{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/absolute-position-encodings/papers/124","list_of":"/method/absolute-position-encodings","method":"Absolute Position Encodings","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":124,"pages_in_order":140,"rows_per_page":100,"rows":[12301,12400],"of":13942,"counts":{"archive_papers_tagged":13942,"with_a_code_link":6505,"where_syntology_ran_a_sample":2224,"not_listed_spam_title":0,"listed":13942,"listed_where_code_ran":2224,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1897,"every_run_a_failure_of_syntologys_instrument":327,"listed_with_a_run_with_no_instrument_failure":1897,"listed_every_run_a_failure_of_syntologys_instrument":327,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/absolute-position-encodings","prev":"/method/absolute-position-encodings/papers/123","next":"/method/absolute-position-encodings/papers/125","papers":[{"paper":null,"slug":"severity-quantification-and-lesion","title":"Severity Quantification and Lesion Localization of COVID-19 on CXR using Vision Transformer","date":"2021-03-12","arxiv_id":"2103.07062","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-transformer-for-covid-19-cxr-diagnosis","title":"Vision Transformer for COVID-19 CXR Diagnosis using Chest X-ray Feature Corpus","date":"2021-03-12","arxiv_id":"2103.07055","n_code_links":0,"syntology":null},{"paper":"/paper/canine-pre-training-an-efficient-tokenization","slug":"canine-pre-training-an-efficient-tokenization","title":"CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation","date":"2021-03-11","arxiv_id":"2103.06874","n_code_links":6,"syntology":null},{"paper":null,"slug":"continuous-3d-multi-channel-sign-language","title":"Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks","date":"2021-03-11","arxiv_id":"2103.06982","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-improving-deep-learning-trace-analysis","title":"On Improving Deep Learning Trace Analysis with System Call Arguments","date":"2021-03-11","arxiv_id":"2103.06915","n_code_links":0,"syntology":null},{"paper":"/paper/unknown-object-segmentation-from-stereo","slug":"unknown-object-segmentation-from-stereo","title":"Unknown Object Segmentation from Stereo Images","date":"2021-03-11","arxiv_id":"2103.06796","n_code_links":2,"syntology":null},{"paper":"/paper/cuad-an-expert-annotated-nlp-dataset-for","slug":"cuad-an-expert-annotated-nlp-dataset-for","title":"CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review","date":"2021-03-10","arxiv_id":"2103.06268","n_code_links":2,"syntology":null},{"paper":"/paper/pretrained-transformers-as-universal","slug":"pretrained-transformers-as-universal","title":"Pretrained Transformers as Universal Computation Engines","date":"2021-03-09","arxiv_id":"2103.05247","n_code_links":4,"syntology":null},{"paper":"/paper/end-to-end-human-object-interaction-detection","slug":"end-to-end-human-object-interaction-detection","title":"End-to-End Human Object Interaction Detection with HOI Transformer","date":"2021-03-08","arxiv_id":"2103.04503","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["bbepoch/HoiTransformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"mtlhealth-a-deep-learning-system-for","title":"MTLHealth: A Deep Learning System for Detecting Disturbing Content in Student Essays","date":"2021-03-07","arxiv_id":"2103.04290","n_code_links":0,"syntology":null},{"paper":"/paper/syntax-bert-improving-pre-trained","slug":"syntax-bert-improving-pre-trained","title":"Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees","date":"2021-03-07","arxiv_id":"2103.04350","n_code_links":1,"syntology":null},{"paper":"/paper/transbts-multimodal-brain-tumor-segmentation","slug":"transbts-multimodal-brain-tumor-segmentation","title":"TransBTS: Multimodal Brain Tumor Segmentation Using Transformer","date":"2021-03-07","arxiv_id":"2103.04430","n_code_links":3,"syntology":null},{"paper":"/paper/attention-is-not-all-you-need-pure-attention","slug":"attention-is-not-all-you-need-pure-attention","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","date":"2021-03-05","arxiv_id":"2103.03404","n_code_links":1,"syntology":null},{"paper":null,"slug":"hierarchical-transformer-for-multilingual","title":"Hierarchical Transformer for Multilingual Machine Translation","date":"2021-03-05","arxiv_id":"2103.03589","n_code_links":0,"syntology":null},{"paper":"/paper/iot-instance-wise-layer-reordering-for-1","slug":"iot-instance-wise-layer-reordering-for-1","title":"IOT: Instance-wise Layer Reordering for Transformer Structures","date":"2021-03-05","arxiv_id":"2103.03457","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":1,"n_instrument":2,"unverified":2,"pointer_only":5,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":{"repos":["instance-wise-ordered-transformer/IOT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/measuring-mathematical-problem-solving-with","slug":"measuring-mathematical-problem-solving-with","title":"Measuring Mathematical Problem Solving With the MATH Dataset","date":"2021-03-05","arxiv_id":"2103.03874","n_code_links":5,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hendrycks/math"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/spectr-spectral-transformer-for-hyperspectral","slug":"spectr-spectral-transformer-for-hyperspectral","title":"SpecTr: Spectral Transformer for Hyperspectral Pathology Image Segmentation","date":"2021-03-05","arxiv_id":"2103.03604","n_code_links":1,"syntology":null},{"paper":"/paper/cotr-efficiently-bridging-cnn-and-transformer","slug":"cotr-efficiently-bridging-cnn-and-transformer","title":"CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation","date":"2021-03-04","arxiv_id":"2103.03024","n_code_links":1,"syntology":null},{"paper":null,"slug":"end-to-end-acoustic-modelling-for-phone","title":"End-to-end acoustic modelling for phone recognition of young readers","date":"2021-03-04","arxiv_id":"2103.02899","n_code_links":0,"syntology":null},{"paper":"/paper/the-transformer-network-for-the-traveling","slug":"the-transformer-network-for-the-traveling","title":"The Transformer Network for the Traveling Salesman Problem","date":"2021-03-04","arxiv_id":"2103.03012","n_code_links":1,"syntology":null},{"paper":null,"slug":"university-of-copenhagen-participation-in","title":"University of Copenhagen Participation in TREC Health Misinformation Track 2020","date":"2021-03-03","arxiv_id":"2103.02462","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-hint-from-arithmetic-on-systematic","title":"A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics","date":"2021-03-02","arxiv_id":"2103.01403","n_code_links":0,"syntology":null},{"paper":null,"slug":"dual-reinforcement-based-specification","title":"Dual Reinforcement-Based Specification Generation for Image De-Rendering","date":"2021-03-02","arxiv_id":"2103.01867","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-product-description-generation-via","title":"Probing Product Description Generation via Posterior Distillation","date":"2021-03-02","arxiv_id":"2103.01594","n_code_links":0,"syntology":null},{"paper":null,"slug":"crossmap-transformer-a-crossmodal-masked-path","title":"CrossMap Transformer: A Crossmodal Masked Path Transformer Using Double Back-Translation for Vision-and-Language Navigation","date":"2021-03-01","arxiv_id":"2103.00852","n_code_links":0,"syntology":null},{"paper":"/paper/generative-chemical-transformer-attention","slug":"generative-chemical-transformer-attention","title":"Generative Chemical Transformer: Neural Machine Learning of Molecular Geometric Structures from Chemical Language via Attention","date":"2021-02-27","arxiv_id":"2103.00213","n_code_links":2,"syntology":null},{"paper":"/paper/transformer-in-transformer","slug":"transformer-in-transformer","title":"Transformer in Transformer","date":"2021-02-27","arxiv_id":"2103.00112","n_code_links":12,"syntology":{"ran":16,"of":24,"n_ran_checked":15,"n_instrument":1,"unverified":8,"pointer_only":5,"phrase":"16 ran (of which 12 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 1 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","official":{"repos":["huawei-noah/CV-backbones"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"transformers-with-competitive-ensembles-of-1","title":"Transformers with Competitive Ensembles of Independent Mechanisms","date":"2021-02-27","arxiv_id":"2103.00336","n_code_links":0,"syntology":null},{"paper":null,"slug":"lazyformer-self-attention-with-lazy-update","title":"LazyFormer: Self Attention with Lazy Update","date":"2021-02-25","arxiv_id":"2102.12702","n_code_links":0,"syntology":null},{"paper":"/paper/let-linguistic-knowledge-enhanced-graph","slug":"let-linguistic-knowledge-enhanced-graph","title":"LET: Linguistic Knowledge Enhanced Graph Transformer for Chinese Short Text Matching","date":"2021-02-25","arxiv_id":"2102.12671","n_code_links":1,"syntology":null},{"paper":null,"slug":"mixspeech-data-augmentation-for-low-resource","title":"MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition","date":"2021-02-25","arxiv_id":"2102.12664","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-universal-language-model-to-downstream","title":"From Universal Language Model to Downstream Task: Improving RoBERTa-Based Vietnamese Hate Speech Detection","date":"2021-02-24","arxiv_id":"2102.12162","n_code_links":0,"syntology":null},{"paper":"/paper/pyramid-vision-transformer-a-versatile","slug":"pyramid-vision-transformer-a-versatile","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","date":"2021-02-24","arxiv_id":"2102.12122","n_code_links":11,"syntology":{"ran":22,"of":30,"n_ran_checked":18,"n_instrument":4,"unverified":8,"pointer_only":1,"phrase":"22 ran (of which 16 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 0 violated, 16 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified","official":{"repos":["whai362/PVT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/when-attention-meets-fast-recurrence-training","slug":"when-attention-meets-fast-recurrence-training","title":"When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute","date":"2021-02-24","arxiv_id":"2102.12459","n_code_links":1,"syntology":null},{"paper":"/paper/accurate-learning-of-graph-representations-1","slug":"accurate-learning-of-graph-representations-1","title":"Accurate Learning of Graph Representations with Graph Multiset Pooling","date":"2021-02-23","arxiv_id":"2102.11533","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["JinheonBaek/GMT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"deep-deformation-detail-synthesis-for-thin","title":"Deep Deformation Detail Synthesis for Thin Shell Models","date":"2021-02-23","arxiv_id":"2102.11541","n_code_links":0,"syntology":null},{"paper":"/paper/do-transformer-modifications-transfer-across","slug":"do-transformer-modifications-transfer-across","title":"Do Transformer Modifications Transfer Across Implementations and Applications?","date":"2021-02-23","arxiv_id":"2102.11972","n_code_links":1,"syntology":null},{"paper":"/paper/deepfake-video-detection-using-convolutional","slug":"deepfake-video-detection-using-convolutional","title":"Deepfake Video Detection Using Convolutional Vision Transformer","date":"2021-02-22","arxiv_id":"2102.11126","n_code_links":1,"syntology":null},{"paper":null,"slug":"determination-of-fault-location-in","title":"Determination of Fault Location in Transmission Lines with Image Processing and Artificial Neural Networks","date":"2021-02-22","arxiv_id":"2102.11073","n_code_links":0,"syntology":null},{"paper":"/paper/do-we-really-need-explicit-position-encodings","slug":"do-we-really-need-explicit-position-encodings","title":"Conditional Positional Encodings for Vision Transformers","date":"2021-02-22","arxiv_id":"2102.10882","n_code_links":2,"syntology":null},{"paper":null,"slug":"position-information-in-transformers-an","title":"Position Information in Transformers: An Overview","date":"2021-02-22","arxiv_id":"2102.11090","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-is-all-you-need-multimodal","slug":"transformer-is-all-you-need-multimodal","title":"UniT: Multimodal Multitask Learning with a Unified Transformer","date":"2021-02-22","arxiv_id":"2102.10772","n_code_links":1,"syntology":null},{"paper":"/paper/medical-transformer-gated-axial-attention-for","slug":"medical-transformer-gated-axial-attention-for","title":"Medical Transformer: Gated Axial-Attention for Medical Image Segmentation","date":"2021-02-21","arxiv_id":"2102.10662","n_code_links":2,"syntology":null},{"paper":null,"slug":"multilingual-answer-sentence-reranking-via","title":"Multilingual Answer Sentence Reranking via Automatically Translated Data","date":"2021-02-20","arxiv_id":"2102.10250","n_code_links":0,"syntology":null},{"paper":"/paper/towards-accurate-and-compact-architectures","slug":"towards-accurate-and-compact-architectures","title":"Towards Accurate and Compact Architectures via Neural Architecture Transformer","date":"2021-02-20","arxiv_id":"2102.10301","n_code_links":2,"syntology":null},{"paper":null,"slug":"dialect-identification-in-nuanced-arabic","title":"Dialect Identification in Nuanced Arabic Tweets Using Farasa Segmentation and AraBERT","date":"2021-02-19","arxiv_id":"2102.09749","n_code_links":0,"syntology":null},{"paper":"/paper/latent-variable-nested-set-transformers","slug":"latent-variable-nested-set-transformers","title":"Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction","date":"2021-02-19","arxiv_id":"2104.00563","n_code_links":2,"syntology":{"ran":11,"of":17,"n_ran_checked":10,"n_instrument":1,"unverified":6,"pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["roggirg/AutoBots"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/going-full-tilt-boogie-on-document","slug":"going-full-tilt-boogie-on-document","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","date":"2021-02-18","arxiv_id":"2102.09550","n_code_links":1,"syntology":null},{"paper":"/paper/quiz-style-question-generation-for-news","slug":"quiz-style-question-generation-for-news","title":"Quiz-Style Question Generation for News Stories","date":"2021-02-18","arxiv_id":"2102.09094","n_code_links":2,"syntology":null},{"paper":"/paper/beyond-fully-connected-layers-with","slug":"beyond-fully-connected-layers-with","title":"Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with $1/n$ Parameters","date":"2021-02-17","arxiv_id":"2102.08597","n_code_links":3,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["astonzhang/Parameterization-of-Hypercomplex-Multiplications"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/gradinit-learning-to-initialize-neural","slug":"gradinit-learning-to-initialize-neural","title":"GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training","date":"2021-02-16","arxiv_id":"2102.08098","n_code_links":2,"syntology":{"ran":7,"of":13,"n_ran_checked":4,"n_instrument":3,"unverified":6,"pointer_only":12,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","official":{"repos":["zhuchen03/gradinit"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/revisiting-language-encoding-in-learning","slug":"revisiting-language-encoding-in-learning","title":"Revisiting Language Encoding in Learning Multilingual Representations","date":"2021-02-16","arxiv_id":"2102.08357","n_code_links":1,"syntology":null},{"paper":"/paper/translational-equivariance-in-kernelizable","slug":"translational-equivariance-in-kernelizable","title":"Translational Equivariance in Kernelizable Attention","date":"2021-02-15","arxiv_id":"2102.07680","n_code_links":1,"syntology":null},{"paper":null,"slug":"dancing-along-battery-enabling-transformer","title":"Dancing along Battery: Enabling Transformer with Run-time Reconfigurability on Mobile Devices","date":"2021-02-12","arxiv_id":"2102.06336","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-zero-shot-neural-machine","title":"Improving Zero-shot Neural Machine Translation on Language-specific Encoders-Decoders","date":"2021-02-12","arxiv_id":"2102.06578","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-inference-performance-of","title":"Optimizing Inference Performance of Transformers on CPUs","date":"2021-02-12","arxiv_id":"2102.06621","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-language-models-with-lstm-based","slug":"transformer-language-models-with-lstm-based","title":"Transformer Language Models with LSTM-based Cross-utterance Information Representation","date":"2021-02-12","arxiv_id":"2102.06474","n_code_links":1,"syntology":null},{"paper":"/paper/proof-artifact-co-training-for-theorem","slug":"proof-artifact-co-training-for-theorem","title":"Proof Artifact Co-training for Theorem Proving with Language Models","date":"2021-02-11","arxiv_id":"2102.06203","n_code_links":4,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["jasonrute/lean-proof-recording-public","jasonrute/lean_proof_recording","jesse-michael-han/lean-step-public"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"text-compression-aided-transformer-encoding","title":"Text Compression-aided Transformer Encoding","date":"2021-02-11","arxiv_id":"2102.05951","n_code_links":0,"syntology":null},{"paper":"/paper/nast-non-autoregressive-spatial-temporal","slug":"nast-non-autoregressive-spatial-temporal","title":"NAST: Non-Autoregressive Spatial-Temporal Transformer for Time Series Forecasting","date":"2021-02-10","arxiv_id":"2102.05624","n_code_links":1,"syntology":null},{"paper":null,"slug":"bayesian-transformer-language-models-for","title":"Bayesian Transformer Language Models for Speech Recognition","date":"2021-02-09","arxiv_id":"2102.04754","n_code_links":0,"syntology":null},{"paper":null,"slug":"conversational-query-rewriting-with-self","title":"Conversational Query Rewriting with Self-supervised Learning","date":"2021-02-09","arxiv_id":"2102.04708","n_code_links":0,"syntology":null},{"paper":null,"slug":"joint-intent-detection-and-slot-filling-with","title":"Joint Intent Detection and Slot Filling with Wheel-Graph Attention Networks","date":"2021-02-09","arxiv_id":"2102.04610","n_code_links":0,"syntology":null},{"paper":"/paper/point-cloud-transformers-applied-to-collider","slug":"point-cloud-transformers-applied-to-collider","title":"Point Cloud Transformers applied to Collider Physics","date":"2021-02-09","arxiv_id":"2102.05073","n_code_links":1,"syntology":null},{"paper":"/paper/colorization-transformer-1","slug":"colorization-transformer-1","title":"Colorization Transformer","date":"2021-02-08","arxiv_id":"2102.04432","n_code_links":2,"syntology":null},{"paper":"/paper/transreid-transformer-based-object-re","slug":"transreid-transformer-based-object-re","title":"TransReID: Transformer-based Object Re-Identification","date":"2021-02-08","arxiv_id":"2102.04378","n_code_links":4,"syntology":null},{"paper":"/paper/transunet-transformers-make-strong-encoders","slug":"transunet-transformers-make-strong-encoders","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","date":"2021-02-08","arxiv_id":"2102.04306","n_code_links":22,"syntology":{"ran":6,"of":7,"n_ran_checked":2,"n_instrument":4,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["Beckschen/TransUNet"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":null,"slug":"wake-word-detection-with-streaming","title":"Wake Word Detection with Streaming Transformers","date":"2021-02-08","arxiv_id":"2102.04488","n_code_links":0,"syntology":null},{"paper":"/paper/nystromformer-a-nystrom-based-algorithm-for","slug":"nystromformer-a-nystrom-based-algorithm-for","title":"Nyströmformer: A Nyström-Based Algorithm for Approximating Self-Attention","date":"2021-02-07","arxiv_id":"2102.03902","n_code_links":10,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["mlpen/Nystromformer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/baller2vec-a-multi-entity-transformer-for","slug":"baller2vec-a-multi-entity-transformer-for","title":"baller2vec: A Multi-Entity Transformer For Multi-Agent Spatiotemporal Modeling","date":"2021-02-05","arxiv_id":"2102.03291","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["airalcorn2/baller2vec"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/pipetransformer-automated-elastic-pipelining","slug":"pipetransformer-automated-elastic-pipelining","title":"PipeTransformer: Automated Elastic Pipelining for Distributed Training of Transformers","date":"2021-02-05","arxiv_id":"2102.03161","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Distributed-AI/PipeTransformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/vilt-vision-and-language-transformer-without","slug":"vilt-vision-and-language-transformer-without","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","date":"2021-02-05","arxiv_id":"2102.03334","n_code_links":6,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["dandelin/vilt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"mufasa-multimodal-fusion-architecture-search","title":"MUFASA: Multimodal Fusion Architecture Search for Electronic Health Records","date":"2021-02-03","arxiv_id":"2102.02340","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-transfer-learning-with-transformers","title":"Introduction to Neural Transfer Learning with Transformers for Social Science Text Analysis","date":"2021-02-03","arxiv_id":"2102.02111","n_code_links":0,"syntology":null},{"paper":"/paper/pitfalls-of-static-language-modelling","slug":"pitfalls-of-static-language-modelling","title":"Mind the Gap: Assessing Temporal Generalization in Neural Language Models","date":"2021-02-03","arxiv_id":"2102.01951","n_code_links":1,"syntology":null},{"paper":"/paper/relaxed-transformer-decoders-for-direct","slug":"relaxed-transformer-decoders-for-direct","title":"Relaxed Transformer Decoders for Direct Action Proposal Generation","date":"2021-02-03","arxiv_id":"2102.01894","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["MCG-NJU/RTD-Action"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-natural-and-controllable-cross","title":"Towards Natural and Controllable Cross-Lingual Voice Conversion Based on Neural TTS Model and Phonetic Posteriorgram","date":"2021-02-03","arxiv_id":"2102.01991","n_code_links":0,"syntology":null},{"paper":"/paper/automated-query-reformulation-for-efficient","slug":"automated-query-reformulation-for-efficient","title":"Automated Query Reformulation for Efficient Search based on Query Logs From Stack Overflow","date":"2021-02-01","arxiv_id":"2102.00826","n_code_links":1,"syntology":null},{"paper":null,"slug":"gtae-graph-transformer-based-auto-encoders","title":"GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfer","date":"2021-02-01","arxiv_id":"2102.00769","n_code_links":0,"syntology":null},{"paper":"/paper/computational-performance-predictions-for","slug":"computational-performance-predictions-for","title":"A Runtime-Based Computational Performance Predictor for Deep Neural Network Training","date":"2021-01-31","arxiv_id":"2102.00527","n_code_links":1,"syntology":null},{"paper":"/paper/short-text-clustering-with-transformers","slug":"short-text-clustering-with-transformers","title":"Short Text Clustering with Transformers","date":"2021-01-31","arxiv_id":"2102.00541","n_code_links":0,"syntology":null},{"paper":"/paper/transition-based-graph-decoder-for-neural","slug":"transition-based-graph-decoder-for-neural","title":"Enhancing the Transformer Decoder with Transition-based Syntax","date":"2021-01-29","arxiv_id":"2101.12640","n_code_links":1,"syntology":null},{"paper":null,"slug":"lstm-sakt-lstm-encoded-sakt-like-transformer","title":"LSTM-SAKT: LSTM-Encoded SAKT-like Transformer for Knowledge Tracing","date":"2021-01-28","arxiv_id":"2102.00845","n_code_links":0,"syntology":null},{"paper":"/paper/tokens-to-token-vit-training-vision","slug":"tokens-to-token-vit-training-vision","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","date":"2021-01-28","arxiv_id":"2101.11986","n_code_links":13,"syntology":{"ran":21,"of":26,"n_ran_checked":21,"n_instrument":0,"unverified":5,"pointer_only":8,"phrase":"21 ran (of which 16 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 0 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["yitu-opensource/T2T-ViT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"an-explainable-transformer-based-deep","title":"An explainable Transformer-based deep learning model for the prediction of incident heart failure","date":"2021-01-27","arxiv_id":"2101.11359","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-multi-task-multi-lingual-learning","slug":"exploring-multi-task-multi-lingual-learning","title":"Exploring multi-task multi-lingual learning of transformer models for hate speech and offensive speech identification in social media","date":"2021-01-27","arxiv_id":"2101.11155","n_code_links":1,"syntology":null},{"paper":null,"slug":"spatial-channel-transformer-network-for","title":"Spatial-Channel Transformer Network for Trajectory Prediction on the Traffic Scenes","date":"2021-01-27","arxiv_id":"2101.11472","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-can-reflect-syntactic-structure-if","title":"Attention Can Reflect Syntactic Structure (If You Let It)","date":"2021-01-26","arxiv_id":"2101.10927","n_code_links":0,"syntology":null},{"paper":null,"slug":"cptr-full-transformer-network-for-image","title":"CPTR: Full Transformer Network for Image Captioning","date":"2021-01-26","arxiv_id":"2101.10804","n_code_links":0,"syntology":null},{"paper":null,"slug":"randomized-deep-structured-prediction-for","title":"Randomized Deep Structured Prediction for Discourse-Level Processing","date":"2021-01-25","arxiv_id":"2101.10435","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-task-time-series-forecasting-with","title":"Multi-Task Time Series Forecasting With Shared Attention","date":"2021-01-24","arxiv_id":"2101.09645","n_code_links":0,"syntology":null},{"paper":"/paper/towards-a-better-integration-of-fuzzy-matches","slug":"towards-a-better-integration-of-fuzzy-matches","title":"Towards a Better Integration of Fuzzy Matches in Neural Machine Translation through Data Augmentation","date":"2021-01-24","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"enriching-non-autoregressive-transformer-with","title":"Enriching Non-Autoregressive Transformer with Syntactic and SemanticStructures for Neural Machine Translation","date":"2021-01-22","arxiv_id":"2101.08942","n_code_links":0,"syntology":null},{"paper":"/paper/activity-graph-transformer-for-temporal","slug":"activity-graph-transformer-for-temporal","title":"Activity Graph Transformer for Temporal Action Localization","date":"2021-01-21","arxiv_id":"2101.08540","n_code_links":0,"syntology":null},{"paper":"/paper/daf-re-a-challenging-crowd-sourced-large","slug":"daf-re-a-challenging-crowd-sourced-large","title":"DAF:re: A Challenging, Crowd-Sourced, Large-Scale, Long-Tailed Dataset For Anime Character Recognition","date":"2021-01-21","arxiv_id":"2101.08674","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["arkel23/animesion"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/evaluating-multilingual-text-encoders-for","slug":"evaluating-multilingual-text-encoders-for","title":"Evaluating Multilingual Text Encoders for Unsupervised Cross-Lingual Retrieval","date":"2021-01-21","arxiv_id":"2101.08370","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rlitschk/EncoderCLIR"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/learn-to-dance-with-aist-music-conditioned-3d","slug":"learn-to-dance-with-aist-music-conditioned-3d","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","date":"2021-01-21","arxiv_id":"2101.08779","n_code_links":1,"syntology":null},{"paper":null,"slug":"active-learning-for-sequence-tagging-with","title":"Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates","date":"2021-01-20","arxiv_id":"2101.08133","n_code_links":0,"syntology":null},{"paper":"/paper/open-domain-conversational-search-assistant","slug":"open-domain-conversational-search-assistant","title":"Open-Domain Conversational Search Assistant with Transformers","date":"2021-01-20","arxiv_id":"2101.08197","n_code_links":1,"syntology":null},{"paper":"/paper/pgt-pseudo-relevance-feedback-using-a-graph","slug":"pgt-pseudo-relevance-feedback-using-a-graph","title":"PGT: Pseudo Relevance Feedback Using a Graph-Based Transformer","date":"2021-01-20","arxiv_id":"2101.07918","n_code_links":1,"syntology":null}],"record_sha256":"ebac9d47d6c952d3cad562db5facb99c3c3e5a92ff78e3e2dfcf37bdb40cbe57","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}