{"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/linear-layer/papers/206","list_of":"/method/linear-layer","method":"Linear Layer","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":206,"pages_in_order":255,"rows_per_page":100,"rows":[20501,20600],"of":25421,"counts":{"archive_papers_tagged":25421,"with_a_code_link":11479,"where_syntology_ran_a_sample":3523,"not_listed_spam_title":0,"listed":25421,"listed_where_code_ran":3523,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2976,"every_run_a_failure_of_syntologys_instrument":547,"listed_with_a_run_with_no_instrument_failure":2976,"listed_every_run_a_failure_of_syntologys_instrument":547,"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/linear-layer","prev":"/method/linear-layer/papers/205","next":"/method/linear-layer/papers/207","papers":[{"paper":"/paper/improved-representation-learning-for-session","slug":"improved-representation-learning-for-session","title":"Introducing Self-Attention to Target Attentive Graph Neural Networks","date":"2021-07-04","arxiv_id":"2107.01516","n_code_links":1,"syntology":null},{"paper":"/paper/kaisa-an-adaptive-second-order-optimizer","slug":"kaisa-an-adaptive-second-order-optimizer","title":"KAISA: An Adaptive Second-Order Optimizer Framework for Deep Neural Networks","date":"2021-07-04","arxiv_id":"2107.01739","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["gpauloski/kfac_pytorch"],"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":"can-transformers-jump-around-right-in-natural","title":"Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN","date":"2021-07-03","arxiv_id":"2107.01366","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-vision-transformers-via-fine","slug":"efficient-vision-transformers-via-fine","title":"Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation","date":"2021-07-03","arxiv_id":"2107.01378","n_code_links":1,"syntology":null},{"paper":"/paper/supervised-off-policy-ranking","slug":"supervised-off-policy-ranking","title":"Supervised Off-Policy Ranking","date":"2021-07-03","arxiv_id":"2107.01360","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["SOPR-T/SOPR-T"],"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":null,"slug":"case-relation-transformer-a-crossmodal","title":"Case Relation Transformer: A Crossmodal Language Generation Model for Fetching Instructions","date":"2021-07-02","arxiv_id":"2107.00789","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-view-geo-localization-with-evolving","title":"Cross-view Geo-localization with Evolving Transformer","date":"2021-07-02","arxiv_id":"2107.00842","n_code_links":0,"syntology":null},{"paper":"/paper/he-thinks-he-knows-better-than-the-doctors","slug":"he-thinks-he-knows-better-than-the-doctors","title":"He Thinks He Knows Better than the Doctors: BERT for Event Factuality Fails on Pragmatics","date":"2021-07-02","arxiv_id":"2107.00807","n_code_links":1,"syntology":null},{"paper":null,"slug":"language-identification-of-hindi-english","title":"Language Identification of Hindi-English tweets using code-mixed BERT","date":"2021-07-02","arxiv_id":"2107.01202","n_code_links":0,"syntology":null},{"paper":"/paper/online-metro-origin-destination-prediction","slug":"online-metro-origin-destination-prediction","title":"Online Metro Origin-Destination Prediction via Heterogeneous Information Aggregation","date":"2021-07-02","arxiv_id":"2107.00946","n_code_links":1,"syntology":null},{"paper":"/paper/r2d2-recursive-transformer-based-on","slug":"r2d2-recursive-transformer-based-on","title":"R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling","date":"2021-07-02","arxiv_id":"2107.00967","n_code_links":1,"syntology":null},{"paper":"/paper/relaxed-attention-a-simple-method-to-boost","slug":"relaxed-attention-a-simple-method-to-boost","title":"Relaxed Attention: A Simple Method to Boost Performance of End-to-End Automatic Speech Recognition","date":"2021-07-02","arxiv_id":"2107.01275","n_code_links":1,"syntology":null},{"paper":null,"slug":"scarecrow-a-framework-for-scrutinizing","title":"Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Text","date":"2021-07-02","arxiv_id":"2107.01294","n_code_links":0,"syntology":null},{"paper":"/paper/solving-machine-learning-problems","slug":"solving-machine-learning-problems","title":"Solving Machine Learning Problems","date":"2021-07-02","arxiv_id":"2107.01238","n_code_links":1,"syntology":null},{"paper":null,"slug":"target-dependent-uniter-a-transformer-based","title":"Target-dependent UNITER: A Transformer-Based Multimodal Language Comprehension Model for Domestic Service Robots","date":"2021-07-02","arxiv_id":"2107.00811","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-f-a-transformer-network-with","title":"Transformer-F: A Transformer network with effective methods for learning universal sentence representation","date":"2021-07-02","arxiv_id":"2107.00653","n_code_links":0,"syntology":null},{"paper":"/paper/ultrasound-video-transformers-for-cardiac","slug":"ultrasound-video-transformers-for-cardiac","title":"Ultrasound Video Transformers for Cardiac Ejection Fraction Estimation","date":"2021-07-02","arxiv_id":"2107.00977","n_code_links":1,"syntology":null},{"paper":"/paper/utnet-a-hybrid-transformer-architecture-for","slug":"utnet-a-hybrid-transformer-architecture-for","title":"UTNet: A Hybrid Transformer Architecture for Medical Image Segmentation","date":"2021-07-02","arxiv_id":"2107.00781","n_code_links":1,"syntology":null},{"paper":null,"slug":"visual-relationship-forecasting-in-videos","title":"Visual Relationship Forecasting in Videos","date":"2021-07-02","arxiv_id":"2107.01181","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-primer-on-pretrained-multilingual-language","title":"A Primer on Pretrained Multilingual Language Models","date":"2021-07-01","arxiv_id":"2107.00676","n_code_links":0,"syntology":null},{"paper":"/paper/action-transformer-a-self-attention-model-for","slug":"action-transformer-a-self-attention-model-for","title":"Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition","date":"2021-07-01","arxiv_id":"2107.00606","n_code_links":4,"syntology":null},{"paper":"/paper/autoformer-searching-transformers-for-visual","slug":"autoformer-searching-transformers-for-visual","title":"AutoFormer: Searching Transformers for Visual Recognition","date":"2021-07-01","arxiv_id":"2107.00651","n_code_links":2,"syntology":null},{"paper":null,"slug":"cross-lingual-adaptation-for-type-inference","title":"Cross-Lingual Transfer Learning for Statistical Type Inference","date":"2021-07-01","arxiv_id":"2107.00157","n_code_links":0,"syntology":null},{"paper":"/paper/cswin-transformer-a-general-vision","slug":"cswin-transformer-a-general-vision","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","date":"2021-07-01","arxiv_id":"2107.00652","n_code_links":7,"syntology":{"ran":4,"of":6,"n_ran_checked":2,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["microsoft/CSWin-Transformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"elbert-fast-albert-with-confidence-window","title":"Elbert: Fast Albert with Confidence-Window Based Early Exit","date":"2021-07-01","arxiv_id":"2107.00175","n_code_links":0,"syntology":null},{"paper":"/paper/focal-self-attention-for-local-global","slug":"focal-self-attention-for-local-global","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","date":"2021-07-01","arxiv_id":"2107.00641","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":2,"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":["microsoft/Focal-Transformer"],"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","unlocated"]}}},{"paper":null,"slug":"glyphcrm-bidirectional-encoder-representation","title":"GlyphCRM: Bidirectional Encoder Representation for Chinese Character with its Glyph","date":"2021-07-01","arxiv_id":"2107.00395","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-domain-agnostic-and-specific","title":"Leveraging Domain Agnostic and Specific Knowledge for Acronym Disambiguation","date":"2021-07-01","arxiv_id":"2107.00316","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-graph-based-transformer-framework","slug":"multimodal-graph-based-transformer-framework","title":"Multimodal Graph-based Transformer Framework for Biomedical Relation Extraction","date":"2021-07-01","arxiv_id":"2107.00596","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-generative-model-for-raw-audio-using","title":"A Generative Model for Raw Audio Using Transformer Architectures","date":"2021-06-30","arxiv_id":"2106.16036","n_code_links":0,"syntology":null},{"paper":null,"slug":"autolaw-augmented-legal-reasoning-through","title":"AutoLAW: Augmented Legal Reasoning through Legal Precedent Prediction","date":"2021-06-30","arxiv_id":"2106.16034","n_code_links":0,"syntology":null},{"paper":"/paper/dual-aspect-self-attention-based-on","slug":"dual-aspect-self-attention-based-on","title":"Dual Aspect Self-Attention based on Transformer for Remaining Useful Life Prediction","date":"2021-06-30","arxiv_id":"2106.15842","n_code_links":1,"syntology":null},{"paper":null,"slug":"early-risk-detection-of-pathological-gambling","title":"Early Risk Detection of Pathological Gambling, Self-Harm and Depression Using BERT","date":"2021-06-30","arxiv_id":"2106.16175","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-factual-consistency-of-abstractive-1","title":"Improving Factual Consistency of Abstractive Summarization on Customer Feedback","date":"2021-06-30","arxiv_id":"2106.16188","n_code_links":0,"syntology":null},{"paper":"/paper/the-multiberts-bert-reproductions-for","slug":"the-multiberts-bert-reproductions-for","title":"The MultiBERTs: BERT Reproductions for Robustness Analysis","date":"2021-06-30","arxiv_id":"2106.16163","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-research/language"],"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"]}}},{"paper":"/paper/an-efficient-cervical-whole-slide-image","slug":"an-efficient-cervical-whole-slide-image","title":"An Efficient Cervical Whole Slide Image Analysis Framework Based on Multi-scale Semantic and Location Deep Features","date":"2021-06-29","arxiv_id":"2106.15113","n_code_links":1,"syntology":null},{"paper":"/paper/fastpitchformant-source-filter-based","slug":"fastpitchformant-source-filter-based","title":"FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis","date":"2021-06-29","arxiv_id":"2106.15123","n_code_links":1,"syntology":null},{"paper":"/paper/geometry-aware-transformer-for-molecular","slug":"geometry-aware-transformer-for-molecular","title":"GeoT: A Geometry-aware Transformer for Reliable Molecular Property Prediction and Chemically Interpretable Representation Learning","date":"2021-06-29","arxiv_id":"2106.15516","n_code_links":1,"syntology":null},{"paper":"/paper/hate-speech-detection-using-static-bert","slug":"hate-speech-detection-using-static-bert","title":"Hate speech detection using static BERT embeddings","date":"2021-06-29","arxiv_id":"2106.15537","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-context-aware-transformers-for","title":"Hierarchical Context-Aware Transformers for Non-Autoregressive Text to Speech","date":"2021-06-29","arxiv_id":"2106.15144","n_code_links":0,"syntology":null},{"paper":"/paper/looking-outside-the-window-wider-context","slug":"looking-outside-the-window-wider-context","title":"Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images","date":"2021-06-29","arxiv_id":"2106.15754","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-exit-vision-transformer-for-dynamic","title":"Multi-Exit Vision Transformer for Dynamic Inference","date":"2021-06-29","arxiv_id":"2106.15183","n_code_links":0,"syntology":null},{"paper":null,"slug":"new-arabic-medical-dataset-for-diseases","title":"New Arabic Medical Dataset for Diseases Classification","date":"2021-06-29","arxiv_id":"2106.15236","n_code_links":0,"syntology":null},{"paper":"/paper/packing-towards-2x-nlp-bert-acceleration","slug":"packing-towards-2x-nlp-bert-acceleration","title":"Efficient Sequence Packing without Cross-contamination: Accelerating Large Language Models without Impacting Performance","date":"2021-06-29","arxiv_id":"2107.02027","n_code_links":1,"syntology":null},{"paper":null,"slug":"rethinking-the-evaluation-of-neural-machine","title":"Digging Errors in NMT: Evaluating and Understanding Model Errors from Partial Hypothesis Space","date":"2021-06-29","arxiv_id":"2106.15217","n_code_links":0,"syntology":null},{"paper":"/paper/unified-questioner-transformer-for","slug":"unified-questioner-transformer-for","title":"Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialogue","date":"2021-06-29","arxiv_id":"2106.15550","n_code_links":1,"syntology":null},{"paper":"/paper/a-3d-cnn-network-with-bert-for-automatic","slug":"a-3d-cnn-network-with-bert-for-automatic","title":"A 3D CNN Network with BERT For Automatic COVID-19 Diagnosis From CT-Scan Images","date":"2021-06-28","arxiv_id":"2106.14403","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-knowledge-grounded-dialog-system-based-on","title":"A Knowledge-Grounded Dialog System Based on Pre-Trained Language Models","date":"2021-06-28","arxiv_id":"2106.14444","n_code_links":0,"syntology":null},{"paper":null,"slug":"complexity-based-partitioning-of-csfi-problem","title":"Complexity-based partitioning of CSFI problem instances with Transformers","date":"2021-06-28","arxiv_id":"2106.14481","n_code_links":0,"syntology":null},{"paper":null,"slug":"current-landscape-of-the-russian-sentiment","title":"Current Landscape of the Russian Sentiment Corpora","date":"2021-06-28","arxiv_id":"2106.14434","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-the-generalization-for-intent","title":"Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLU","date":"2021-06-28","arxiv_id":"2106.14464","n_code_links":0,"syntology":null},{"paper":"/paper/multi-compound-transformer-for-accurate","slug":"multi-compound-transformer-for-accurate","title":"Multi-Compound Transformer for Accurate Biomedical Image Segmentation","date":"2021-06-28","arxiv_id":"2106.14385","n_code_links":1,"syntology":null},{"paper":"/paper/r-drop-regularized-dropout-for-neural","slug":"r-drop-regularized-dropout-for-neural","title":"R-Drop: Regularized Dropout for Neural Networks","date":"2021-06-28","arxiv_id":"2106.14448","n_code_links":8,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"4 ran (of which 2 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) · 2 unverified","official":{"repos":["dropreg/R-Drop"],"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":"rethinking-token-mixing-mlp-for-mlp-based","title":"Rethinking Token-Mixing MLP for MLP-based Vision Backbone","date":"2021-06-28","arxiv_id":"2106.14882","n_code_links":0,"syntology":null},{"paper":"/paper/tent-tensorized-encoder-transformer-for","slug":"tent-tensorized-encoder-transformer-for","title":"TENT: Tensorized Encoder Transformer for Temperature Forecasting","date":"2021-06-28","arxiv_id":"2106.14742","n_code_links":1,"syntology":null},{"paper":null,"slug":"traditional-machine-learning-and-deep","title":"Traditional Machine Learning and Deep Learning Models for Argumentation Mining in Russian Texts","date":"2021-06-28","arxiv_id":"2106.14438","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-s-in-a-measurement-using-gpt-3-on","title":"What's in a Measurement? Using GPT-3 on SemEval 2021 Task 8 -- MeasEval","date":"2021-06-28","arxiv_id":"2106.14720","n_code_links":0,"syntology":null},{"paper":"/paper/a-closer-look-at-how-fine-tuning-changes-bert","slug":"a-closer-look-at-how-fine-tuning-changes-bert","title":"A Closer Look at How Fine-tuning Changes BERT","date":"2021-06-27","arxiv_id":"2106.14282","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":["utahnlp/BERT-fine-tuning-analysis"],"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":"a-reinforcement-learning-approach-for-4","title":"A Reinforcement Learning Approach for Sequential Spatial Transformer Networks","date":"2021-06-27","arxiv_id":"2106.14295","n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-based-presentation-creator-with-customized","title":"AI based Presentation Creator With Customized Audio Content Delivery","date":"2021-06-27","arxiv_id":"2106.14213","n_code_links":0,"syntology":null},{"paper":"/paper/mtrans-multi-modal-transformer-for","slug":"mtrans-multi-modal-transformer-for","title":"Multi-Modal Transformer for Accelerated MR Imaging","date":"2021-06-27","arxiv_id":"2106.14248","n_code_links":1,"syntology":null},{"paper":"/paper/power-law-graph-transformer-for-machine","slug":"power-law-graph-transformer-for-machine","title":"Power Law Graph Transformer for Machine Translation and Representation Learning","date":"2021-06-27","arxiv_id":"2107.02039","n_code_links":3,"syntology":null},{"paper":"/paper/symbolicgpt-a-generative-transformer-model","slug":"symbolicgpt-a-generative-transformer-model","title":"SymbolicGPT: A Generative Transformer Model for Symbolic Regression","date":"2021-06-27","arxiv_id":"2106.14131","n_code_links":2,"syntology":{"ran":9,"of":9,"n_ran_checked":8,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"9 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["git.uwaterloo.ca/data-analytics-lab/symbolicgpt2"],"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/wvoq-at-semeval-2021-task-6-bart-for-span","slug":"wvoq-at-semeval-2021-task-6-bart-for-span","title":"WVOQ at SemEval-2021 Task 6: BART for Span Detection and Classification","date":"2021-06-27","arxiv_id":"2107.05467","n_code_links":1,"syntology":null},{"paper":null,"slug":"answering-chinese-elementary-school-social","title":"Answering Chinese Elementary School Social Study Multiple Choice Questions","date":"2021-06-26","arxiv_id":"2107.02893","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-differential-privacy-and","slug":"benchmarking-differential-privacy-and","title":"Benchmarking Differential Privacy and Federated Learning for BERT Models","date":"2021-06-26","arxiv_id":"2106.13973","n_code_links":1,"syntology":null},{"paper":null,"slug":"low-precision-training-in-logarithmic-number","title":"LNS-Madam: Low-Precision Training in Logarithmic Number System using Multiplicative Weight Update","date":"2021-06-26","arxiv_id":"2106.13914","n_code_links":0,"syntology":null},{"paper":null,"slug":"offroadtranseg-semi-supervised-segmentation","title":"OffRoadTranSeg: Semi-Supervised Segmentation using Transformers on OffRoad environments","date":"2021-06-26","arxiv_id":"2106.13963","n_code_links":0,"syntology":null},{"paper":"/paper/spreadsheetcoder-formula-prediction-from-semi-1","slug":"spreadsheetcoder-formula-prediction-from-semi-1","title":"SpreadsheetCoder: Formula Prediction from Semi-structured Context","date":"2021-06-26","arxiv_id":"2106.15339","n_code_links":1,"syntology":null},{"paper":null,"slug":"toward-less-hidden-cost-of-code-completion","title":"Toward Less Hidden Cost of Code Completion with Acceptance and Ranking Models","date":"2021-06-26","arxiv_id":"2106.13928","n_code_links":0,"syntology":null},{"paper":"/paper/umic-an-unreferenced-metric-for-image","slug":"umic-an-unreferenced-metric-for-image","title":"UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning","date":"2021-06-26","arxiv_id":"2106.14019","n_code_links":1,"syntology":{"ran":7,"of":14,"n_ran_checked":7,"n_instrument":0,"unverified":7,"pointer_only":0,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","official":{"repos":["hwanheelee1993/UMIC"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":4,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-picture-may-be-worth-a-hundred-words-for","title":"A Picture May Be Worth a Hundred Words for Visual Question Answering","date":"2021-06-25","arxiv_id":"2106.13445","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapt-and-distill-developing-small-fast-and","title":"Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains","date":"2021-06-25","arxiv_id":"2106.13474","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-sample-replacements-for-electra","title":"Learning to Sample Replacements for ELECTRA Pre-Training","date":"2021-06-25","arxiv_id":"2106.13715","n_code_links":0,"syntology":null},{"paper":"/paper/np-draw-a-non-parametric-structured-latent","slug":"np-draw-a-non-parametric-structured-latent","title":"NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation","date":"2021-06-25","arxiv_id":"2106.13435","n_code_links":1,"syntology":null},{"paper":null,"slug":"privileged-zero-shot-automl","title":"Privileged Zero-Shot AutoML","date":"2021-06-25","arxiv_id":"2106.13743","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-inter-modality-visual-parsing-with","title":"Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training","date":"2021-06-25","arxiv_id":"2106.13488","n_code_links":0,"syntology":null},{"paper":"/paper/pvtv2-improved-baselines-with-pyramid-vision","slug":"pvtv2-improved-baselines-with-pyramid-vision","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","date":"2021-06-25","arxiv_id":"2106.13797","n_code_links":18,"syntology":null},{"paper":null,"slug":"to-the-point-efficient-3d-object-detection-in","title":"To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernels","date":"2021-06-25","arxiv_id":"2106.13381","n_code_links":0,"syntology":null},{"paper":"/paper/vision-transformer-architecture-search","slug":"vision-transformer-architecture-search","title":"ViTAS: Vision Transformer Architecture Search","date":"2021-06-25","arxiv_id":"2106.13700","n_code_links":1,"syntology":null},{"paper":"/paper/xl-sum-large-scale-multilingual-abstractive","slug":"xl-sum-large-scale-multilingual-abstractive","title":"XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages","date":"2021-06-25","arxiv_id":"2106.13822","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":3,"phrase":"2 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["csebuetnlp/xl-sum"],"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":null,"slug":"an-automated-knowledge-mining-and-document","title":"An Automated Knowledge Mining and Document Classification System with Multi-model Transfer Learning","date":"2021-06-24","arxiv_id":"2106.12744","n_code_links":0,"syntology":null},{"paper":null,"slug":"bidding-via-clustering-ads-intentions-an","title":"An Efficient Group-based Search Engine Marketing System for E-Commerce","date":"2021-06-24","arxiv_id":"2106.12700","n_code_links":0,"syntology":null},{"paper":null,"slug":"discovering-novel-drug-supplement","title":"Discovering novel drug-supplement interactions using a dietary supplements knowledge graph generated from the biomedical literature","date":"2021-06-24","arxiv_id":"2106.12741","n_code_links":0,"syntology":null},{"paper":"/paper/education-to-skill-mapping-using-hierarchical","slug":"education-to-skill-mapping-using-hierarchical","title":"Education-to-Skill Mapping Using Hierarchical Classification and Transformer Neural Network","date":"2021-06-24","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/exploring-corruption-robustness-inductive","slug":"exploring-corruption-robustness-inductive","title":"Exploring Corruption Robustness: Inductive Biases in Vision Transformers and MLP-Mixers","date":"2021-06-24","arxiv_id":"2106.13122","n_code_links":1,"syntology":null},{"paper":"/paper/learning-multiple-stock-trading-patterns-with","slug":"learning-multiple-stock-trading-patterns-with","title":"Learning Multiple Stock Trading Patterns with Temporal Routing Adaptor and Optimal Transport","date":"2021-06-24","arxiv_id":"2106.12950","n_code_links":1,"syntology":null},{"paper":null,"slug":"quantization-aware-training-ernie-and","title":"Quantization Aware Training, ERNIE and Kurtosis Regularizer: a short empirical study","date":"2021-06-24","arxiv_id":"2106.13035","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-topic-segmentation-of-meetings","slug":"unsupervised-topic-segmentation-of-meetings","title":"Unsupervised Topic Segmentation of Meetings with BERT Embeddings","date":"2021-06-24","arxiv_id":"2106.12978","n_code_links":2,"syntology":null},{"paper":"/paper/video-swin-transformer","slug":"video-swin-transformer","title":"Video Swin Transformer","date":"2021-06-24","arxiv_id":"2106.13230","n_code_links":15,"syntology":{"ran":19,"of":32,"n_ran_checked":14,"n_instrument":5,"unverified":13,"pointer_only":7,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified","official":{"repos":["SwinTransformer/Video-Swin-Transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"winner-team-mia-at-textvqa-challenge-2021","title":"Winner Team Mia at TextVQA Challenge 2021: Vision-and-Language Representation Learning with Pre-trained Sequence-to-Sequence Model","date":"2021-06-24","arxiv_id":"2106.15332","n_code_links":0,"syntology":null},{"paper":"/paper/you-are-allset-a-multiset-function-framework","slug":"you-are-allset-a-multiset-function-framework","title":"You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks","date":"2021-06-24","arxiv_id":"2106.13264","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":["jianhao2016/AllSet"],"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/charformer-fast-character-transformers-via","slug":"charformer-fast-character-transformers-via","title":"Charformer: Fast Character Transformers via Gradient-based Subword Tokenization","date":"2021-06-23","arxiv_id":"2106.12672","n_code_links":2,"syntology":{"ran":7,"of":10,"n_ran_checked":4,"n_instrument":3,"unverified":3,"pointer_only":0,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["google-research/google-research"],"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/classifying-textual-data-with-pre-trained","slug":"classifying-textual-data-with-pre-trained","title":"Classifying Textual Data with Pre-trained Vision Models through Transfer Learning and Data Transformations","date":"2021-06-23","arxiv_id":"2106.12479","n_code_links":1,"syntology":null},{"paper":"/paper/ia-red-2-interpretability-aware-redundancy","slug":"ia-red-2-interpretability-aware-redundancy","title":"IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers","date":"2021-06-23","arxiv_id":"2106.12620","n_code_links":0,"syntology":null},{"paper":"/paper/instance-based-vision-transformer-for","slug":"instance-based-vision-transformer-for","title":"Instance-based Vision Transformer for Subtyping of Papillary Renal Cell Carcinoma in Histopathological Image","date":"2021-06-23","arxiv_id":"2106.12265","n_code_links":1,"syntology":null},{"paper":"/paper/learnt-sparsity-for-effective-and","slug":"learnt-sparsity-for-effective-and","title":"Extractive Explanations for Interpretable Text Ranking","date":"2021-06-23","arxiv_id":"2106.12460","n_code_links":1,"syntology":null},{"paper":null,"slug":"stable-fast-and-accurate-kernelized-attention","title":"Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding","date":"2021-06-23","arxiv_id":"2106.12566","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-meets-convolution-a-bilateral","slug":"transformer-meets-convolution-a-bilateral","title":"Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Images","date":"2021-06-23","arxiv_id":"2106.12413","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-case-study-in-bootstrapping-ontology-graphs","title":"A Case Study in Bootstrapping Ontology Graphs from Textbooks","date":"2021-06-22","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"4d43fa799158c77cea18df391753c72e4204e200428f8fc07c241f07cd5b4c42","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}