{"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/multiheadattention-2","entry":"MultiheadAttention","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":44,"n_papers_ran":28,"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":48,"n_samples_ran":29,"n_samples_fingerprinted":2,"n_places":48,"n_places_pointer_only":19,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":29,"unverified":19},"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":"2606.17967","paper":"/paper/arxiv-2606-17967","title":"Learning task-specific subspaces via interventional post-training of speech foundation models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"s3prl/s3prl","path":"s3prl/upstream/distiller/model.py","file_url":"https://github.com/s3prl/s3prl/blob/HEAD/s3prl/upstream/distiller/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":"8ae62a892bc13c8d","mcp_get_code":{"code_sha256":"8ae62a892bc13c8d"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6882e88420185b2a","mcp_get_code":{"code_sha256":"6882e88420185b2a"}},{"arxiv_id":"2604.06814","paper":"/paper/arxiv-2604-06814","title":"OmniTabBench: Mapping the Empirical Frontiers of GBDTs, Neural Networks, and Foundation Models for Tabular Data at Scale","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"yandex-research/rtdl-revisiting-models","path":"package/rtdl_revisiting_models.py","file_url":"https://github.com/yandex-research/rtdl-revisiting-models/blob/HEAD/package/rtdl_revisiting_models.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":"3a561d57f211e806","mcp_get_code":{"code_sha256":"3a561d57f211e806"}},{"arxiv_id":"2603.14171","paper":"/paper/arxiv-2603-14171","title":"TACTIC for Navigating the Unknown: Tabular Anomaly deteCTion via In-Context inference","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"gmum/TACTIC","path":"tactic/model/tactic.py","file_url":"https://github.com/gmum/TACTIC/blob/HEAD/tactic/model/tactic.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b3eb71915b80481c","mcp_get_code":{"code_sha256":"b3eb71915b80481c"}},{"arxiv_id":"2602.15537","paper":"/paper/arxiv-2602-15537","title":"ZeroSyl: Simple Zero-Resource Syllable Tokenization for Spoken Language Modeling","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"nicolvisser/ZeroSyl","path":"zerosyl/zerosyl.py","file_url":"https://github.com/nicolvisser/ZeroSyl/blob/HEAD/zerosyl/zerosyl.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"11bbf68104c4afcd","mcp_get_code":{"code_sha256":"11bbf68104c4afcd"}},{"arxiv_id":"2510.19710","paper":"/paper/arxiv-2510-19710","title":"SEMPO: Lightweight Foundation Models for Time Series Forecasting","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"mala-lab/SEMPO","path":"models/SEMPO.py","file_url":"https://github.com/mala-lab/SEMPO/blob/HEAD/models/SEMPO.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":"716e24f597b6f1ff","mcp_get_code":{"code_sha256":"716e24f597b6f1ff"}},{"arxiv_id":"2510.13329","paper":"/paper/arxiv-2510-13329","title":"Embedding-Based Context-Aware Reranker","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"BorealisAI/EBCAR","path":"src/model/ebcar_dedicated_attention_model.py","file_url":"https://github.com/BorealisAI/EBCAR/blob/HEAD/src/model/ebcar_dedicated_attention_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"621850593b6a52e8","mcp_get_code":{"code_sha256":"621850593b6a52e8"}},{"arxiv_id":"2503.20826","paper":"/paper/exploring-clip-s-dense-knowledge-for-weakly","title":"Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation","date":"2025-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zwyang6/ExCEL","path":"model/model_excel.py","file_url":"https://github.com/zwyang6/ExCEL/blob/HEAD/model/model_excel.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9fec802d480b8213","mcp_get_code":{"code_sha256":"9fec802d480b8213"}},{"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":"71680f2ec58be898","mcp_get_code":{"code_sha256":"71680f2ec58be898"}},{"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":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d232f407f48ea631","mcp_get_code":{"code_sha256":"d232f407f48ea631"}},{"arxiv_id":"2402.19009","paper":"/paper/generating-reconstructing-and-representing","title":"Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding","date":"2024-02-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guangyliu/eddpm","path":"Protein/codes/nn/models.py","file_url":"https://github.com/guangyliu/eddpm/blob/HEAD/Protein/codes/nn/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ebbb4cab1eb5afaf","mcp_get_code":{"code_sha256":"ebbb4cab1eb5afaf"}},{"arxiv_id":"2309.12855","paper":"/paper/cross-modal-translation-and-alignment-for","title":"Cross-Modal Translation and Alignment for Survival Analysis","date":"2023-09-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ft-zhou-zzz/cmta","path":"models/cmta/network.py","file_url":"https://github.com/ft-zhou-zzz/cmta/blob/HEAD/models/cmta/network.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"239d8370d131c65d","mcp_get_code":{"code_sha256":"239d8370d131c65d"}},{"arxiv_id":"2308.06383","paper":"/paper/u-red-unsupervised-3d-shape-retrieval-and","title":"U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Clouds","date":"2023-08-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhangcyg/u-red","path":"network/deformation_net.py","file_url":"https://github.com/zhangcyg/u-red/blob/HEAD/network/deformation_net.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c9afeb7769ae9b17","mcp_get_code":{"code_sha256":"c9afeb7769ae9b17"}},{"arxiv_id":"2306.08330","paper":"/paper/multimodal-optimal-transport-based-co","title":"Multimodal Optimal Transport-based Co-Attention Transformer with Global Structure Consistency for Survival Prediction","date":"2023-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JJ-ZHOU-Code/RobustMultiModel","path":"models/model_coattn.py","file_url":"https://github.com/JJ-ZHOU-Code/RobustMultiModel/blob/HEAD/models/model_coattn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b3b023b4c6805594","mcp_get_code":{"code_sha256":"b3b023b4c6805594"}},{"arxiv_id":"2305.05665","paper":"/paper/imagebind-one-embedding-space-to-bind-them","title":"ImageBind: One Embedding Space To Bind Them All","date":"2023-05-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/imagebind","path":"imagebind/models/imagebind_model.py","file_url":"https://github.com/facebookresearch/imagebind/blob/HEAD/imagebind/models/imagebind_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"e571e943335367a5","mcp_get_code":{"code_sha256":"e571e943335367a5"}},{"arxiv_id":"2305.00664","paper":"/paper/dynamic-transfer-learning-across-graphs","title":"EvoluNet: Advancing Dynamic Non-IID Transfer Learning on Graphs","date":"2023-05-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wanghh7/evolunet","path":"model/model.py","file_url":"https://github.com/wanghh7/evolunet/blob/HEAD/model/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0838369745d53cad","mcp_get_code":{"code_sha256":"0838369745d53cad"}},{"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":"3e1a3d7b3bf9ed48","mcp_get_code":{"code_sha256":"3e1a3d7b3bf9ed48"}},{"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":"89990d89c23c5bfa","mcp_get_code":{"code_sha256":"89990d89c23c5bfa"}},{"arxiv_id":"2303.09266","paper":"/paper/smartbert-a-promotion-of-dynamic-early","title":"SmartBERT: A Promotion of Dynamic Early Exiting Mechanism for Accelerating BERT Inference","date":"2023-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HuBoren99/SmartBert","path":"models/SmartBert.py","file_url":"https://github.com/HuBoren99/SmartBert/blob/HEAD/models/SmartBert.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a55fea32788cd568","mcp_get_code":{"code_sha256":"a55fea32788cd568"}},{"arxiv_id":"2302.11002","paper":"/paper/learning-physical-models-that-can-respect","title":"Learning Physical Models that Can Respect Conservation Laws","date":"2023-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-science/probconserv","path":"deep_pdes/attentive_neural_process/probconserv.py","file_url":"https://github.com/amazon-science/probconserv/blob/HEAD/deep_pdes/attentive_neural_process/probconserv.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":"fc456591ed6ce764","mcp_get_code":{"code_sha256":"fc456591ed6ce764"}},{"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":"2a40c453f8215cf1","mcp_get_code":{"code_sha256":"2a40c453f8215cf1"}},{"arxiv_id":"2211.07950","paper":"/paper/breakpoint-transformers-for-modeling-and","title":"Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs","date":"2022-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NicolasAG/SGinPG","path":"src/model.py","file_url":"https://github.com/NicolasAG/SGinPG/blob/HEAD/src/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"0b4cce6121085c3c","mcp_get_code":{"code_sha256":"0b4cce6121085c3c"}},{"arxiv_id":"2207.09840","paper":"/paper/elegant-exquisite-and-locally-editable-gan","title":"EleGANt: Exquisite and Locally Editable GAN for Makeup Transfer","date":"2022-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Chenyu-Yang-2000/EleGANt","path":"models/elegant.py","file_url":"https://github.com/Chenyu-Yang-2000/EleGANt/blob/HEAD/models/elegant.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"153bf0a3c6aaf0ac","mcp_get_code":{"code_sha256":"153bf0a3c6aaf0ac"}},{"arxiv_id":"2204.04667","paper":"/paper/linear-complexity-randomized-self-attention","title":"Linear Complexity Randomized Self-attention Mechanism","date":"2022-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hkunlp/efficient-attention","path":"efficient-attention/efficient_attention/lara.py","file_url":"https://github.com/hkunlp/efficient-attention/blob/HEAD/efficient-attention/efficient_attention/lara.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":"bd857b15ac85b005","mcp_get_code":{"code_sha256":"bd857b15ac85b005"}},{"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":"4639b692ef625093","mcp_get_code":{"code_sha256":"4639b692ef625093"}},{"arxiv_id":"2112.10741","paper":"/paper/glide-towards-photorealistic-image-generation","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","date":"2021-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openai/glide-text2im","path":"glide_text2im/text2im_model.py","file_url":"https://github.com/openai/glide-text2im/blob/HEAD/glide_text2im/text2im_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"001daee6f2379723","mcp_get_code":{"code_sha256":"001daee6f2379723"}},{"arxiv_id":"2111.12594","paper":"/paper/conditional-object-centric-learning-from-1","title":"Conditional Object-Centric Learning from Video","date":"2021-11-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Genera1Z/SAVi-PyTorch","path":"model.py","file_url":"https://github.com/Genera1Z/SAVi-PyTorch/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":"a50cd588d4e75a0a","mcp_get_code":{"code_sha256":"a50cd588d4e75a0a"}},{"arxiv_id":"2110.09408","paper":"/paper/hrformer-high-resolution-transformer-for","title":"HRFormer: High-Resolution Transformer for Dense Prediction","date":"2021-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HRNet/HRFormer","path":"cls/models/hrt.py","file_url":"https://github.com/HRNet/HRFormer/blob/HEAD/cls/models/hrt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7f956321be67f123","mcp_get_code":{"code_sha256":"7f956321be67f123"}},{"arxiv_id":"2106.01269","paper":"/paper/more-identifiable-yet-equally-performant","title":"More Identifiable yet Equally Performant Transformers for Text Classification","date":"2021-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"declare-lab/identifiable-transformers","path":"model_identifiable.py","file_url":"https://github.com/declare-lab/identifiable-transformers/blob/HEAD/model_identifiable.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":"65062d0b9d191cb5","mcp_get_code":{"code_sha256":"65062d0b9d191cb5"}},{"arxiv_id":"2105.13868","paper":"/paper/learning-relation-alignment-for-calibrated","title":"Learning Relation Alignment for Calibrated Cross-modal Retrieval","date":"2021-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lancopku/IAIS","path":"model/attention.py","file_url":"https://github.com/lancopku/IAIS/blob/HEAD/model/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7a6b1633c8b59698","mcp_get_code":{"code_sha256":"7a6b1633c8b59698"}},{"arxiv_id":"2105.11269","paper":"/paper/neural-machine-translation-with-monolingual","title":"Neural Machine Translation with Monolingual Translation Memory","date":"2021-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jcyk/copyisallyouneed","path":"generator.py","file_url":"https://github.com/jcyk/copyisallyouneed/blob/HEAD/generator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"869a715ba18c9742","mcp_get_code":{"code_sha256":"869a715ba18c9742"}},{"arxiv_id":"2104.08821","paper":"/paper/simcse-simple-contrastive-learning-of","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","date":"2021-04-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jeongukjae/KR-BERT-SimCSE","path":"model.py","file_url":"https://github.com/jeongukjae/KR-BERT-SimCSE/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0903880703193f2a","mcp_get_code":{"code_sha256":"0903880703193f2a"}},{"arxiv_id":"2104.00678","paper":"/paper/group-free-3d-object-detection-via","title":"Group-Free 3D Object Detection via Transformers","date":"2021-04-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"KookHoiKim/GroupFree3dBaseline","path":"models/detector.py","file_url":"https://github.com/KookHoiKim/GroupFree3dBaseline/blob/HEAD/models/detector.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6bd1a32eae6a6a53","mcp_get_code":{"code_sha256":"6bd1a32eae6a6a53"}},{"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":"1b733e1fccc5d345","mcp_get_code":{"code_sha256":"1b733e1fccc5d345"}},{"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":"topdu/openocr","path":"openrec/modeling/decoders/abinet_decoder.py","file_url":"https://github.com/topdu/openocr/blob/HEAD/openrec/modeling/decoders/abinet_decoder.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":"5dd87791ac034fb5","mcp_get_code":{"code_sha256":"5dd87791ac034fb5"}},{"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":"7c0b340a62978887","mcp_get_code":{"code_sha256":"7c0b340a62978887"}},{"arxiv_id":"2103.03457","paper":"/paper/iot-instance-wise-layer-reordering-for-1","title":"IOT: Instance-wise Layer Reordering for Transformer Structures","date":"2021-03-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"instance-wise-ordered-transformer/IOT","path":"fairseq/modules/transformer_sentence_encoder_layer.py","file_url":"https://github.com/instance-wise-ordered-transformer/IOT/blob/HEAD/fairseq/modules/transformer_sentence_encoder_layer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"b4aacbb45af4df12","mcp_get_code":{"code_sha256":"b4aacbb45af4df12"}},{"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":"nateraw/lightning-vision-transformer","path":"vit.py","file_url":"https://github.com/nateraw/lightning-vision-transformer/blob/HEAD/vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"28d07cea36220258","mcp_get_code":{"code_sha256":"28d07cea36220258"}},{"arxiv_id":"2010.04245","paper":"/paper/query-key-normalization-for-transformers","title":"Query-Key Normalization for Transformers","date":"2020-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CyndxAI/QKNorm","path":"QKNorm/layers.py","file_url":"https://github.com/CyndxAI/QKNorm/blob/HEAD/QKNorm/layers.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":"ca45e6f04d39e00c","mcp_get_code":{"code_sha256":"ca45e6f04d39e00c"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"91289eb6932cf19a","mcp_get_code":{"code_sha256":"91289eb6932cf19a"}},{"arxiv_id":"2004.05572","paper":"/paper/amr-parsing-via-graph-sequence-iterative","title":"AMR Parsing via Graph-Sequence Iterative Inference","date":"2020-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bjascob/amrlib","path":"amrlib/models/parse_gsii/modules/parser.py","file_url":"https://github.com/bjascob/amrlib/blob/HEAD/amrlib/models/parse_gsii/modules/parser.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4b0bd99292baeaff","mcp_get_code":{"code_sha256":"4b0bd99292baeaff"}},{"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":"34e57a8ff4c50a35","mcp_get_code":{"code_sha256":"34e57a8ff4c50a35"}},{"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":"a1bae24ff466241b","mcp_get_code":{"code_sha256":"a1bae24ff466241b"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huanghonggit/Mask-Language-Model","path":"model/bert.py","file_url":"https://github.com/huanghonggit/Mask-Language-Model/blob/HEAD/model/bert.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":"0d4d097ae7a7f1de","mcp_get_code":{"code_sha256":"0d4d097ae7a7f1de"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"devJWSong/bert-crf-entity-recognition-pytorch","path":"src/layers.py","file_url":"https://github.com/devJWSong/bert-crf-entity-recognition-pytorch/blob/HEAD/src/layers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"af47ebae6c05725a","mcp_get_code":{"code_sha256":"af47ebae6c05725a"}},{"arxiv_id":"1807.03819","paper":"/paper/universal-transformers","title":"Universal Transformers","date":"2018-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cfiken/universal_transformer","path":"model/ut.py","file_url":"https://github.com/cfiken/universal_transformer/blob/HEAD/model/ut.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"97703c2875660e0b","mcp_get_code":{"code_sha256":"97703c2875660e0b"}},{"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":"knotgrass/attention","path":"attn/attention.py","file_url":"https://github.com/knotgrass/attention/blob/HEAD/attn/attention.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6c73a396116acbdd","mcp_get_code":{"code_sha256":"6c73a396116acbdd"}},{"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":"abhaskumarsinha/Keras-implementation-of-Transformer-Architecture","path":"Transformer.py","file_url":"https://github.com/abhaskumarsinha/Keras-implementation-of-Transformer-Architecture/blob/HEAD/Transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"bc1bf715a553f14a","mcp_get_code":{"code_sha256":"bc1bf715a553f14a"}}]}