{"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/layer-normalization/papers/192","list_of":"/method/layer-normalization","method":"Layer Normalization","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":192,"pages_in_order":250,"rows_per_page":100,"rows":[19101,19200],"of":24980,"counts":{"archive_papers_tagged":24980,"with_a_code_link":11273,"where_syntology_ran_a_sample":3471,"not_listed_spam_title":0,"listed":24980,"listed_where_code_ran":3471,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2923,"every_run_a_failure_of_syntologys_instrument":548,"listed_with_a_run_with_no_instrument_failure":2923,"listed_every_run_a_failure_of_syntologys_instrument":548,"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/layer-normalization","prev":"/method/layer-normalization/papers/191","next":"/method/layer-normalization/papers/193","papers":[{"paper":"/paper/transformers-generalize-deepsets-and-can-be","slug":"transformers-generalize-deepsets-and-can-be","title":"Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs","date":"2021-10-27","arxiv_id":"2110.14416","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["jw9730/hot"],"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":"vision-transformer-for-classification-of","title":"Vision Transformer for Classification of Breast Ultrasound Images","date":"2021-10-27","arxiv_id":"2110.14731","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-t-fool-me-adversarially-robust","title":"Can't Fool Me: Adversarially Robust Transformer for Video Understanding","date":"2021-10-26","arxiv_id":"2110.13950","n_code_links":0,"syntology":null},{"paper":null,"slug":"clauserec-a-clause-recommendation-framework","title":"CLAUSEREC: A Clause Recommendation Framework for AI-aided Contract Authoring","date":"2021-10-26","arxiv_id":"2110.15794","n_code_links":0,"syntology":null},{"paper":"/paper/geometric-transformer-for-end-to-end-molecule","slug":"geometric-transformer-for-end-to-end-molecule","title":"Geometric Transformer for End-to-End Molecule Properties Prediction","date":"2021-10-26","arxiv_id":"2110.13721","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yoniLc/GeometricTransformerMolecule"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/hierarchical-transformers-are-more-efficient","slug":"hierarchical-transformers-are-more-efficient","title":"Hierarchical Transformers Are More Efficient Language Models","date":"2021-10-26","arxiv_id":"2110.13711","n_code_links":3,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["google/trax"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"leveraging-local-temporal-information-for","title":"Leveraging Local Temporal Information for Multimodal Scene Classification","date":"2021-10-26","arxiv_id":"2110.13992","n_code_links":0,"syntology":null},{"paper":"/paper/post-processing-for-individual-fairness","slug":"post-processing-for-individual-fairness","title":"Post-processing for Individual Fairness","date":"2021-10-26","arxiv_id":"2110.13796","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"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":["felix-petersen/fairness-post-processing"],"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/s2s-ft-fine-tuning-pretrained-transformer","slug":"s2s-ft-fine-tuning-pretrained-transformer","title":"s2s-ft: Fine-Tuning Pretrained Transformer Encoders for Sequence-to-Sequence Learning","date":"2021-10-26","arxiv_id":"2110.13640","n_code_links":1,"syntology":null},{"paper":"/paper/tribert-full-body-human-centric-audio-visual","slug":"tribert-full-body-human-centric-audio-visual","title":"TriBERT: Full-body Human-centric Audio-visual Representation Learning for Visual Sound Separation","date":"2021-10-26","arxiv_id":"2110.13412","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["ubc-vision/tribert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/wavlm-large-scale-self-supervised-pre","slug":"wavlm-large-scale-self-supervised-pre","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","date":"2021-10-26","arxiv_id":"2110.13900","n_code_links":9,"syntology":null},{"paper":"/paper/actions-speak-louder-than-listening","slug":"actions-speak-louder-than-listening","title":"Actions Speak Louder than Listening: Evaluating Music Style Transfer based on Editing Experience","date":"2021-10-25","arxiv_id":"2110.12855","n_code_links":1,"syntology":null},{"paper":"/paper/doctr-document-image-transformer-for","slug":"doctr-document-image-transformer-for","title":"DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction","date":"2021-10-25","arxiv_id":"2110.12942","n_code_links":2,"syntology":null},{"paper":"/paper/fine-tuning-of-pre-trained-transformers-for","slug":"fine-tuning-of-pre-trained-transformers-for","title":"Fine-tuning of Pre-trained Transformers for Hate, Offensive, and Profane Content Detection in English and Marathi","date":"2021-10-25","arxiv_id":"2110.12687","n_code_links":1,"syntology":null},{"paper":null,"slug":"generating-artificial-texts-as-substitution","title":"Generating artificial texts as substitution or complement of training data","date":"2021-10-25","arxiv_id":"2110.13016","n_code_links":0,"syntology":null},{"paper":null,"slug":"gophormer-ego-graph-transformer-for-node","title":"Gophormer: Ego-Graph Transformer for Node Classification","date":"2021-10-25","arxiv_id":"2110.13094","n_code_links":0,"syntology":null},{"paper":"/paper/history-aware-multimodal-transformer-for","slug":"history-aware-multimodal-transformer-for","title":"History Aware Multimodal Transformer for Vision-and-Language Navigation","date":"2021-10-25","arxiv_id":"2110.13309","n_code_links":1,"syntology":{"ran":7,"of":15,"n_ran_checked":7,"n_instrument":0,"unverified":8,"pointer_only":0,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","official":null}},{"paper":"/paper/iconqa-a-new-benchmark-for-abstract-diagram","slug":"iconqa-a-new-benchmark-for-abstract-diagram","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","date":"2021-10-25","arxiv_id":"2110.13214","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["lupantech/iconqa"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/mvt-multi-view-vision-transformer-for-3d","slug":"mvt-multi-view-vision-transformer-for-3d","title":"MVT: Multi-view Vision Transformer for 3D Object Recognition","date":"2021-10-25","arxiv_id":"2110.13083","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["shanshuo/MVT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"revisiting-cnn-for-highly-inflected-bengali","title":"Paradigm Shift in Language Modeling: Revisiting CNN for Modeling Sanskrit Originated Bengali and Hindi Language","date":"2021-10-25","arxiv_id":"2110.13032","n_code_links":0,"syntology":null},{"paper":null,"slug":"stransgan-an-empirical-study-on-transformer-1","title":"The Nuts and Bolts of Adopting Transformer in GANs","date":"2021-10-25","arxiv_id":"2110.13107","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-source-separation-by-steering","slug":"unsupervised-source-separation-by-steering","title":"Unsupervised Source Separation By Steering Pretrained Music Models","date":"2021-10-25","arxiv_id":"2110.13071","n_code_links":1,"syntology":null},{"paper":"/paper/cvt-assd-convolutional-vision-transformer","slug":"cvt-assd-convolutional-vision-transformer","title":"CvT-ASSD: Convolutional vision-Transformer Based Attentive Single Shot MultiBox Detector","date":"2021-10-24","arxiv_id":"2110.12364","n_code_links":1,"syntology":null},{"paper":null,"slug":"hate-and-offensive-speech-detection-in-hindi","title":"Hate and Offensive Speech Detection in Hindi and Marathi","date":"2021-10-23","arxiv_id":"2110.12200","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-countable-armed-bandit-with-vanishing","title":"Bandits with Dynamic Arm-acquisition Costs","date":"2021-10-23","arxiv_id":"2110.12118","n_code_links":0,"syntology":null},{"paper":"/paper/double-trouble-how-to-not-explain-a-text","slug":"double-trouble-how-to-not-explain-a-text","title":"Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?","date":"2021-10-22","arxiv_id":"2110.11929","n_code_links":1,"syntology":null},{"paper":"/paper/learning-text-image-joint-embedding-for","slug":"learning-text-image-joint-embedding-for","title":"Learning Text-Image Joint Embedding for Efficient Cross-Modal Retrieval with Deep Feature Engineering","date":"2021-10-22","arxiv_id":"2110.11592","n_code_links":1,"syntology":null},{"paper":"/paper/3d-anas-v2-grafting-transformer-module-on","slug":"3d-anas-v2-grafting-transformer-module-on","title":"Grafting Transformer on Automatically Designed Convolutional Neural Network for Hyperspectral Image Classification","date":"2021-10-21","arxiv_id":"2110.11084","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-channel-attention-based-mlp-mixer-network","title":"A channel attention based MLP-Mixer network for motor imagery decoding with EEG","date":"2021-10-21","arxiv_id":"2110.10939","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-scale-invariant-ranking-function-for","title":"A scale invariant ranking function for learning-to-rank: a real-world use case","date":"2021-10-21","arxiv_id":"2110.11259","n_code_links":0,"syntology":null},{"paper":"/paper/cloob-modern-hopfield-networks-with-infoloob-1","slug":"cloob-modern-hopfield-networks-with-infoloob-1","title":"CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP","date":"2021-10-21","arxiv_id":"2110.11316","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":1,"n_instrument":6,"unverified":4,"pointer_only":4,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","official":{"repos":["ml-jku/cloob"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community","official"]}}},{"paper":"/paper/fast-model-editing-at-scale-1","slug":"fast-model-editing-at-scale-1","title":"Fast Model Editing at Scale","date":"2021-10-21","arxiv_id":"2110.11309","n_code_links":3,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["eric-mitchell/mend"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"modeling-performance-in-open-domain-dialogue","title":"Modeling Performance in Open-Domain Dialogue with PARADISE","date":"2021-10-21","arxiv_id":"2110.11164","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-acceleration-with-dynamic-sparse","title":"Transformer Acceleration with Dynamic Sparse Attention","date":"2021-10-21","arxiv_id":"2110.11299","n_code_links":0,"syntology":null},{"paper":null,"slug":"vis-top-visual-transformer-overlay-processor","title":"Vis-TOP: Visual Transformer Overlay Processor","date":"2021-10-21","arxiv_id":"2110.10957","n_code_links":0,"syntology":null},{"paper":null,"slug":"after-unet-axial-fusion-transformer-unet-for","title":"AFTer-UNet: Axial Fusion Transformer UNet for Medical Image Segmentation","date":"2021-10-20","arxiv_id":"2110.10403","n_code_links":0,"syntology":null},{"paper":"/paper/aniformer-data-driven-3d-animation-with","slug":"aniformer-data-driven-3d-animation-with","title":"AniFormer: Data-driven 3D Animation with Transformer","date":"2021-10-20","arxiv_id":"2110.10533","n_code_links":1,"syntology":null},{"paper":null,"slug":"continual-learning-in-multilingual-nmt-via","title":"Continual Learning in Multilingual NMT via Language-Specific Embeddings","date":"2021-10-20","arxiv_id":"2110.10478","n_code_links":0,"syntology":null},{"paper":"/paper/distributionally-robust-classifiers-in","slug":"distributionally-robust-classifiers-in","title":"Distributionally Robust Classifiers in Sentiment Analysis","date":"2021-10-20","arxiv_id":"2110.10372","n_code_links":1,"syntology":null},{"paper":null,"slug":"esod-edge-based-task-scheduling-for-object","title":"ESOD:Edge-based Task Scheduling for Object Detection","date":"2021-10-20","arxiv_id":"2110.11342","n_code_links":0,"syntology":null},{"paper":"/paper/few-shot-temporal-action-localization-with","slug":"few-shot-temporal-action-localization-with","title":"Few-Shot Temporal Action Localization with Query Adaptive Transformer","date":"2021-10-20","arxiv_id":"2110.10552","n_code_links":1,"syntology":null},{"paper":null,"slug":"sea-graph-shell-attention-in-graph-neural","title":"SEA: Graph Shell Attention in Graph Neural Networks","date":"2021-10-20","arxiv_id":"2110.10674","n_code_links":0,"syntology":null},{"paper":null,"slug":"slam-a-unified-encoder-for-speech-and","title":"SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training","date":"2021-10-20","arxiv_id":"2110.10329","n_code_links":0,"syntology":null},{"paper":null,"slug":"toward-accurate-and-reliable-iris","title":"Toward Accurate and Reliable Iris Segmentation Using Uncertainty Learning","date":"2021-10-20","arxiv_id":"2110.10334","n_code_links":0,"syntology":null},{"paper":null,"slug":"vldeformer-learning-visual-semantic","title":"VLDeformer: Vision-Language Decomposed Transformer for Fast Cross-Modal Retrieval","date":"2021-10-20","arxiv_id":"2110.11338","n_code_links":0,"syntology":null},{"paper":"/paper/a-picture-is-worth-a-thousand-words-a-unified","slug":"a-picture-is-worth-a-thousand-words-a-unified","title":"A Picture is Worth a Thousand Words: A Unified System for Diverse Captions and Rich Images Generation","date":"2021-10-19","arxiv_id":"2110.09756","n_code_links":1,"syntology":null},{"paper":null,"slug":"accelerating-framework-of-transformer-by","title":"Accelerating Framework of Transformer by Hardware Design and Model Compression Co-Optimization","date":"2021-10-19","arxiv_id":"2110.10030","n_code_links":0,"syntology":null},{"paper":null,"slug":"bilateral-vit-for-robust-fovea-localization","title":"Bilateral-ViT for Robust Fovea Localization","date":"2021-10-19","arxiv_id":"2110.09860","n_code_links":0,"syntology":null},{"paper":"/paper/cascaded-cross-mlp-mixer-gans-for-cross-view","slug":"cascaded-cross-mlp-mixer-gans-for-cross-view","title":"Cascaded Cross MLP-Mixer GANs for Cross-View Image Translation","date":"2021-10-19","arxiv_id":"2110.10183","n_code_links":1,"syntology":null},{"paper":null,"slug":"detectornet-transformer-enhanced-spatial","title":"DetectorNet: Transformer-enhanced Spatial Temporal Graph Neural Network for Traffic Prediction","date":"2021-10-19","arxiv_id":"2111.00869","n_code_links":0,"syntology":null},{"paper":"/paper/ensemble-albert-on-squad-2-0","slug":"ensemble-albert-on-squad-2-0","title":"Ensemble ALBERT on SQuAD 2.0","date":"2021-10-19","arxiv_id":"2110.09665","n_code_links":1,"syntology":null},{"paper":"/paper/generating-symbolic-reasoning-problems-with-1","slug":"generating-symbolic-reasoning-problems-with-1","title":"Generating Symbolic Reasoning Problems with Transformer GANs","date":"2021-10-19","arxiv_id":"2110.10054","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":6,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["reactive-systems/TGAN-SR"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"inductive-biases-and-variable-creation-in-1","title":"Inductive Biases and Variable Creation in Self-Attention Mechanisms","date":"2021-10-19","arxiv_id":"2110.10090","n_code_links":0,"syntology":null},{"paper":"/paper/permutation-invariant-graph-to-sequence-model-1","slug":"permutation-invariant-graph-to-sequence-model-1","title":"Permutation invariant graph-to-sequence model for template-free retrosynthesis and reaction prediction","date":"2021-10-19","arxiv_id":"2110.09681","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["coleygroup/graph2smiles"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"risks-of-ai-foundation-models-in-education","title":"Risks of AI Foundation Models in Education","date":"2021-10-19","arxiv_id":"2110.10024","n_code_links":0,"syntology":null},{"paper":null,"slug":"spatial-temporal-transformer-for-3d-point","title":"Spatial-Temporal Transformer for 3D Point Cloud Sequences","date":"2021-10-19","arxiv_id":"2110.09783","n_code_links":0,"syntology":null},{"paper":"/paper/ssast-self-supervised-audio-spectrogram","slug":"ssast-self-supervised-audio-spectrogram","title":"SSAST: Self-Supervised Audio Spectrogram Transformer","date":"2021-10-19","arxiv_id":"2110.09784","n_code_links":3,"syntology":{"ran":13,"of":16,"n_ran_checked":13,"n_instrument":0,"unverified":3,"pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["YuanGongND/ssast"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/unifying-multimodal-transformer-for-bi","slug":"unifying-multimodal-transformer-for-bi","title":"Unifying Multimodal Transformer for Bi-directional Image and Text Generation","date":"2021-10-19","arxiv_id":"2110.09753","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["researchmm/generate-it"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-data-bootstrapping-recipe-for-low-resource","title":"A Data Bootstrapping Recipe for Low Resource Multilingual Relation Classification","date":"2021-10-18","arxiv_id":"2110.09570","n_code_links":0,"syntology":null},{"paper":null,"slug":"bermo-what-can-bert-learn-from-elmo-1","title":"BERMo: What can BERT learn from ELMo?","date":"2021-10-18","arxiv_id":"2110.15802","n_code_links":0,"syntology":null},{"paper":null,"slug":"ceasing-hate-withmoh-hate-speech-detection-in","title":"Ceasing hate withMoH: Hate Speech Detection in Hindi-English Code-Switched Language","date":"2021-10-18","arxiv_id":"2110.09393","n_code_links":0,"syntology":null},{"paper":"/paper/compositional-attention-disentangling-search-1","slug":"compositional-attention-disentangling-search-1","title":"Compositional Attention: Disentangling Search and Retrieval","date":"2021-10-18","arxiv_id":"2110.09419","n_code_links":3,"syntology":null},{"paper":null,"slug":"contextual-hate-speech-detection-in-code","title":"Contextual Hate Speech Detection in Code Mixed Text using Transformer Based Approaches","date":"2021-10-18","arxiv_id":"2110.09338","n_code_links":0,"syntology":null},{"paper":"/paper/hrformer-high-resolution-transformer-for","slug":"hrformer-high-resolution-transformer-for","title":"HRFormer: High-Resolution Transformer for Dense Prediction","date":"2021-10-18","arxiv_id":"2110.09408","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":7,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 7 samples that ran constructed an object rather than computing a result","official":{"repos":["HRNet/HRFormer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/memo-test-time-robustness-via-adaptation-and","slug":"memo-test-time-robustness-via-adaptation-and","title":"MEMO: Test Time Robustness via Adaptation and Augmentation","date":"2021-10-18","arxiv_id":"2110.09506","n_code_links":2,"syntology":{"ran":14,"of":18,"n_ran_checked":3,"n_instrument":11,"unverified":4,"pointer_only":15,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 11 where Syntology's instrument failed) · 4 unverified","official":{"repos":["zhangmarvin/memo"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]}}},{"paper":"/paper/normformer-improved-transformer-pretraining-1","slug":"normformer-improved-transformer-pretraining-1","title":"NormFormer: Improved Transformer Pretraining with Extra Normalization","date":"2021-10-18","arxiv_id":"2110.09456","n_code_links":1,"syntology":null},{"paper":"/paper/sentimentarcs-a-novel-method-for-self","slug":"sentimentarcs-a-novel-method-for-self","title":"SentimentArcs: A Novel Method for Self-Supervised Sentiment Analysis of Time Series Shows SOTA Transformers Can Struggle Finding Narrative Arcs","date":"2021-10-18","arxiv_id":"2110.09454","n_code_links":1,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["jon-chun/sentimentarcs_notebooks"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/sequential-modeling-with-multiple-attributes","slug":"sequential-modeling-with-multiple-attributes","title":"Sequential Modeling with Multiple Attributes for Watchlist Recommendation in E-Commerce","date":"2021-10-18","arxiv_id":"2110.11072","n_code_links":1,"syntology":null},{"paper":"/paper/tldr-twin-learning-for-dimensionality-1","slug":"tldr-twin-learning-for-dimensionality-1","title":"TLDR: Twin Learning for Dimensionality Reduction","date":"2021-10-18","arxiv_id":"2110.09455","n_code_links":1,"syntology":null},{"paper":null,"slug":"virapart-a-text-refinement-framework-for-asr","title":"ViraPart: A Text Refinement Framework for Automatic Speech Recognition and Natural Language Processing Tasks in Persian","date":"2021-10-18","arxiv_id":"2110.09086","n_code_links":0,"syntology":null},{"paper":"/paper/3d-retr-end-to-end-single-and-multi-view-3d","slug":"3d-retr-end-to-end-single-and-multi-view-3d","title":"3D-RETR: End-to-End Single and Multi-View 3D Reconstruction with Transformers","date":"2021-10-17","arxiv_id":"2110.08861","n_code_links":1,"syntology":null},{"paper":null,"slug":"cae-transformer-transformer-based-model-to","title":"CAE-Transformer: Transformer-based Model to Predict Invasiveness of Lung Adenocarcinoma Subsolid Nodules from Non-thin Section 3D CT Scans","date":"2021-10-17","arxiv_id":"2110.08721","n_code_links":0,"syntology":null},{"paper":"/paper/illiterate-dall-cdot-e-learns-to-compose-1","slug":"illiterate-dall-cdot-e-learns-to-compose-1","title":"Illiterate DALL-E Learns to Compose","date":"2021-10-17","arxiv_id":"2110.11405","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["singhgautam/slate"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"reminding-the-incremental-language-model-via","title":"Reminding the Incremental Language Model via Data-Free Self-Distillation","date":"2021-10-17","arxiv_id":"2110.08745","n_code_links":0,"syntology":null},{"paper":"/paper/siamese-transformer-pyramid-networks-for-real","slug":"siamese-transformer-pyramid-networks-for-real","title":"Siamese Transformer Pyramid Networks for Real-Time UAV Tracking","date":"2021-10-17","arxiv_id":"2110.08822","n_code_links":1,"syntology":null},{"paper":"/paper/taming-visually-guided-sound-generation","slug":"taming-visually-guided-sound-generation","title":"Taming Visually Guided Sound Generation","date":"2021-10-17","arxiv_id":"2110.08791","n_code_links":3,"syntology":{"ran":7,"of":7,"n_ran_checked":6,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["v-iashin/SpecVQGAN"],"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":["listed","official"]}}},{"paper":"/paper/a-good-prompt-is-worth-millions-of-parameters","slug":"a-good-prompt-is-worth-millions-of-parameters","title":"A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models","date":"2021-10-16","arxiv_id":"2110.08484","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-short-study-on-compressing-decoder-based","title":"A Short Study on Compressing Decoder-Based Language Models","date":"2021-10-16","arxiv_id":"2110.08460","n_code_links":0,"syntology":null},{"paper":null,"slug":"alleviating-the-inequality-of-attention-heads-1","title":"Alleviating the Inequality of Attention Heads for Neural Machine Translation","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/asformer-transformer-for-action-segmentation","slug":"asformer-transformer-for-action-segmentation","title":"ASFormer: Transformer for Action Segmentation","date":"2021-10-16","arxiv_id":"2110.08568","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 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","official":{"repos":["chinayi/asformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"attention-temperature-matters-in-abstractive-1","title":"Attention Temperature Matters in Abstractive Summarization Distillation","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bitfit-simple-parameter-efficient-fine-tuning-1","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"covid-19-detection-in-chest-x-ray-images-1","title":"COVID-19 Detection in Chest X-ray Images Using Swin-Transformer and Transformer in Transformer","date":"2021-10-16","arxiv_id":"2110.08427","n_code_links":0,"syntology":null},{"paper":null,"slug":"emotion-flip-reasoning-in-multiparty","title":"Emotion Flip Reasoning in Multiparty Conversations","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"emotion-style-transfer-with-a-specified","title":"Emotion Style Transfer with a Specified Intensity Using Deep Reinforcement Learning","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/enct5-fine-tuning-t5-encoder-for-non","slug":"enct5-fine-tuning-t5-encoder-for-non","title":"EncT5: A Framework for Fine-tuning T5 as Non-autoregressive Models","date":"2021-10-16","arxiv_id":"2110.08426","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluation-of-transfer-learning-for-polish","title":"Evaluation of Transfer Learning for Polish with a text-to-text model","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-transformer-networks-for-long","title":"Hierarchical Transformer Networks for Long-sequence and Multiple Clinical Documents Classification","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/hydra-a-system-for-large-multi-model-deep","slug":"hydra-a-system-for-large-multi-model-deep","title":"Hydra: A System for Large Multi-Model Deep Learning","date":"2021-10-16","arxiv_id":"2110.08633","n_code_links":1,"syntology":null},{"paper":null,"slug":"impli-investigating-nli-models-performance-on","title":"IMPLI: Investigating NLI Models' Performance on Figurative Language","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/improving-compositional-generalization-with","slug":"improving-compositional-generalization-with","title":"Improving Compositional Generalization with Self-Training for Data-to-Text Generation","date":"2021-10-16","arxiv_id":"2110.08467","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowledge-inheritance-for-pre-trained-1","title":"Knowledge Inheritance for Pre-trained Language Models","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-rich-representation-of-keyphrases","title":"Learning Rich Representation of Keyphrases from Text","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-acquire-knowledge-from-a-search","title":"Learning to Acquire Knowledge from a Search Engine for Dialogue Response Generation","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"models-in-a-spelling-bee-language-models-1","title":"Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-task-end-to-end-training-improves","title":"Multi-Task End-to-End Training Improves Conversational Recommendation","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ode-transformer-an-ordinary-differential-1","title":"ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/old-bert-new-tricks-artificial-language-1","slug":"old-bert-new-tricks-artificial-language-1","title":"Old BERT, New Tricks: Artificial Language Learning for Pre-Trained Language Models","date":"2021-10-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-current-state-of-reproducibility-and","title":"On the current state of reproducibility and reporting of uncertainty for Aspect-based Sentiment Analysis","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/on-the-robustness-of-reading-comprehension","slug":"on-the-robustness-of-reading-comprehension","title":"On the Robustness of Reading Comprehension Models to Entity Renaming","date":"2021-10-16","arxiv_id":"2110.08555","n_code_links":1,"syntology":null}],"record_sha256":"878697ad39b500339d49d9fc1a4ed5f587f17991765fe28957d16bf0e3e619ae","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}