{"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/216","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":216,"pages_in_order":250,"rows_per_page":100,"rows":[21501,21600],"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/215","next":"/method/layer-normalization/papers/217","papers":[{"paper":null,"slug":"misspelling-correction-with-pre-trained","title":"Misspelling Correction with Pre-trained Contextual Language Model","date":"2021-01-08","arxiv_id":"2101.03204","n_code_links":0,"syntology":null},{"paper":null,"slug":"applying-transfer-learning-for-improving","title":"Applying Transfer Learning for Improving Domain-Specific Search Experience Using Query to Question Similarity","date":"2021-01-07","arxiv_id":"2101.02351","n_code_links":0,"syntology":null},{"paper":"/paper/compound-word-transformer-learning-to-compose","slug":"compound-word-transformer-learning-to-compose","title":"Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs","date":"2021-01-07","arxiv_id":"2101.02402","n_code_links":5,"syntology":{"ran":4,"of":9,"n_ran_checked":4,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"4 ran (of which 0 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) · 5 unverified","official":{"repos":["YatingMusic/compound-word-transformer"],"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/exploring-text-transformers-in-aaai-2021","slug":"exploring-text-transformers-in-aaai-2021","title":"Exploring Text-transformers in AAAI 2021 Shared Task: COVID-19 Fake News Detection in English","date":"2021-01-07","arxiv_id":"2101.02359","n_code_links":1,"syntology":null},{"paper":null,"slug":"homonym-identification-using-bert-using-a","title":"Homonym Identification using BERT -- Using a Clustering Approach","date":"2021-01-07","arxiv_id":"2101.02398","n_code_links":0,"syntology":null},{"paper":"/paper/trackformer-multi-object-tracking-with","slug":"trackformer-multi-object-tracking-with","title":"TrackFormer: Multi-Object Tracking with Transformers","date":"2021-01-07","arxiv_id":"2101.02702","n_code_links":2,"syntology":null},{"paper":"/paper/transformer-based-approach-towards-music","slug":"transformer-based-approach-towards-music","title":"Transformer-based approach towards music emotion recognition from lyrics","date":"2021-01-06","arxiv_id":"2101.02051","n_code_links":1,"syntology":null},{"paper":"/paper/autodropout-learning-dropout-patterns-to","slug":"autodropout-learning-dropout-patterns-to","title":"AutoDropout: Learning Dropout Patterns to Regularize Deep Networks","date":"2021-01-05","arxiv_id":"2101.01761","n_code_links":1,"syntology":null},{"paper":null,"slug":"covid-19-comparative-analysis-of-methods-for","title":"COVID-19: Comparative Analysis of Methods for Identifying Articles Related to Therapeutics and Vaccines without Using Labeled Data","date":"2021-01-05","arxiv_id":"2101.02017","n_code_links":0,"syntology":null},{"paper":"/paper/i-bert-integer-only-bert-quantization","slug":"i-bert-integer-only-bert-quantization","title":"I-BERT: Integer-only BERT Quantization","date":"2021-01-05","arxiv_id":"2101.01321","n_code_links":7,"syntology":null},{"paper":"/paper/improving-reference-mining-in-patents-with","slug":"improving-reference-mining-in-patents-with","title":"Improving reference mining in patents with BERT","date":"2021-01-04","arxiv_id":"2101.01039","n_code_links":1,"syntology":null},{"paper":"/paper/transformers-and-transfer-learning-for","slug":"transformers-and-transfer-learning-for","title":"Improving Portuguese Semantic Role Labeling with Transformers and Transfer Learning","date":"2021-01-04","arxiv_id":"2101.01213","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformers-in-vision-a-survey","title":"Transformers in Vision: A Survey","date":"2021-01-04","arxiv_id":"2101.01169","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-bart-for-multiobjective-optimization-of","title":"Using BART to Perform Pareto Optimization and Quantify its Uncertainties","date":"2021-01-04","arxiv_id":"2101.02558","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-efficient-transformer-decoder-with","title":"An Efficient Transformer Decoder with Compressed Sub-layers","date":"2021-01-03","arxiv_id":"2101.00542","n_code_links":0,"syntology":null},{"paper":"/paper/a-robust-and-domain-adaptive-approach-for-low","slug":"a-robust-and-domain-adaptive-approach-for-low","title":"A Robust and Domain-Adaptive Approach for Low-Resource Named Entity Recognition","date":"2021-01-02","arxiv_id":"2101.00388","n_code_links":1,"syntology":null},{"paper":"/paper/cross-document-language-modeling","slug":"cross-document-language-modeling","title":"CDLM: Cross-Document Language Modeling","date":"2021-01-02","arxiv_id":"2101.00406","n_code_links":2,"syntology":null},{"paper":"/paper/end-to-end-training-of-neural-retrievers-for","slug":"end-to-end-training-of-neural-retrievers-for","title":"End-to-End Training of Neural Retrievers for Open-Domain Question Answering","date":"2021-01-02","arxiv_id":"2101.00408","n_code_links":2,"syntology":null},{"paper":"/paper/improving-sequence-to-sequence-pre-training","slug":"improving-sequence-to-sequence-pre-training","title":"Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting","date":"2021-01-02","arxiv_id":"2101.00416","n_code_links":1,"syntology":null},{"paper":"/paper/km-bart-knowledge-enhanced-multimodal-bart","slug":"km-bart-knowledge-enhanced-multimodal-bart","title":"KM-BART: Knowledge Enhanced Multimodal BART for Visual Commonsense Generation","date":"2021-01-02","arxiv_id":"2101.00419","n_code_links":1,"syntology":null},{"paper":null,"slug":"lex-bert-enhancing-bert-based-ner-with","title":"Lex-BERT: Enhancing BERT based NER with lexicons","date":"2021-01-02","arxiv_id":"2101.00396","n_code_links":0,"syntology":null},{"paper":"/paper/superbizarre-is-not-superb-improving-bert-s","slug":"superbizarre-is-not-superb-improving-bert-s","title":"Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex Words","date":"2021-01-02","arxiv_id":"2101.00403","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 1 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) · 0 unverified","official":{"repos":["valentinhofmann/superbizarre"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"what-all-do-audio-transformer-models-hear","title":"What all do audio transformer models hear? Probing Acoustic Representations for Language Delivery and its Structure","date":"2021-01-02","arxiv_id":"2101.00387","n_code_links":0,"syntology":null},{"paper":"/paper/zero-shot-learning-by-generating-task","slug":"zero-shot-learning-by-generating-task","title":"Learning to Generate Task-Specific Adapters from Task Description","date":"2021-01-02","arxiv_id":"2101.00420","n_code_links":1,"syntology":null},{"paper":null,"slug":"adding-recurrence-to-pretrained-transformers-1","title":"Adding Recurrence to Pretrained Transformers","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"analogical-reasoning-for-visually-grounded-1","title":"Analogical Reasoning for Visually Grounded Compositional Generalization","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ariel-volume-coding-for-sentence-generation-1","title":"AriEL: Volume Coding for Sentence Generation Comparisons","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-is-not-enough-mitigating-the","title":"Attention Is Not Enough: Mitigating the Distribution Discrepancy in Asynchronous Multimodal Sequence Fusion","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"block-skim-transformer-for-efficient-question","title":"Block Skim Transformer for Efficient Question Answering","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bros-a-pre-trained-language-model-for","title":"BROS: A Pre-trained Language Model for Understanding Texts in Document","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cluster-former-clustering-based-sparse-1","title":"Cluster-Former: Clustering-based Sparse Transformer for Question Answering","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cluster-tune-enhance-bert-performance-in-low","title":"Cluster & Tune: Enhance BERT Performance in Low Resource Text Classification","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/crackformer-transformer-network-for-fine","slug":"crackformer-transformer-network-for-fine","title":"CrackFormer: Transformer Network for Fine-Grained Crack Detection","date":"2021-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"cross-probe-bert-for-efficient-and-effective","title":"Cross-Probe BERT for Efficient and Effective Cross-Modal Search","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dact-bert-increasing-the-efficiency-and","title":"DACT-BERT: Increasing the efficiency and interpretability of BERT by using adaptive computation time.","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"data-aware-low-rank-compression-for-large-nlp","title":"Data-aware Low-Rank Compression for Large NLP Models","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-proteins-using-a-triplet-bert","title":"Deep Learning Proteins using a Triplet-BERT network","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/deep-representational-re-tuning-using","slug":"deep-representational-re-tuning-using","title":"Deep Representational Re-tuning using Contrastive Tension","date":"2021-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"discovering-human-interactions-with-large","title":"Discovering Human Interactions With Large-Vocabulary Objects via Query and Multi-Scale Detection","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"do-transformers-understand-polynomial","title":"Do Transformers Understand Polynomial Simplification?","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"domain-slot-relationship-modeling-using-a-pre","title":"Domain-slot Relationship Modeling using a Pre-trained Language Encoder for Multi-Domain Dialogue State Tracking","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-detr-end-to-end-object-detection-with","title":"Dynamic DETR: End-to-End Object Detection With Dynamic Attention","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"erasure-for-advancing-dynamic-self-supervised","title":"Erasure for Advancing: Dynamic Self-Supervised Learning for Commonsense Reasoning","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/event-based-video-reconstruction-using","slug":"event-based-video-reconstruction-using","title":"Event-Based Video Reconstruction Using Transformer","date":"2021-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-routing-strategies-for-multilingual","title":"Exploring Routing Strategies for Multilingual Mixture-of-Experts Models","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-vulnerabilities-of-bert-based-apis","title":"EXPLORING VULNERABILITIES OF BERT-BASED APIS","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"frequency-aware-spatiotemporal-transformers","title":"Frequency-Aware Spatiotemporal Transformers for Video Inpainting Detection","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"generalizing-tree-models-for-improving","title":"Generalizing Tree Models for Improving Prediction Accuracy","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"high-performance-discriminative-tracking-with","title":"High-Performance Discriminative Tracking With Transformers","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"how-multipurpose-are-language-models","title":"How Multipurpose Are Language Models?","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hypergrid-transformers-towards-a-single-model","title":"HyperGrid Transformers: Towards A Single Model for Multiple Tasks","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/image-harmonization-with-transformer","slug":"image-harmonization-with-transformer","title":"Image Harmonization With Transformer","date":"2021-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-generalizability-of-protein","title":"Improving Generalizability of Protein Sequence Models via Data Augmentations","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-machine-translation-by-searching","title":"Improving Machine Translation by Searching Skip Connections Efficiently","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"isotropy-in-the-contextual-embedding-space","title":"Isotropy in the Contextual Embedding Space: Clusters and Manifolds","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ketg-a-knowledge-enhanced-text-generation","title":"KETG: A Knowledge Enhanced Text Generation Framework","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"long-range-arena-a-benchmark-for-efficient","title":"Long Range Arena : A Benchmark for Efficient Transformers","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"memory-representation-in-transformer","title":"Memory Representation in Transformer","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"modelling-drug-target-binding-affinity-using","title":"Modelling Drug-Target Binding Affinity using a BERT based Graph Neural network","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-span-question-answering-using-span","title":"MULTI-SPAN QUESTION ANSWERING USING SPAN-IMAGE NETWORK","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-view-3d-reconstruction-with","title":"Multi-View 3D Reconstruction With Transformers","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-co-attention-transformer-for","slug":"multimodal-co-attention-transformer-for","title":"Multimodal Co-Attention Transformer for Survival Prediction in Gigapixel Whole Slide Images","date":"2021-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"non-iterative-parallel-text-generation-via","title":"Non-iterative Parallel Text Generation via Glancing Transformer","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/on-explaining-your-explanations-of-bert-an","slug":"on-explaining-your-explanations-of-bert-an","title":"On Explaining Your Explanations of BERT: An Empirical Study with Sequence Classification","date":"2021-01-01","arxiv_id":"2101.00196","n_code_links":2,"syntology":null},{"paper":null,"slug":"on-position-embeddings-in-bert","title":"On Position Embeddings in BERT","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"parameterization-of-hypercomplex","title":"Parameterization of Hypercomplex Multiplications","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/phrasetransformer-self-attention-using-local","slug":"phrasetransformer-self-attention-using-local","title":"PhraseTransformer: Self-Attention using Local Context for Semantic Parsing","date":"2021-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/polyjuice-automated-general-purpose","slug":"polyjuice-automated-general-purpose","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","date":"2021-01-01","arxiv_id":"2101.00288","n_code_links":1,"syntology":null},{"paper":null,"slug":"post-training-weighted-quantization-of-neural","title":"Post-Training Weighted Quantization of Neural Networks for Language Models","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"pre-training-text-to-text-transformers-to","title":"Pre-training Text-to-Text Transformers to Write and Reason with Concepts","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"predictive-attention-transformer-improving","title":"Predictive Attention Transformer: Improving Transformer with Attention Map Prediction","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/prefix-tuning-optimizing-continuous-prompts","slug":"prefix-tuning-optimizing-continuous-prompts","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","date":"2021-01-01","arxiv_id":"2101.00190","n_code_links":13,"syntology":{"ran":4,"of":6,"n_ran_checked":2,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["XiangLi1999/PrefixTuning"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"pretrain-knowledge-aware-language-models","title":"Pretrain Knowledge-Aware Language Models","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"representation-and-bias-in-multilingual-nlp","title":"Representation and Bias in Multilingual NLP: Insights from Controlled Experiments on Conditional Language Modeling","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"representational-correlates-of-hierarchical","title":"Representational correlates of hierarchical phrase structure in deep language models","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/scene-context-aware-salient-object-detection","slug":"scene-context-aware-salient-object-detection","title":"Scene Context-Aware Salient Object Detection","date":"2021-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"share-or-not-learning-to-schedule-language","title":"Share or Not? Learning to Schedule Language-Specific Capacity for Multilingual Translation","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"single-layers-of-attention-suffice-to-predict","title":"Single Layers of Attention Suffice to Predict Protein Contacts","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"skillbert-skilling-the-bert-to-classify","title":"SkillBERT: “Skilling” the BERT to classify skills!","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"speeding-up-deep-learning-training-by-sharing","title":"Speeding up Deep Learning Training by Sharing Weights and Then Unsharing","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/star-a-structure-aware-lightweight","slug":"star-a-structure-aware-lightweight","title":"STAR: A Structure-Aware Lightweight Transformer for Real-Time Image Enhancement","date":"2021-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/subformer-a-parameter-reduced-transformer","slug":"subformer-a-parameter-reduced-transformer","title":"Subformer: A Parameter Reduced Transformer","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/subformer-exploring-weight-sharing-for","slug":"subformer-exploring-weight-sharing-for","title":"Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers","date":"2021-01-01","arxiv_id":"2101.00234","n_code_links":1,"syntology":null},{"paper":null,"slug":"syntactic-relevance-xlnet-word-embedding","title":"Syntactic Relevance XLNet Word Embedding Generation in Low-Resource Machine Translation","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"synthesizer-rethinking-self-attention-for","title":"Synthesizer: Rethinking Self-Attention for Transformer Models","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"taking-notes-on-the-fly-helps-language-pre","title":"Taking Notes on the Fly Helps Language Pre-Training","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"task-agnostic-and-adaptive-size-bert","title":"Task-Agnostic and Adaptive-Size BERT Compression","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/towards-practical-second-order-optimization","slug":"towards-practical-second-order-optimization","title":"Towards Practical Second Order Optimization for Deep Learning","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"trans-caps-transformer-capsule-networks-with","title":"Trans-Caps: Transformer Capsule Networks with Self-attention Routing","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/transformer-based-automatic-covid-19-fake","slug":"transformer-based-automatic-covid-19-fake","title":"Transformer based Automatic COVID-19 Fake News Detection System","date":"2021-01-01","arxiv_id":"2101.00180","n_code_links":2,"syntology":null},{"paper":null,"slug":"transformer-protein-language-models-are","title":"Transformer protein language models are unsupervised structure learners","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-ql-a-step-towards-making","title":"Transformer-QL: A Step Towards Making Transformer Network Quadratically Large","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transformers-satisfy","title":"Transformers satisfy","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transforming-recurrent-neural-networks-with","title":"Transforming Recurrent Neural Networks with Attention and Fixed-point Equations","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/trar-routing-the-attention-spans-in","slug":"trar-routing-the-attention-spans-in","title":"TRAR: Routing the Attention Spans in Transformer for Visual Question Answering","date":"2021-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"u-bert-pre-training-user-representations-for","title":"U-BERT: Pre-training User Representations for Improved Recommendation","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"updet-universal-multi-agent-rl-via-policy","title":"UPDeT: Universal Multi-agent RL via Policy Decoupling with Transformers","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"userbert-self-supervised-user-representation","title":"UserBERT: Self-supervised User Representation Learning","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"visual-transformers-where-do-transformers","title":"Visual Transformers: Where Do Transformers Really Belong in Vision Models?","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/visualsparta-sparse-transformer-fragment","slug":"visualsparta-sparse-transformer-fragment","title":"VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-words","date":"2021-01-01","arxiv_id":"2101.00265","n_code_links":1,"syntology":null}],"record_sha256":"6ee46ff878a9aa89dbd44c6883f5ecce91801c678e8ffcf4028e4ec60d4fbcb0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}