{"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/dropout/papers/210","list_of":"/method/dropout","method":"Dropout","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":210,"pages_in_order":275,"rows_per_page":100,"rows":[20901,21000],"of":27472,"counts":{"archive_papers_tagged":27472,"with_a_code_link":12129,"where_syntology_ran_a_sample":3620,"not_listed_spam_title":0,"listed":27472,"listed_where_code_ran":3620,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3044,"every_run_a_failure_of_syntologys_instrument":576,"listed_with_a_run_with_no_instrument_failure":3044,"listed_every_run_a_failure_of_syntologys_instrument":576,"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/dropout","prev":"/method/dropout/papers/209","next":"/method/dropout/papers/211","papers":[{"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/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":null,"slug":"topological-semantic-mapping-by-consolidation","title":"Topological Semantic Mapping by Consolidation of Deep Visual Features","date":"2021-06-24","arxiv_id":"2106.12709","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/apnn-tc-accelerating-arbitrary-precision","slug":"apnn-tc-accelerating-arbitrary-precision","title":"APNN-TC: Accelerating Arbitrary Precision Neural Networks on Ampere GPU Tensor Cores","date":"2021-06-23","arxiv_id":"2106.12169","n_code_links":1,"syntology":null},{"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":"/paper/numerical-influence-of-relu-0-on","slug":"numerical-influence-of-relu-0-on","title":"Numerical influence of ReLU'(0) on backpropagation","date":"2021-06-23","arxiv_id":"2106.12915","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},{"paper":"/paper/a-comprehensive-exploration-of-pre-training","slug":"a-comprehensive-exploration-of-pre-training","title":"A Comprehensive Comparison of Pre-training Language Models","date":"2021-06-22","arxiv_id":"2106.11483","n_code_links":2,"syntology":null},{"paper":"/paper/bartscore-evaluating-generated-text-as-text","slug":"bartscore-evaluating-generated-text-as-text","title":"BARTScore: Evaluating Generated Text as Text Generation","date":"2021-06-22","arxiv_id":"2106.11520","n_code_links":3,"syntology":null},{"paper":"/paper/combining-analogy-with-language-models-for","slug":"combining-analogy-with-language-models-for","title":"Combining Analogy with Language Models for Knowledge Extraction","date":"2021-06-22","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/fine-tune-the-entire-rag-architecture","slug":"fine-tune-the-entire-rag-architecture","title":"Fine-tune the Entire RAG Architecture (including DPR retriever) for Question-Answering","date":"2021-06-22","arxiv_id":"2106.11517","n_code_links":2,"syntology":null},{"paper":"/paper/lv-bert-exploiting-layer-variety-for-bert","slug":"lv-bert-exploiting-layer-variety-for-bert","title":"LV-BERT: Exploiting Layer Variety for BERT","date":"2021-06-22","arxiv_id":"2106.11740","n_code_links":1,"syntology":null},{"paper":"/paper/one-shot-to-weakly-supervised-relation","slug":"one-shot-to-weakly-supervised-relation","title":"One-shot to Weakly-Supervised Relation Classification using Language Models","date":"2021-06-22","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/p2t-pyramid-pooling-transformer-for-scene","slug":"p2t-pyramid-pooling-transformer-for-scene","title":"P2T: Pyramid Pooling Transformer for Scene Understanding","date":"2021-06-22","arxiv_id":"2106.12011","n_code_links":4,"syntology":null},{"paper":"/paper/revisiting-deep-learning-models-for-tabular","slug":"revisiting-deep-learning-models-for-tabular","title":"Revisiting Deep Learning Models for Tabular Data","date":"2021-06-22","arxiv_id":"2106.11959","n_code_links":11,"syntology":{"ran":18,"of":22,"n_ran_checked":15,"n_instrument":3,"unverified":4,"pointer_only":1,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 1 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["yandex-research/tabular-dl-revisiting-models","Yura52/tabular-dl-revisiting-models"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"structured-in-space-randomized-in-time","title":"Structured in Space, Randomized in Time: Leveraging Dropout in RNNs for Efficient Training","date":"2021-06-22","arxiv_id":"2106.12089","n_code_links":0,"syntology":null},{"paper":null,"slug":"ad-text-classification-with-transformer-based","title":"Ad Text Classification with Transformer-Based Natural Language Processing Methods","date":"2021-06-21","arxiv_id":"2106.10899","n_code_links":0,"syntology":null},{"paper":null,"slug":"constructing-forest-biomass-prediction-maps","title":"On the potential of sequential and non-sequential regression models for Sentinel-1-based biomass prediction in Tanzanian miombo forests","date":"2021-06-21","arxiv_id":"2106.15020","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-models-in-detection-of-dietary","title":"Deep Learning Models in Detection of Dietary Supplement Adverse Event Signals from Twitter","date":"2021-06-21","arxiv_id":"2106.11403","n_code_links":0,"syntology":null},{"paper":null,"slug":"hi-behrt-hierarchical-transformer-based-model","title":"Hi-BEHRT: Hierarchical Transformer-based model for accurate prediction of clinical events using multimodal longitudinal electronic health records","date":"2021-06-21","arxiv_id":"2106.11360","n_code_links":0,"syntology":null},{"paper":"/paper/iterative-network-pruning-with-uncertainty","slug":"iterative-network-pruning-with-uncertainty","title":"Iterative Network Pruning with Uncertainty Regularization for Lifelong Sentiment Classification","date":"2021-06-21","arxiv_id":"2106.11197","n_code_links":1,"syntology":null},{"paper":null,"slug":"modetr-moving-object-detection-with","title":"MODETR: Moving Object Detection with Transformers","date":"2021-06-21","arxiv_id":"2106.11422","n_code_links":0,"syntology":null},{"paper":"/paper/pseudo-relevance-feedback-for-multiple","slug":"pseudo-relevance-feedback-for-multiple","title":"Pseudo-Relevance Feedback for Multiple Representation Dense Retrieval","date":"2021-06-21","arxiv_id":"2106.11251","n_code_links":3,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["terrierteam/pyterrier_colbert","cmacdonald/pyterrier_colbert"],"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":null,"slug":"tcic-theme-concepts-learning-cross-language","title":"TCIC: Theme Concepts Learning Cross Language and Vision for Image Captioning","date":"2021-06-21","arxiv_id":"2106.10936","n_code_links":0,"syntology":null},{"paper":"/paper/context-aware-legal-citation-recommendation","slug":"context-aware-legal-citation-recommendation","title":"Context-Aware Legal Citation Recommendation using Deep Learning","date":"2021-06-20","arxiv_id":"2106.10776","n_code_links":1,"syntology":null},{"paper":"/paper/cpm-2-large-scale-cost-effective-pre-trained","slug":"cpm-2-large-scale-cost-effective-pre-trained","title":"CPM-2: Large-scale Cost-effective Pre-trained Language Models","date":"2021-06-20","arxiv_id":"2106.10715","n_code_links":2,"syntology":null},{"paper":"/paper/solution-for-large-scale-long-tailed","slug":"solution-for-large-scale-long-tailed","title":"Solution for Large-scale Long-tailed Recognition with Noisy Labels","date":"2021-06-20","arxiv_id":"2106.10683","n_code_links":1,"syntology":null},{"paper":null,"slug":"adaptive-image-transformer-for-one-shot","title":"Adaptive Image Transformer for One-Shot Object Detection","date":"2021-06-19","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/clusformer-a-transformer-based-clustering","slug":"clusformer-a-transformer-based-clustering","title":"Clusformer: A Transformer Based Clustering Approach to Unsupervised Large-Scale Face and Visual Landmark Recognition","date":"2021-06-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/densely-connected-multi-dilated-convolutional","slug":"densely-connected-multi-dilated-convolutional","title":"Densely Connected Multi-Dilated Convolutional Networks for Dense Prediction Tasks","date":"2021-06-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/exploring-vision-transformers-for-fine","slug":"exploring-vision-transformers-for-fine","title":"Exploring Vision Transformers for Fine-grained Classification","date":"2021-06-19","arxiv_id":"2106.10587","n_code_links":1,"syntology":null},{"paper":null,"slug":"gaussian-context-transformer","title":"Gaussian Context Transformer","date":"2021-06-19","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-approach-to-detecting-symptoms-of","title":"Hybrid approach to detecting symptoms of depression in social media entries","date":"2021-06-19","arxiv_id":"2106.10485","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-compositional-generalization-in-1","title":"Improving Compositional Generalization in Classification Tasks via Structure Annotations","date":"2021-06-19","arxiv_id":"2106.10434","n_code_links":0,"syntology":null},{"paper":"/paper/jointgt-graph-text-joint-representation","slug":"jointgt-graph-text-joint-representation","title":"JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs","date":"2021-06-19","arxiv_id":"2106.10502","n_code_links":1,"syntology":null},{"paper":"/paper/point-4d-transformer-networks-for-spatio","slug":"point-4d-transformer-networks-for-spatio","title":"Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos","date":"2021-06-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/rstnet-captioning-with-adaptive-attention-on","slug":"rstnet-captioning-with-adaptive-attention-on","title":"RSTNet: Captioning With Adaptive Attention on Visual and Non-Visual Words","date":"2021-06-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"vln-bert-a-recurrent-vision-and-language-bert","title":"VLN BERT: A Recurrent Vision-and-Language BERT for Navigation","date":"2021-06-19","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/all-you-can-embed-natural-language-based","slug":"all-you-can-embed-natural-language-based","title":"All You Can Embed: Natural Language based Vehicle Retrieval with Spatio-Temporal Transformers","date":"2021-06-18","arxiv_id":"2106.10153","n_code_links":1,"syntology":null},{"paper":"/paper/anomaly-detection-in-dynamic-graphs-via","slug":"anomaly-detection-in-dynamic-graphs-via","title":"Anomaly Detection in Dynamic Graphs via Transformer","date":"2021-06-18","arxiv_id":"2106.09876","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":null}},{"paper":"/paper/bitfit-simple-parameter-efficient-fine-tuning","slug":"bitfit-simple-parameter-efficient-fine-tuning","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","date":"2021-06-18","arxiv_id":"2106.10199","n_code_links":6,"syntology":{"ran":4,"of":13,"n_ran_checked":3,"n_instrument":1,"unverified":9,"pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","official":{"repos":["benzakenelad/BitFit"],"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/end-to-end-temporal-action-detection-with","slug":"end-to-end-temporal-action-detection-with","title":"End-to-end Temporal Action Detection with Transformer","date":"2021-06-18","arxiv_id":"2106.10271","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"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) · 1 unverified","official":{"repos":["xlliu7/TadTR"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"graph-based-joint-pandemic-concern-and","title":"Graph-based Joint Pandemic Concern and Relation Extraction on Twitter","date":"2021-06-18","arxiv_id":"2106.09929","n_code_links":0,"syntology":null},{"paper":null,"slug":"process-for-adapting-language-models-to","title":"Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets","date":"2021-06-18","arxiv_id":"2106.10328","n_code_links":0,"syntology":null},{"paper":null,"slug":"recurrent-stacking-of-layers-in-neural","title":"Recurrent Stacking of Layers in Neural Networks: An Application to Neural Machine Translation","date":"2021-06-18","arxiv_id":"2106.10002","n_code_links":0,"syntology":null},{"paper":"/paper/dual-view-molecule-pre-training","slug":"dual-view-molecule-pre-training","title":"Dual-view Molecule Pre-training","date":"2021-06-17","arxiv_id":"2106.10234","n_code_links":1,"syntology":null},{"paper":"/paper/knowledgeable-or-educated-guess-revisiting","slug":"knowledgeable-or-educated-guess-revisiting","title":"Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases","date":"2021-06-17","arxiv_id":"2106.09231","n_code_links":1,"syntology":null},{"paper":"/paper/large-scale-private-learning-via-low-rank","slug":"large-scale-private-learning-via-low-rank","title":"Large Scale Private Learning via Low-rank Reparametrization","date":"2021-06-17","arxiv_id":"2106.09352","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":1,"n_instrument":3,"unverified":4,"pointer_only":8,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["dayu11/Differentially-Private-Deep-Learning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/lnn-el-a-neuro-symbolic-approach-to-short","slug":"lnn-el-a-neuro-symbolic-approach-to-short","title":"LNN-EL: A Neuro-Symbolic Approach to Short-text Entity Linking","date":"2021-06-17","arxiv_id":"2106.09795","n_code_links":1,"syntology":null},{"paper":null,"slug":"long-short-temporal-contrastive-learning-of","title":"Long-Short Temporal Contrastive Learning of Video Transformers","date":"2021-06-17","arxiv_id":"2106.09212","n_code_links":0,"syntology":null},{"paper":"/paper/lora-low-rank-adaptation-of-large-language","slug":"lora-low-rank-adaptation-of-large-language","title":"LoRA: Low-Rank Adaptation of Large Language Models","date":"2021-06-17","arxiv_id":"2106.09685","n_code_links":74,"syntology":{"ran":51,"of":84,"n_ran_checked":44,"n_instrument":7,"unverified":33,"pointer_only":30,"phrase":"51 ran (of which 19 constructed an object rather than computing a result; 44 with no instrument failure: 1 honoured, 0 violated, 43 with no contract checked; 7 where Syntology's instrument failed) · 33 unverified","official":{"repos":["microsoft/LoRA"],"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/multi-head-or-single-head-an-empirical","slug":"multi-head-or-single-head-an-empirical","title":"Multi-head or Single-head? An Empirical Comparison for Transformer Training","date":"2021-06-17","arxiv_id":"2106.09650","n_code_links":1,"syntology":null},{"paper":null,"slug":"orthogonal-pade-activation-functions","title":"Orthogonal-Padé Activation Functions: Trainable Activation functions for smooth and faster convergence in deep networks","date":"2021-06-17","arxiv_id":"2106.09693","n_code_links":0,"syntology":null},{"paper":"/paper/semi-autoregressive-transformer-for-image","slug":"semi-autoregressive-transformer-for-image","title":"Semi-Autoregressive Transformer for Image Captioning","date":"2021-06-17","arxiv_id":"2106.09436","n_code_links":1,"syntology":null},{"paper":"/paper/time-series-is-a-special-sequence-forecasting","slug":"time-series-is-a-special-sequence-forecasting","title":"SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction","date":"2021-06-17","arxiv_id":"2106.09305","n_code_links":6,"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: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["WenjieDu/PyPOTS"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","named_in_paper"]}}},{"paper":null,"slug":"algorithm-to-compilation-codesign-an","title":"Algorithm to Compilation Co-design: An Integrated View of Neural Network Sparsity","date":"2021-06-16","arxiv_id":"2106.08846","n_code_links":0,"syntology":null},{"paper":"/paper/end-to-end-semi-supervised-object-detection","slug":"end-to-end-semi-supervised-object-detection","title":"End-to-End Semi-Supervised Object Detection with Soft Teacher","date":"2021-06-16","arxiv_id":"2106.09018","n_code_links":8,"syntology":null},{"paper":"/paper/grounding-spatio-temporal-language-with","slug":"grounding-spatio-temporal-language-with","title":"Grounding Spatio-Temporal Language with Transformers","date":"2021-06-16","arxiv_id":"2106.08858","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-evaluation-and-improvement-of-tail-label","title":"On Evaluation and Improvement of Tail Label Performance for Multi-label Text Classification","date":"2021-06-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-up-diverse-orthogonal-convolutional","title":"Scaling-up Diverse Orthogonal Convolutional Networks with a Paraunitary Framework","date":"2021-06-16","arxiv_id":"2106.09121","n_code_links":0,"syntology":null},{"paper":null,"slug":"shuffle-transformer-with-feature-alignment","title":"Shuffle Transformer with Feature Alignment for Video Face Parsing","date":"2021-06-16","arxiv_id":"2106.08650","n_code_links":0,"syntology":null},{"paper":null,"slug":"simultaneous-training-of-partially-masked","title":"Masked Training of Neural Networks with Partial Gradients","date":"2021-06-16","arxiv_id":"2106.08895","n_code_links":0,"syntology":null},{"paper":"/paper/tssubert-tweet-stream-summarization-using","slug":"tssubert-tweet-stream-summarization-using","title":"TSSuBERT: Tweet Stream Summarization Using BERT","date":"2021-06-16","arxiv_id":"2106.08770","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-automated-quality-evaluation-framework-of","title":"An Automated Quality Evaluation Framework of Psychotherapy Conversations with Local Quality Estimates","date":"2021-06-15","arxiv_id":"2106.07922","n_code_links":0,"syntology":null},{"paper":null,"slug":"asr-adaptation-for-e-commerce-chatbots-using","title":"ASR Adaptation for E-commerce Chatbots using Cross-Utterance Context and Multi-Task Language Modeling","date":"2021-06-15","arxiv_id":"2106.09532","n_code_links":0,"syntology":null},{"paper":"/paper/beit-bert-pre-training-of-image-transformers","slug":"beit-bert-pre-training-of-image-transformers","title":"BEiT: BERT Pre-Training of Image Transformers","date":"2021-06-15","arxiv_id":"2106.08254","n_code_links":14,"syntology":{"ran":6,"of":11,"n_ran_checked":4,"n_instrument":2,"unverified":5,"pointer_only":0,"phrase":"6 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; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["microsoft/unilm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"coda-constructivism-learning-for-instance","title":"CODA: Constructivism Learning for Instance-Dependent Dropout Architecture Construction","date":"2021-06-15","arxiv_id":"2106.08444","n_code_links":0,"syntology":null},{"paper":null,"slug":"ctrl-p-temporal-control-of-prosodic-variation","title":"Ctrl-P: Temporal Control of Prosodic Variation for Speech Synthesis","date":"2021-06-15","arxiv_id":"2106.08352","n_code_links":0,"syntology":null},{"paper":"/paper/generating-thermal-human-faces-for","slug":"generating-thermal-human-faces-for","title":"Generating Thermal Human Faces for Physiological Assessment Using Thermal Sensor Auxiliary Labels","date":"2021-06-15","arxiv_id":"2106.08091","n_code_links":1,"syntology":null},{"paper":"/paper/incorporating-word-sense-disambiguation-in","slug":"incorporating-word-sense-disambiguation-in","title":"Incorporating Word Sense Disambiguation in Neural Language Models","date":"2021-06-15","arxiv_id":"2106.07967","n_code_links":2,"syntology":null},{"paper":"/paper/knowledge-rich-bert-embeddings-for","slug":"knowledge-rich-bert-embeddings-for","title":"BERT Embeddings for Automatic Readability Assessment","date":"2021-06-15","arxiv_id":"2106.07935","n_code_links":1,"syntology":null},{"paper":"/paper/medical-code-prediction-from-discharge","slug":"medical-code-prediction-from-discharge","title":"Medical Code Prediction from Discharge Summary: Document to Sequence BERT using Sequence Attention","date":"2021-06-15","arxiv_id":"2106.07932","n_code_links":1,"syntology":null},{"paper":"/paper/mlp-singer-towards-rapid-parallel-singing","slug":"mlp-singer-towards-rapid-parallel-singing","title":"MLP Singer: Towards Rapid Parallel Singing Voice Synthesis","date":"2021-06-15","arxiv_id":null,"n_code_links":3,"syntology":null},{"paper":null,"slug":"pairconnect-a-compute-efficient-mlp","title":"PairConnect: A Compute-Efficient MLP Alternative to Attention","date":"2021-06-15","arxiv_id":"2106.08235","n_code_links":0,"syntology":null},{"paper":"/paper/scene-transformer-a-unified-multi-task-model","slug":"scene-transformer-a-unified-multi-task-model","title":"Scene Transformer: A unified architecture for predicting multiple agent trajectories","date":"2021-06-15","arxiv_id":"2106.08417","n_code_links":4,"syntology":{"ran":2,"of":6,"n_ran_checked":1,"n_instrument":1,"unverified":4,"pointer_only":6,"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) · 4 unverified","official":null}},{"paper":null,"slug":"textual-data-distributions-kullback-leibler","title":"Textual Data Distributions: Kullback Leibler Textual Distributions Contrasts on GPT-2 Generated Texts, with Supervised, Unsupervised Learning on Vaccine & Market Topics & Sentiment","date":"2021-06-15","arxiv_id":"2107.02025","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-bert-dig-it-named-entity-recognition-for","title":"Can BERT Dig It? -- Named Entity Recognition for Information Retrieval in the Archaeology Domain","date":"2021-06-14","arxiv_id":"2106.07742","n_code_links":0,"syntology":null},{"paper":"/paper/dataset-of-propaganda-techniques-of-the-state","slug":"dataset-of-propaganda-techniques-of-the-state","title":"Dataset of Propaganda Techniques of the State-Sponsored Information Operation of the People's Republic of China","date":"2021-06-14","arxiv_id":"2106.07544","n_code_links":1,"syntology":null},{"paper":"/paper/dfm-a-performance-baseline-for-deep-feature","slug":"dfm-a-performance-baseline-for-deep-feature","title":"DFM: A Performance Baseline for Deep Feature Matching","date":"2021-06-14","arxiv_id":"2106.07791","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-face-detection-in-the-fisheye-image","title":"Efficient Face Detection in the Fisheye Image Domain","date":"2021-06-14","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"42e85a25936e167789d8d268cdcd81a1e85a0ff6980bb7461be7dc5ebb725611","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}