{"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/attention/papers/265","list_of":"/method/attention","method":"Attention","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":265,"pages_in_order":316,"rows_per_page":100,"rows":[26401,26500],"of":31583,"counts":{"archive_papers_tagged":31583,"with_a_code_link":13473,"where_syntology_ran_a_sample":3998,"not_listed_spam_title":0,"listed":31583,"listed_where_code_ran":3998,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3366,"every_run_a_failure_of_syntologys_instrument":632,"listed_with_a_run_with_no_instrument_failure":3366,"listed_every_run_a_failure_of_syntologys_instrument":632,"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/attention","prev":"/method/attention/papers/264","next":"/method/attention/papers/266","papers":[{"paper":"/paper/trans4trans-efficient-transformer-for-1","slug":"trans4trans-efficient-transformer-for-1","title":"Trans4Trans: Efficient Transformer for Transparent Object and Semantic Scene Segmentation in Real-World Navigation Assistance","date":"2021-08-20","arxiv_id":"2108.09174","n_code_links":1,"syntology":null},{"paper":null,"slug":"uncertainties-and-output-feedback-in-rollout","title":"Uncertainties and output feedback in rollout event-triggered control","date":"2021-08-20","arxiv_id":"2108.09125","n_code_links":0,"syntology":null},{"paper":"/paper/a-framework-for-neural-topic-modeling-of-text","slug":"a-framework-for-neural-topic-modeling-of-text","title":"A Framework for Neural Topic Modeling of Text Corpora","date":"2021-08-19","arxiv_id":"2108.08946","n_code_links":1,"syntology":null},{"paper":"/paper/causal-attention-for-unbiased-visual","slug":"causal-attention-for-unbiased-visual","title":"Causal Attention for Unbiased Visual Recognition","date":"2021-08-19","arxiv_id":"2108.08782","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["wangt-cn/caam"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/contrastive-language-image-pre-training-for","slug":"contrastive-language-image-pre-training-for","title":"Contrastive Language-Image Pre-training for the Italian Language","date":"2021-08-19","arxiv_id":"2108.08688","n_code_links":1,"syntology":null},{"paper":null,"slug":"detection-of-illicit-drug-trafficking-events","title":"Detection of Illicit Drug Trafficking Events on Instagram: A Deep Multimodal Multilabel Learning Approach","date":"2021-08-19","arxiv_id":"2108.08920","n_code_links":0,"syntology":null},{"paper":"/paper/do-vision-transformers-see-like-convolutional","slug":"do-vision-transformers-see-like-convolutional","title":"Do Vision Transformers See Like Convolutional Neural Networks?","date":"2021-08-19","arxiv_id":"2108.08810","n_code_links":4,"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":null}},{"paper":"/paper/fast-passage-re-ranking-with-contextualized","slug":"fast-passage-re-ranking-with-contextualized","title":"Fast Passage Re-ranking with Contextualized Exact Term Matching and Efficient Passage Expansion","date":"2021-08-19","arxiv_id":"2108.08513","n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-grained-element-identification-in","title":"Fine-Grained Element Identification in Complaint Text of Internet Fraud","date":"2021-08-19","arxiv_id":"2108.08676","n_code_links":0,"syntology":null},{"paper":"/paper/how-hateful-are-movies-a-study-and-prediction","slug":"how-hateful-are-movies-a-study-and-prediction","title":"How Hateful are Movies? A Study and Prediction on Movie Subtitles","date":"2021-08-19","arxiv_id":"2108.10724","n_code_links":1,"syntology":null},{"paper":null,"slug":"mvsr-nat-multi-view-subset-regularization-for","title":"MvSR-NAT: Multi-view Subset Regularization for Non-Autoregressive Machine Translation","date":"2021-08-19","arxiv_id":"2108.08447","n_code_links":0,"syntology":null},{"paper":"/paper/sentence-t5-scalable-sentence-encoders-from","slug":"sentence-t5-scalable-sentence-encoders-from","title":"Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models","date":"2021-08-19","arxiv_id":"2108.08877","n_code_links":2,"syntology":null},{"paper":"/paper/uniqorn-unified-question-answering-over-rdf","slug":"uniqorn-unified-question-answering-over-rdf","title":"UNIQORN: Unified Question Answering over RDF Knowledge Graphs and Natural Language Text","date":"2021-08-19","arxiv_id":"2108.08614","n_code_links":1,"syntology":null},{"paper":"/paper/video-relation-detection-via-tracklet-based","slug":"video-relation-detection-via-tracklet-based","title":"Video Relation Detection via Tracklet based Visual Transformer","date":"2021-08-19","arxiv_id":"2108.08669","n_code_links":1,"syntology":null},{"paper":null,"slug":"contributions-of-transformer-attention-heads","title":"Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks","date":"2021-08-18","arxiv_id":"2108.08375","n_code_links":0,"syntology":null},{"paper":null,"slug":"integrating-dialog-history-into-end-to-end","title":"Integrating Dialog History into End-to-End Spoken Language Understanding Systems","date":"2021-08-18","arxiv_id":"2108.08405","n_code_links":0,"syntology":null},{"paper":null,"slug":"shaq-single-headed-attention-with-quasi","title":"SHAQ: Single Headed Attention with Quasi-Recurrence","date":"2021-08-18","arxiv_id":"2108.08207","n_code_links":0,"syntology":null},{"paper":null,"slug":"sifn-a-sentiment-aware-interactive-fusion","title":"SIFN: A Sentiment-aware Interactive Fusion Network for Review-based Item Recommendation","date":"2021-08-18","arxiv_id":"2108.08022","n_code_links":0,"syntology":null},{"paper":"/paper/table-caption-generation-in-scholarly","slug":"table-caption-generation-in-scholarly","title":"Table Caption Generation in Scholarly Documents Leveraging Pre-trained Language Models","date":"2021-08-18","arxiv_id":"2108.08111","n_code_links":1,"syntology":null},{"paper":"/paper/transformers-predicting-the-future-applying","slug":"transformers-predicting-the-future-applying","title":"Transformers predicting the future. Applying attention in next-frame and time series forecasting","date":"2021-08-18","arxiv_id":"2108.08224","n_code_links":1,"syntology":null},{"paper":null,"slug":"tsi-an-ad-text-strength-indicator-using-text","title":"TSI: an Ad Text Strength Indicator using Text-to-CTR and Semantic-Ad-Similarity","date":"2021-08-18","arxiv_id":"2108.08226","n_code_links":0,"syntology":null},{"paper":null,"slug":"two-streams-and-two-resolution-spectrograms","title":"A Multi-level Acoustic Feature Extraction Framework for Transformer Based End-to-End Speech Recognition","date":"2021-08-18","arxiv_id":"2108.07980","n_code_links":0,"syntology":null},{"paper":"/paper/boosting-salient-object-detection-with","slug":"boosting-salient-object-detection-with","title":"Boosting Salient Object Detection with Transformer-based Asymmetric Bilateral U-Net","date":"2021-08-17","arxiv_id":"2108.07851","n_code_links":1,"syntology":null},{"paper":null,"slug":"enct5-fine-tuning-t5-encoder-for","title":"EncT5: Fine-tuning T5 Encoder for Discriminative Tasks","date":"2021-08-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/learning-c-to-x86-translation-an-experiment","slug":"learning-c-to-x86-translation-an-experiment","title":"Learning C to x86 Translation: An Experiment in Neural Compilation","date":"2021-08-17","arxiv_id":"2108.07639","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["jordiae/neural-compilers"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/light-field-image-super-resolution-with","slug":"light-field-image-super-resolution-with","title":"Light Field Image Super-Resolution with Transformers","date":"2021-08-17","arxiv_id":"2108.07597","n_code_links":1,"syntology":null},{"paper":null,"slug":"moi-mixer-improving-mlp-mixer-with-multi","title":"MOI-Mixer: Improving MLP-Mixer with Multi Order Interactions in Sequential Recommendation","date":"2021-08-17","arxiv_id":"2108.07505","n_code_links":0,"syntology":null},{"paper":"/paper/response-ranking-with-multi-types-of-deep","slug":"response-ranking-with-multi-types-of-deep","title":"Response Ranking with Multi-types of Deep Interactive Representations in Retrieval-based Dialogues","date":"2021-08-17","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"semantics-aware-attention-improves-neural-1","title":"Semantics-aware Attention Improves Neural Machine Translation","date":"2021-08-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/semi-parametric-bayesian-additive-regression","slug":"semi-parametric-bayesian-additive-regression","title":"Accounting for shared covariates in semi-parametric Bayesian additive regression trees","date":"2021-08-17","arxiv_id":"2108.07636","n_code_links":2,"syntology":null},{"paper":null,"slug":"an-effective-non-autoregressive-model-for","title":"An Effective Non-Autoregressive Model for Spoken Language Understanding","date":"2021-08-16","arxiv_id":"2108.07005","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-natural-language-processing-for-linkedin-1","title":"Deep Natural Language Processing for LinkedIn Search","date":"2021-08-16","arxiv_id":"2108.13300","n_code_links":0,"syntology":null},{"paper":"/paper/misleading-the-covid-19-vaccination-discourse","slug":"misleading-the-covid-19-vaccination-discourse","title":"Misleading the Covid-19 vaccination discourse on Twitter: An exploratory study of infodemic around the pandemic","date":"2021-08-16","arxiv_id":"2108.10735","n_code_links":1,"syntology":null},{"paper":"/paper/no-reference-image-quality-assessment-via-1","slug":"no-reference-image-quality-assessment-via-1","title":"No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency","date":"2021-08-16","arxiv_id":"2108.06858","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-opportunities-and-risks-of-foundation","slug":"on-the-opportunities-and-risks-of-foundation","title":"On the Opportunities and Risks of Foundation Models","date":"2021-08-16","arxiv_id":"2108.07258","n_code_links":2,"syntology":null},{"paper":"/paper/scene-designer-a-unified-model-for-scene","slug":"scene-designer-a-unified-model-for-scene","title":"Scene Designer: a Unified Model for Scene Search and Synthesis from Sketch","date":"2021-08-16","arxiv_id":"2108.07353","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-generalization-ability-of","title":"Exploring Generalization Ability of Pretrained Language Models on Arithmetic and Logical Reasoning","date":"2021-08-15","arxiv_id":"2108.06743","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-temporal-coherence-for-more-general","slug":"exploring-temporal-coherence-for-more-general","title":"Exploring Temporal Coherence for More General Video Face Forgery Detection","date":"2021-08-15","arxiv_id":"2108.06693","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":6,"phrase":"6 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"maps-search-misspelling-detection-leveraging","title":"Maps Search Misspelling Detection Leveraging Domain-Augmented Contextual Representations","date":"2021-08-15","arxiv_id":"2108.06842","n_code_links":0,"syntology":null},{"paper":null,"slug":"sapphire-approaches-for-enhanced-concept-to","title":"SAPPHIRE: Approaches for Enhanced Concept-to-Text Generation","date":"2021-08-15","arxiv_id":"2108.06643","n_code_links":0,"syntology":null},{"paper":"/paper/sotr-segmenting-objects-with-transformers","slug":"sotr-segmenting-objects-with-transformers","title":"SOTR: Segmenting Objects with Transformers","date":"2021-08-15","arxiv_id":"2108.06747","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":6,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["easton-cau/SOTR"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/heterogeneous-temporal-graph-transformer-an","slug":"heterogeneous-temporal-graph-transformer-an","title":"heterogeneous temporal graph transformer: an intelligent system for evolving android malware detection","date":"2021-08-14","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/conditional-detr-for-fast-training","slug":"conditional-detr-for-fast-training","title":"Conditional DETR for Fast Training Convergence","date":"2021-08-13","arxiv_id":"2108.06152","n_code_links":4,"syntology":{"ran":6,"of":9,"n_ran_checked":4,"n_instrument":2,"unverified":3,"pointer_only":4,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["atten4vis/conditionaldetr"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/curriculum-learning-a-regularization-method","slug":"curriculum-learning-a-regularization-method","title":"The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models","date":"2021-08-13","arxiv_id":"2108.06084","n_code_links":1,"syntology":null},{"paper":"/paper/point-voxel-transformer-an-efficient-approach","slug":"point-voxel-transformer-an-efficient-approach","title":"PVT: Point-Voxel Transformer for Point Cloud Learning","date":"2021-08-13","arxiv_id":"2108.06076","n_code_links":2,"syntology":null},{"paper":null,"slug":"towards-structured-dynamic-sparse-pre","title":"Towards Structured Dynamic Sparse Pre-Training of BERT","date":"2021-08-13","arxiv_id":"2108.06277","n_code_links":0,"syntology":null},{"paper":"/paper/ammus-a-survey-of-transformer-based","slug":"ammus-a-survey-of-transformer-based","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","date":"2021-08-12","arxiv_id":"2108.05542","n_code_links":1,"syntology":null},{"paper":"/paper/how-optimal-is-greedy-decoding-for-extractive","slug":"how-optimal-is-greedy-decoding-for-extractive","title":"How Optimal is Greedy Decoding for Extractive Question Answering?","date":"2021-08-12","arxiv_id":"2108.05857","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["ocastel/exact-extract"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/mobile-former-bridging-mobilenet-and","slug":"mobile-former-bridging-mobilenet-and","title":"Mobile-Former: Bridging MobileNet and Transformer","date":"2021-08-12","arxiv_id":"2108.05895","n_code_links":4,"syntology":null},{"paper":null,"slug":"modeling-relevance-ranking-under-the-pre","title":"Modeling Relevance Ranking under the Pre-training and Fine-tuning Paradigm","date":"2021-08-12","arxiv_id":"2108.05652","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-analysis-of-the-predictability-of","title":"Multimodal analysis of the predictability of hand-gesture properties","date":"2021-08-12","arxiv_id":"2108.05762","n_code_links":0,"syntology":null},{"paper":"/paper/musiq-multi-scale-image-quality-transformer","slug":"musiq-multi-scale-image-quality-transformer","title":"MUSIQ: Multi-scale Image Quality Transformer","date":"2021-08-12","arxiv_id":"2108.05997","n_code_links":2,"syntology":{"ran":5,"of":6,"n_ran_checked":4,"n_instrument":1,"unverified":1,"pointer_only":6,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 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":null,"slug":"overview-of-the-hasoc-track-at-fire-2020-hate","title":"Overview of the HASOC track at FIRE 2020: Hate Speech and Offensive Content Identification in Indo-European Languages","date":"2021-08-12","arxiv_id":"2108.05927","n_code_links":0,"syntology":null},{"paper":"/paper/patrickstar-parallel-training-of-pre-trained","slug":"patrickstar-parallel-training-of-pre-trained","title":"PatrickStar: Parallel Training of Pre-trained Models via Chunk-based Memory Management","date":"2021-08-12","arxiv_id":"2108.05818","n_code_links":1,"syntology":null},{"paper":"/paper/tvt-transferable-vision-transformer-for","slug":"tvt-transferable-vision-transformer-for","title":"TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation","date":"2021-08-12","arxiv_id":"2108.05988","n_code_links":1,"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: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["uta-smile/TVT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"abstractive-sentence-summarization-with-1","title":"ICAF: Iterative Contrastive Alignment Framework for Multimodal Abstractive Summarization","date":"2021-08-11","arxiv_id":"2108.05123","n_code_links":0,"syntology":null},{"paper":null,"slug":"convnets-vs-transformers-whose-visual","title":"ConvNets vs. Transformers: Whose Visual Representations are More Transferable?","date":"2021-08-11","arxiv_id":"2108.05305","n_code_links":0,"syntology":null},{"paper":null,"slug":"medical-vlbert-medical-visual-language-bert","title":"Medical-VLBERT: Medical Visual Language BERT for COVID-19 CT Report Generation With Alternate Learning","date":"2021-08-11","arxiv_id":"2108.05067","n_code_links":0,"syntology":null},{"paper":null,"slug":"nofake-at-checkthat-2021-fake-news-detection","title":"NoFake at CheckThat! 2021: Fake News Detection Using BERT","date":"2021-08-11","arxiv_id":"2108.05419","n_code_links":0,"syntology":null},{"paper":"/paper/perturbing-inputs-for-fragile-interpretations","slug":"perturbing-inputs-for-fragile-interpretations","title":"Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing","date":"2021-08-11","arxiv_id":"2108.04990","n_code_links":1,"syntology":null},{"paper":"/paper/variable-length-music-score-infilling-via","slug":"variable-length-music-score-infilling-via","title":"Variable-Length Music Score Infilling via XLNet and Musically Specialized Positional Encoding","date":"2021-08-11","arxiv_id":"2108.05064","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-study-of-social-and-behavioral-determinants","title":"A Study of Social and Behavioral Determinants of Health in Lung Cancer Patients Using Transformers-based Natural Language Processing Models","date":"2021-08-10","arxiv_id":"2108.04949","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-multi-resolution-attention-with","title":"Adaptive Multi-Resolution Attention with Linear Complexity","date":"2021-08-10","arxiv_id":"2108.04962","n_code_links":0,"syntology":null},{"paper":"/paper/adarnn-adaptive-learning-and-forecasting-of","slug":"adarnn-adaptive-learning-and-forecasting-of","title":"AdaRNN: Adaptive Learning and Forecasting of Time Series","date":"2021-08-10","arxiv_id":"2108.04443","n_code_links":2,"syntology":null},{"paper":"/paper/bros-a-layout-aware-pre-trained-language","slug":"bros-a-layout-aware-pre-trained-language","title":"BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents","date":"2021-08-10","arxiv_id":"2108.04539","n_code_links":2,"syntology":{"ran":13,"of":13,"n_ran_checked":11,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["clovaai/bros"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"clsebert-contrastive-learning-for-syntax","title":"SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation","date":"2021-08-10","arxiv_id":"2108.04556","n_code_links":0,"syntology":null},{"paper":"/paper/differentiable-subset-pruning-of-transformer","slug":"differentiable-subset-pruning-of-transformer","title":"Differentiable Subset Pruning of Transformer Heads","date":"2021-08-10","arxiv_id":"2108.04657","n_code_links":2,"syntology":null},{"paper":"/paper/embodied-bert-a-transformer-model-for","slug":"embodied-bert-a-transformer-model-for","title":"Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion","date":"2021-08-10","arxiv_id":"2108.04927","n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-user-behavior-retrieval-in-click","slug":"end-to-end-user-behavior-retrieval-in-click","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","date":"2021-08-10","arxiv_id":"2108.04468","n_code_links":1,"syntology":null},{"paper":null,"slug":"ft-tdr-frequency-guided-transformer-and-top","title":"FT-TDR: Frequency-guided Transformer and Top-Down Refinement Network for Blind Face Inpainting","date":"2021-08-10","arxiv_id":"2108.04424","n_code_links":0,"syntology":null},{"paper":"/paper/truman-trope-understanding-in-movies-and","slug":"truman-trope-understanding-in-movies-and","title":"TrUMAn: Trope Understanding in Movies and Animations","date":"2021-08-10","arxiv_id":"2108.04542","n_code_links":0,"syntology":null},{"paper":"/paper/do-images-really-do-the-talking-analysing-the","slug":"do-images-really-do-the-talking-analysing-the","title":"Do Images really do the Talking? Analysing the significance of Images in Tamil Troll meme classification","date":"2021-08-09","arxiv_id":"2108.03886","n_code_links":1,"syntology":null},{"paper":"/paper/dossier-coliee-2021-leveraging-dense","slug":"dossier-coliee-2021-leveraging-dense","title":"DoSSIER@COLIEE 2021: Leveraging dense retrieval and summarization-based re-ranking for case law retrieval","date":"2021-08-09","arxiv_id":"2108.03937","n_code_links":1,"syntology":null},{"paper":"/paper/filming-multimodal-sarcasm-detection-with","slug":"filming-multimodal-sarcasm-detection-with","title":"FiLMing Multimodal Sarcasm Detection with Attention","date":"2021-08-09","arxiv_id":"2110.00416","n_code_links":1,"syntology":null},{"paper":null,"slug":"intent5-search-result-diversification-using","title":"IntenT5: Search Result Diversification using Causal Language Models","date":"2021-08-09","arxiv_id":"2108.04026","n_code_links":0,"syntology":null},{"paper":"/paper/making-transformers-solve-compositional-tasks","slug":"making-transformers-solve-compositional-tasks","title":"Making Transformers Solve Compositional Tasks","date":"2021-08-09","arxiv_id":"2108.04378","n_code_links":1,"syntology":null},{"paper":"/paper/paint-transformer-feed-forward-neural","slug":"paint-transformer-feed-forward-neural","title":"Paint Transformer: Feed Forward Neural Painting with Stroke Prediction","date":"2021-08-09","arxiv_id":"2108.03798","n_code_links":2,"syntology":null},{"paper":"/paper/raftmlp-do-mlp-based-models-dream-of-winning","slug":"raftmlp-do-mlp-based-models-dream-of-winning","title":"RaftMLP: How Much Can Be Done Without Attention and with Less Spatial Locality?","date":"2021-08-09","arxiv_id":"2108.04384","n_code_links":2,"syntology":null},{"paper":null,"slug":"the-hw-tsc-s-offline-speech-translation","title":"The HW-TSC's Offline Speech Translation Systems for IWSLT 2021 Evaluation","date":"2021-08-09","arxiv_id":"2108.03845","n_code_links":0,"syntology":null},{"paper":"/paper/efficacy-of-bert-embeddings-on-predicting","slug":"efficacy-of-bert-embeddings-on-predicting","title":"Efficacy of BERT embeddings on predicting disaster from Twitter data","date":"2021-08-08","arxiv_id":"2108.10698","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-commonsense-knowledge-on","title":"Leveraging Commonsense Knowledge on Classifying False News and Determining Checkworthiness of Claims","date":"2021-08-08","arxiv_id":"2108.03731","n_code_links":0,"syntology":null},{"paper":"/paper/edge-augmented-graph-transformers-global-self","slug":"edge-augmented-graph-transformers-global-self","title":"Global Self-Attention as a Replacement for Graph Convolution","date":"2021-08-07","arxiv_id":"2108.03348","n_code_links":3,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["shamim-hussain/egt","shamim-hussain/egt_pytorch","shamim-hussain/egt_triangular"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/hetemotionnet-two-stream-heterogeneous-graph","slug":"hetemotionnet-two-stream-heterogeneous-graph","title":"HetEmotionNet: Two-Stream Heterogeneous Graph Recurrent Neural Network for Multi-modal Emotion Recognition","date":"2021-08-07","arxiv_id":"2108.03354","n_code_links":2,"syntology":null},{"paper":null,"slug":"psvit-better-vision-transformer-via-token","title":"PSViT: Better Vision Transformer via Token Pooling and Attention Sharing","date":"2021-08-07","arxiv_id":"2108.03428","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-of-alphastar","slug":"rethinking-of-alphastar","title":"Rethinking of AlphaStar","date":"2021-08-07","arxiv_id":"2108.03452","n_code_links":2,"syntology":null},{"paper":null,"slug":"vision-transformers-for-femur-fracture","title":"Vision Transformer for femur fracture classification","date":"2021-08-07","arxiv_id":"2108.03414","n_code_links":0,"syntology":null},{"paper":"/paper/deriving-disinformation-insights-from","slug":"deriving-disinformation-insights-from","title":"Deriving Disinformation Insights from Geolocalized Twitter Callouts","date":"2021-08-06","arxiv_id":"2108.03067","n_code_links":1,"syntology":null},{"paper":null,"slug":"offensive-language-and-hate-speech-detection-1","title":"Offensive Language and Hate Speech Detection with Deep Learning and Transfer Learning","date":"2021-08-06","arxiv_id":"2108.03305","n_code_links":0,"syntology":null},{"paper":null,"slug":"rollout-event-triggered-control-reconciling","title":"Rollout event-triggered control: reconciling event- and time-triggered control","date":"2021-08-06","arxiv_id":"2108.02994","n_code_links":0,"syntology":null},{"paper":"/paper/simpler-is-better-few-shot-semantic","slug":"simpler-is-better-few-shot-semantic","title":"Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer","date":"2021-08-06","arxiv_id":"2108.03032","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 1 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":["zhiheLu/CWT-for-FSS"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-right-to-talk-an-audio-visual-transformer","slug":"the-right-to-talk-an-audio-visual-transformer","title":"The Right to Talk: An Audio-Visual Transformer Approach","date":"2021-08-06","arxiv_id":"2108.03256","n_code_links":1,"syntology":null},{"paper":null,"slug":"adaptive-residue-wise-profile-fusion-for-low","title":"Adaptive Residue-wise Profile Fusion for Low Homologous Protein SecondaryStructure Prediction Using External Knowledge","date":"2021-08-05","arxiv_id":"2108.04176","n_code_links":0,"syntology":null},{"paper":null,"slug":"decoupled-transformer-for-scalable-inference","title":"Decoupled Transformer for Scalable Inference in Open-domain Question Answering","date":"2021-08-05","arxiv_id":"2108.02765","n_code_links":0,"syntology":null},{"paper":"/paper/fast-convergence-of-detr-with-spatially-1","slug":"fast-convergence-of-detr-with-spatially-1","title":"Fast Convergence of DETR with Spatially Modulated Co-Attention","date":"2021-08-05","arxiv_id":"2108.02404","n_code_links":1,"syntology":null},{"paper":"/paper/finetuning-pretrained-transformers-into","slug":"finetuning-pretrained-transformers-into","title":"Finetuning Pretrained Transformers into Variational Autoencoders","date":"2021-08-05","arxiv_id":"2108.02446","n_code_links":1,"syntology":null},{"paper":null,"slug":"robust-transfer-learning-with-pretrained","title":"Robust Transfer Learning with Pretrained Language Models through Adapters","date":"2021-08-05","arxiv_id":"2108.02340","n_code_links":0,"syntology":null},{"paper":null,"slug":"rockgpt-reconstructing-three-dimensional","title":"RockGPT: Reconstructing three-dimensional digital rocks from single two-dimensional slice from the perspective of video generation","date":"2021-08-05","arxiv_id":"2108.03132","n_code_links":0,"syntology":null},{"paper":null,"slug":"sentiment-analysis-on-the-news-to-improve","title":"Sentiment Analysis on the News to Improve Mental Health","date":"2021-08-05","arxiv_id":"2108.07706","n_code_links":0,"syntology":null},{"paper":"/paper/token-shift-transformer-for-video","slug":"token-shift-transformer-for-video","title":"Token Shift Transformer for Video Classification","date":"2021-08-05","arxiv_id":"2108.02432","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":["VideoNetworks/TokShift-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":null,"slug":"transrefer3d-entity-and-relation-aware","title":"TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding","date":"2021-08-05","arxiv_id":"2108.02388","n_code_links":0,"syntology":null}],"record_sha256":"ba2b6f41e98836f80c173da2dd53b9338d2878247972380180dab23b841a4c59","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}