxiv_id":"2103.11468","paper":"/paper/learning-multi-scene-absolute-pose-regression","title":"Learning Multi-Scene Absolute Pose Regression with Transformers","date":"2021-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yolish/c2f-ms-transformer","path":"models/transposenet/C2FEMSTransPoseNet.py","file_url":"https://github.com/yolish/c2f-ms-transformer/blob/HEAD/models/transposenet/C2FEMSTransPoseNet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e3af5e4f895771eb","mcp_get_code":{"code_sha256":"e3af5e4f895771eb"}},{"arxiv_id":"2103.06495","paper":"/paper/read-like-humans-autonomous-bidirectional-and","title":"Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition","date":"2021-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FangShancheng/ABINet","path":"modules/model_abinet.py","file_url":"https://github.com/FangShancheng/ABINet/blob/HEAD/modules/model_abinet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"152fce378f96441c","mcp_get_code":{"code_sha256":"152fce378f96441c"}},{"arxiv_id":"2103.03027","paper":"/paper/modeling-multi-label-action-dependencies-for","title":"Modeling Multi-Label Action Dependencies for Temporal Action Localization","date":"2021-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ptirupat/MLAD","path":"src/models/v1.py","file_url":"https://github.com/ptirupat/MLAD/blob/HEAD/src/models/v1.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5829945a54f11904","mcp_get_code":{"code_sha256":"5829945a54f11904"}},{"arxiv_id":"2103.01863","paper":"/paper/data-augmentation-for-abstractive-query","title":"Data Augmentation for Abstractive Query-Focused Multi-Document Summarization","date":"2021-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ramakanth-pasunuru/QmdsCnnIr","path":"src/abstractive/transformer_encoder.py","file_url":"https://github.com/ramakanth-pasunuru/QmdsCnnIr/blob/HEAD/src/abstractive/transformer_encoder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"aef61f6816c3986e","mcp_get_code":{"code_sha256":"aef61f6816c3986e"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SHI-Labs/Compact-Transformers","path":"src/vit.py","file_url":"https://github.com/SHI-Labs/Compact-Transformers/blob/HEAD/src/vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2f168ea21eac6721","mcp_get_code":{"code_sha256":"2f168ea21eac6721"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stevenwalton/scs-cct","path":"src/vit.py","file_url":"https://github.com/stevenwalton/scs-cct/blob/HEAD/src/vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"211aaa8ef68bf255","mcp_get_code":{"code_sha256":"211aaa8ef68bf255"}},{"arxiv_id":"2010.04505","paper":"/paper/self-paced-learning-for-neural-machine","title":"Self-Paced Learning for Neural Machine Translation","date":"2020-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wanyu2018umac/Self-Paced-Learning-for-Neural-Machine-Translation","path":"train/train_single.py","file_url":"https://github.com/wanyu2018umac/Self-Paced-Learning-for-Neural-Machine-Translation/blob/HEAD/train/train_single.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e579d3edd8e83e00","mcp_get_code":{"code_sha256":"e579d3edd8e83e00"}},{"arxiv_id":"2006.09265","paper":"/paper/modelling-high-level-mathematical-reasoning","title":"IsarStep: a Benchmark for High-level Mathematical Reasoning","date":"2020-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"reactive-systems/ml2","path":"ml2/models/tf_hierarchical_transformer.py","file_url":"https://github.com/reactive-systems/ml2/blob/HEAD/ml2/models/tf_hierarchical_transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"96e9ed72cac68cc4","mcp_get_code":{"code_sha256":"96e9ed72cac68cc4"}},{"arxiv_id":"2006.04558","paper":"/paper/fastspeech-2-fast-and-high-quality-end-to-end","title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","date":"2020-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"keonlee9420/Comprehensive-Transformer-TTS","path":"model/transformers/transformer_fs2.py","file_url":"https://github.com/keonlee9420/Comprehensive-Transformer-TTS/blob/HEAD/model/transformers/transformer_fs2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8b3460ae89d120ba","mcp_get_code":{"code_sha256":"8b3460ae89d120ba"}},{"arxiv_id":"2005.12872","paper":"/paper/end-to-end-object-detection-with-transformers","title":"End-to-End Object Detection with Transformers","date":"2020-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"clive819/Modified-DETR","path":"models/detr.py","file_url":"https://github.com/clive819/Modified-DETR/blob/HEAD/models/detr.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3e3613a79dc6d21d","mcp_get_code":{"code_sha256":"3e3613a79dc6d21d"}},{"arxiv_id":"2005.12872","paper":"/paper/end-to-end-object-detection-with-transformers","title":"End-to-End Object Detection with Transformers","date":"2020-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alibaba/EasyCV","path":"easycv/models/detection/detectors/detr/detr_transformer.py","file_url":"https://github.com/alibaba/EasyCV/blob/HEAD/easycv/models/detection/detectors/detr/detr_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"526d67b8881712d6","mcp_get_code":{"code_sha256":"526d67b8881712d6"}},{"arxiv_id":"1906.00295","paper":"/paper/190600295","title":"Multimodal Transformer for Unaligned Multimodal Language Sequences","date":"2019-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kenford953/graphcage","path":"src/CrossmodalTransformer.py","file_url":"https://github.com/kenford953/graphcage/blob/HEAD/src/CrossmodalTransformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b04b6b2fd212ab1a","mcp_get_code":{"code_sha256":"b04b6b2fd212ab1a"}},{"arxiv_id":"1906.00295","paper":"/paper/190600295","title":"Multimodal Transformer for Unaligned Multimodal Language Sequences","date":"2019-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yaohungt/Multimodal-Transformer","path":"src/models.py","file_url":"https://github.com/yaohungt/Multimodal-Transformer/blob/HEAD/src/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9518e860e7fd09b2","mcp_get_code":{"code_sha256":"9518e860e7fd09b2"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AssafSinger94/sigmorphon-2020-inflection","path":"src/transformer.py","file_url":"https://github.com/AssafSinger94/sigmorphon-2020-inflection/blob/HEAD/src/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"24c45b3ce8fe00b9","mcp_get_code":{"code_sha256":"24c45b3ce8fe00b9"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"enhuiz/torchnmt","path":"torchnmt/networks/transformer.py","file_url":"https://github.com/enhuiz/torchnmt/blob/HEAD/torchnmt/networks/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aa82a87615f2df7e","mcp_get_code":{"code_sha256":"aa82a87615f2df7e"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JanAthmer/Compositional-generalization-capabillity-of-Transformer","path":"models/transformer.py","file_url":"https://github.com/JanAthmer/Compositional-generalization-capabillity-of-Transformer/blob/HEAD/models/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"77b7bfa892f25276","mcp_get_code":{"code_sha256":"77b7bfa892f25276"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cosmoquester/seq2seq","path":"seq2seq/model.py","file_url":"https://github.com/cosmoquester/seq2seq/blob/HEAD/seq2seq/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1558999453664ba0","mcp_get_code":{"code_sha256":"1558999453664ba0"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Iwontbecreative/Abstractive-summarization-OpenNMT","path":"onmt/modules/Transformer.py","file_url":"https://github.com/Iwontbecreative/Abstractive-summarization-OpenNMT/blob/HEAD/onmt/modules/Transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b0a0e6e6c4566c2f","mcp_get_code":{"code_sha256":"b0a0e6e6c4566c2f"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"reactive-systems/circuit-repair","path":"ml2/models/transformer.py","file_url":"https://github.com/reactive-systems/circuit-repair/blob/HEAD/ml2/models/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b258126cffa99758","mcp_get_code":{"code_sha256":"b258126cffa99758"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gooppe/transformer-summarization","path":"nn/modules/transformer.py","file_url":"https://github.com/gooppe/transformer-summarization/blob/HEAD/nn/modules/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"40371c45b63eed0c","mcp_get_code":{"code_sha256":"40371c45b63eed0c"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WenjieDu/PyPOTS","path":"pypots/nn/modules/transformer/autoencoder.py","file_url":"https://github.com/WenjieDu/PyPOTS/blob/HEAD/pypots/nn/modules/transformer/autoencoder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"1aff7736e8206c95","mcp_get_code":{"code_sha256":"1aff7736e8206c95"}}]}