{"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/254","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":254,"pages_in_order":316,"rows_per_page":100,"rows":[25301,25400],"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/253","next":"/method/attention/papers/255","papers":[{"paper":null,"slug":"buildformer-automatic-building-extraction","title":"Building extraction with vision transformer","date":"2021-11-29","arxiv_id":"2111.15637","n_code_links":0,"syntology":null},{"paper":null,"slug":"customer-sentiment-analysis-using-weak","title":"Customer Sentiment Analysis using Weak Supervision for Customer-Agent Chat","date":"2021-11-29","arxiv_id":"2111.14282","n_code_links":0,"syntology":null},{"paper":"/paper/daformer-improving-network-architectures-and","slug":"daformer-improving-network-architectures-and","title":"DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation","date":"2021-11-29","arxiv_id":"2111.14887","n_code_links":3,"syntology":{"ran":6,"of":6,"n_ran_checked":2,"n_instrument":4,"unverified":0,"pointer_only":6,"phrase":"6 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lhoyer/DAFormer"],"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","unlocated"]}}},{"paper":null,"slug":"mixed-precision-low-bit-quantization-of","title":"Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition","date":"2021-11-29","arxiv_id":"2112.11438","n_code_links":0,"syntology":null},{"paper":null,"slug":"mixed-precision-of-quantization-of","title":"Mixed Precision of Quantization of Transformer Language Models for Speech Recognition","date":"2021-11-29","arxiv_id":"2112.11540","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-rate-of-convergence-of-a-classifier","title":"On the rate of convergence of a classifier based on a Transformer encoder","date":"2021-11-29","arxiv_id":"2111.14574","n_code_links":0,"syntology":null},{"paper":"/paper/point-bert-pre-training-3d-point-cloud","slug":"point-bert-pre-training-3d-point-cloud","title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","date":"2021-11-29","arxiv_id":"2111.14819","n_code_links":3,"syntology":{"ran":5,"of":6,"n_ran_checked":2,"n_instrument":3,"unverified":1,"pointer_only":2,"phrase":"5 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["lulutang0608/Point-BERT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"recurrent-vision-transformer-for-solving","title":"Recurrent Vision Transformer for Solving Visual Reasoning Problems","date":"2021-11-29","arxiv_id":"2111.14576","n_code_links":0,"syntology":null},{"paper":"/paper/searching-the-search-space-of-vision-1","slug":"searching-the-search-space-of-vision-1","title":"Searching the Search Space of Vision Transformer","date":"2021-11-29","arxiv_id":"2111.14725","n_code_links":2,"syntology":null},{"paper":"/paper/sparse-detr-efficient-end-to-end-object-1","slug":"sparse-detr-efficient-end-to-end-object-1","title":"Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity","date":"2021-11-29","arxiv_id":"2111.14330","n_code_links":1,"syntology":{"ran":3,"of":7,"n_ran_checked":3,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"3 ran (of which 3 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) · 4 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":{"repos":["kakaobrain/sparse-detr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"speech-tasks-relevant-to-sleepiness","title":"Speech Tasks Relevant to Sleepiness Determined with Deep Transfer Learning","date":"2021-11-29","arxiv_id":"2111.14684","n_code_links":0,"syntology":null},{"paper":"/paper/transmvsnet-global-context-aware-multi-view","slug":"transmvsnet-global-context-aware-multi-view","title":"TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers","date":"2021-11-29","arxiv_id":"2111.14600","n_code_links":1,"syntology":null},{"paper":null,"slug":"context-matters-in-semantically-controlled","title":"Context Matters in Semantically Controlled Language Generation for Task-oriented Dialogue Systems","date":"2021-11-28","arxiv_id":"2111.14119","n_code_links":0,"syntology":null},{"paper":"/paper/fasttrees-parallel-latent-tree-induction-for","slug":"fasttrees-parallel-latent-tree-induction-for","title":"FastTrees: Parallel Latent Tree-Induction for Faster Sequence Encoding","date":"2021-11-28","arxiv_id":"2111.14031","n_code_links":1,"syntology":null},{"paper":null,"slug":"mist-net-multi-domain-integrative-swin","title":"Multi-domain Integrative Swin Transformer network for Sparse-View Tomographic Reconstruction","date":"2021-11-28","arxiv_id":"2111.14831","n_code_links":0,"syntology":null},{"paper":"/paper/orchard-a-benchmark-for-measuring-systematic","slug":"orchard-a-benchmark-for-measuring-systematic","title":"ORCHARD: A Benchmark For Measuring Systematic Generalization of Multi-Hierarchical Reasoning","date":"2021-11-28","arxiv_id":"2111.14034","n_code_links":1,"syntology":null},{"paper":"/paper/abusive-and-threatening-language-detection-in","slug":"abusive-and-threatening-language-detection-in","title":"Abusive and Threatening Language Detection in Urdu using Boosting based and BERT based models: A Comparative Approach","date":"2021-11-27","arxiv_id":"2111.14830","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-transformer-based-models-to","title":"Exploring Transformer Based Models to Identify Hate Speech and Offensive Content in English and Indo-Aryan Languages","date":"2021-11-27","arxiv_id":"2111.13974","n_code_links":0,"syntology":null},{"paper":"/paper/fq-vit-fully-quantized-vision-transformer","slug":"fq-vit-fully-quantized-vision-transformer","title":"FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer","date":"2021-11-27","arxiv_id":"2111.13824","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["megvii-research/FQ-ViT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"geoscan-global-earth-observation-using-swarm","title":"GEOSCAN: Global Earth Observation using Swarm of Coordinated Autonomous Nanosats","date":"2021-11-27","arxiv_id":"2111.15627","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-a-3d-cnn-and-transformer-prior-for","title":"Learning A 3D-CNN and Transformer Prior for Hyperspectral Image Super-Resolution","date":"2021-11-27","arxiv_id":"2111.13923","n_code_links":0,"syntology":null},{"paper":null,"slug":"tapping-bert-for-preposition-sense","title":"Tapping BERT for Preposition Sense Disambiguation","date":"2021-11-27","arxiv_id":"2111.13972","n_code_links":0,"syntology":null},{"paper":"/paper/a-volumetric-transformer-for-accurate-3d","slug":"a-volumetric-transformer-for-accurate-3d","title":"A Robust Volumetric Transformer for Accurate 3D Tumor Segmentation","date":"2021-11-26","arxiv_id":"2111.13300","n_code_links":1,"syntology":{"ran":4,"of":10,"n_ran_checked":3,"n_instrument":1,"unverified":6,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["himashi92/vt-unet"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/exploiting-full-resolution-feature-context","slug":"exploiting-full-resolution-feature-context","title":"Exploiting full Resolution Feature Context for Liver Tumor and Vessel Segmentation via Integrate Framework: Application to Liver Tumor and Vessel 3D Reconstruction under embedded microprocessor","date":"2021-11-26","arxiv_id":"2111.13299","n_code_links":1,"syntology":null},{"paper":"/paper/gmflow-learning-optical-flow-via-global","slug":"gmflow-learning-optical-flow-via-global","title":"GMFlow: Learning Optical Flow via Global Matching","date":"2021-11-26","arxiv_id":"2111.13680","n_code_links":4,"syntology":{"ran":14,"of":19,"n_ran_checked":13,"n_instrument":1,"unverified":5,"pointer_only":7,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["haofeixu/gmflow"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"predicting-document-coverage-for-relation","title":"Predicting Document Coverage for Relation Extraction","date":"2021-11-26","arxiv_id":"2111.13611","n_code_links":0,"syntology":null},{"paper":"/paper/swat-spatial-structure-within-and-among","slug":"swat-spatial-structure-within-and-among","title":"SWAT: Spatial Structure Within and Among Tokens","date":"2021-11-26","arxiv_id":"2111.13677","n_code_links":1,"syntology":null},{"paper":"/paper/amortized-prompt-lightweight-fine-tuning-for","slug":"amortized-prompt-lightweight-fine-tuning-for","title":"Domain Prompt Learning for Efficiently Adapting CLIP to Unseen Domains","date":"2021-11-25","arxiv_id":"2111.12853","n_code_links":1,"syntology":{"ran":12,"of":17,"n_ran_checked":8,"n_instrument":4,"unverified":5,"pointer_only":17,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","official":{"repos":["shogi880/DPLCLIP"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/attend-to-who-you-are-supervising-self-1","slug":"attend-to-who-you-are-supervising-self-1","title":"Attend to Who You Are: Supervising Self-Attention for Keypoint Detection and Instance-Aware Association","date":"2021-11-25","arxiv_id":"2111.12892","n_code_links":1,"syntology":null},{"paper":"/paper/boxer-box-attention-for-2d-and-3d","slug":"boxer-box-attention-for-2d-and-3d","title":"BoxeR: Box-Attention for 2D and 3D Transformers","date":"2021-11-25","arxiv_id":"2111.13087","n_code_links":1,"syntology":null},{"paper":null,"slug":"does-constituency-analysis-enhance-domain","title":"Does constituency analysis enhance domain-specific pre-trained BERT models for relation extraction?","date":"2021-11-25","arxiv_id":"2112.02955","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-the-robustness-of-retrieval","slug":"evaluating-the-robustness-of-retrieval","title":"Evaluating the Robustness of Retrieval Pipelines with Query Variation Generators","date":"2021-11-25","arxiv_id":"2111.13057","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploiting-both-domain-specific-and-invariant","title":"Exploiting Both Domain-specific and Invariant Knowledge via a Win-win Transformer for Unsupervised Domain Adaptation","date":"2021-11-25","arxiv_id":"2111.12941","n_code_links":0,"syntology":null},{"paper":null,"slug":"global-interaction-modelling-in-vision","title":"Global Interaction Modelling in Vision Transformer via Super Tokens","date":"2021-11-25","arxiv_id":"2111.13156","n_code_links":0,"syntology":null},{"paper":null,"slug":"new-approaches-to-long-document-summarization","title":"New Approaches to Long Document Summarization: Fourier Transform Based Attention in a Transformer Model","date":"2021-11-25","arxiv_id":"2111.15473","n_code_links":0,"syntology":null},{"paper":null,"slug":"probabilistic-impact-score-generation-using","title":"Probabilistic Impact Score Generation using Ktrain-BERT to Identify Hate Words from Twitter Discussions","date":"2021-11-25","arxiv_id":"2111.12939","n_code_links":0,"syntology":null},{"paper":null,"slug":"recommending-multiple-positive-citations-for","title":"Recommending Multiple Positive Citations for Manuscript via Content-Dependent Modeling and Multi-Positive Triplet","date":"2021-11-25","arxiv_id":"2111.12899","n_code_links":0,"syntology":null},{"paper":"/paper/scene-representation-transformer-geometry","slug":"scene-representation-transformer-geometry","title":"Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations","date":"2021-11-25","arxiv_id":"2111.13152","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":null}},{"paper":null,"slug":"transformer-based-korean-pretrained-language","title":"Transformer-based Korean Pretrained Language Models: A Survey on Three Years of Progress","date":"2021-11-25","arxiv_id":"2112.03014","n_code_links":0,"syntology":null},{"paper":null,"slug":"tunbert-pretrained-contextualized-text","title":"TunBERT: Pretrained Contextualized Text Representation for Tunisian Dialect","date":"2021-11-25","arxiv_id":"2111.13138","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-based-dual-stream-vision","title":"Attention-based Dual-stream Vision Transformer for Radar Gait Recognition","date":"2021-11-24","arxiv_id":"2111.12290","n_code_links":0,"syntology":null},{"paper":"/paper/mhformer-multi-hypothesis-transformer-for-3d","slug":"mhformer-multi-hypothesis-transformer-for-3d","title":"MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation","date":"2021-11-24","arxiv_id":"2111.12707","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["Vegetebird/MHFormer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/morphmlp-a-self-attention-free-mlp-like","slug":"morphmlp-a-self-attention-free-mlp-like","title":"MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning","date":"2021-11-24","arxiv_id":"2111.12527","n_code_links":2,"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":["MTLab/MorphMLP"],"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/peco-perceptual-codebook-for-bert-pre","slug":"peco-perceptual-codebook-for-bert-pre","title":"PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers","date":"2021-11-24","arxiv_id":"2111.12710","n_code_links":1,"syntology":null},{"paper":null,"slug":"sparse-is-enough-in-scaling-transformers-1","title":"Sparse is Enough in Scaling Transformers","date":"2021-11-24","arxiv_id":"2111.12763","n_code_links":0,"syntology":null},{"paper":"/paper/unleashing-transformers-parallel-token","slug":"unleashing-transformers-parallel-token","title":"Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes","date":"2021-11-24","arxiv_id":"2111.12701","n_code_links":3,"syntology":null},{"paper":null,"slug":"utilizing-resource-rich-language-datasets-for","title":"Utilizing Resource-Rich Language Datasets for End-to-End Scene Text Recognition in Resource-Poor Languages","date":"2021-11-24","arxiv_id":"2111.12276","n_code_links":0,"syntology":null},{"paper":"/paper/violet-end-to-end-video-language-transformers","slug":"violet-end-to-end-video-language-transformers","title":"VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling","date":"2021-11-24","arxiv_id":"2111.12681","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["tsujuifu/pytorch_violet"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":"/paper/dabs-a-domain-agnostic-benchmark-for-self","slug":"dabs-a-domain-agnostic-benchmark-for-self","title":"DABS: A Domain-Agnostic Benchmark for Self-Supervised Learning","date":"2021-11-23","arxiv_id":"2111.12062","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: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["alextamkin/dabs"],"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":"deep-point-cloud-reconstruction-1","title":"Deep Point Cloud Reconstruction","date":"2021-11-23","arxiv_id":"2111.11704","n_code_links":0,"syntology":null},{"paper":"/paper/multi-person-3d-motion-prediction-with-multi-1","slug":"multi-person-3d-motion-prediction-with-multi-1","title":"Multi-Person 3D Motion Prediction with Multi-Range Transformers","date":"2021-11-23","arxiv_id":"2111.12073","n_code_links":1,"syntology":null},{"paper":"/paper/pruning-self-attentions-into-convolutional","slug":"pruning-self-attentions-into-convolutional","title":"Pruning Self-attentions into Convolutional Layers in Single Path","date":"2021-11-23","arxiv_id":"2111.11802","n_code_links":3,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["zhuang-group/spvit","zip-group/spvit","ziplab/spvit"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pureformer-do-we-even-need-attention","title":"SimpleTRON: Simple Transformer with O(N) Complexity","date":"2021-11-23","arxiv_id":"2111.15588","n_code_links":0,"syntology":null},{"paper":null,"slug":"s-simcse-sampled-sub-networks-for-contrastive","title":"S-SimCSE: Sampled Sub-networks for Contrastive Learning of Sentence Embedding","date":"2021-11-23","arxiv_id":"2111.11750","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-pre-training-for-transformer","slug":"self-supervised-pre-training-for-transformer","title":"Self-Supervised Pre-Training for Transformer-Based Person Re-Identification","date":"2021-11-23","arxiv_id":"2111.12084","n_code_links":3,"syntology":{"ran":7,"of":8,"n_ran_checked":4,"n_instrument":3,"unverified":1,"pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["michuanhaohao/transreid-ssl"],"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/u-shape-transformer-for-underwater-image","slug":"u-shape-transformer-for-underwater-image","title":"U-shape Transformer for Underwater Image Enhancement","date":"2021-11-23","arxiv_id":"2111.11843","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":1,"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":["LintaoPeng/U-shape_Transformer"],"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/variational-learning-for-unsupervised-1","slug":"variational-learning-for-unsupervised-1","title":"Variational Learning for Unsupervised Knowledge Grounded Dialogs","date":"2021-11-23","arxiv_id":"2112.00653","n_code_links":1,"syntology":null},{"paper":"/paper/benchmarking-detection-transfer-learning-with","slug":"benchmarking-detection-transfer-learning-with","title":"Benchmarking Detection Transfer Learning with Vision Transformers","date":"2021-11-22","arxiv_id":"2111.11429","n_code_links":2,"syntology":null},{"paper":"/paper/dbia-data-free-backdoor-injection-attack","slug":"dbia-data-free-backdoor-injection-attack","title":"DBIA: Data-free Backdoor Injection Attack against Transformer Networks","date":"2021-11-22","arxiv_id":"2111.11870","n_code_links":1,"syntology":null},{"paper":"/paper/ext5-towards-extreme-multi-task-scaling-for-1","slug":"ext5-towards-extreme-multi-task-scaling-for-1","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","date":"2021-11-22","arxiv_id":"2111.10952","n_code_links":4,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["google-research/text-to-text-transfer-transformer","tensorflow/mesh"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"finding-the-winning-ticket-of-bert-for-binary","title":"Can depth-adaptive BERT perform better on binary classification tasks","date":"2021-11-22","arxiv_id":"2111.10951","n_code_links":0,"syntology":null},{"paper":"/paper/l-verse-bidirectional-generation-between","slug":"l-verse-bidirectional-generation-between","title":"L-Verse: Bidirectional Generation Between Image and Text","date":"2021-11-22","arxiv_id":"2111.11133","n_code_links":1,"syntology":null},{"paper":"/paper/metaformer-is-actually-what-you-need-for","slug":"metaformer-is-actually-what-you-need-for","title":"MetaFormer Is Actually What You Need for Vision","date":"2021-11-22","arxiv_id":"2111.11418","n_code_links":18,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rwightman/pytorch-image-models","sail-sg/poolformer"],"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":"patch-vestiges-in-the-adversarial-examples","title":"Patch Vestiges in the Adversarial Examples Against Vision Transformer Can Be Leveraged for Adversarial Detection","date":"2021-11-22","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"replica-enhanced-feature-pyramid-network-by","title":"Lightweight Transformer Backbone for Medical Object Detection","date":"2021-11-22","arxiv_id":"2111.11546","n_code_links":0,"syntology":null},{"paper":"/paper/semi-supervised-vision-transformers","slug":"semi-supervised-vision-transformers","title":"Semi-Supervised Vision Transformers","date":"2021-11-22","arxiv_id":"2111.11067","n_code_links":1,"syntology":null},{"paper":null,"slug":"cpt-convolutional-point-transformer-for-3d","title":"CpT: Convolutional Point Transformer for 3D Point Cloud Processing","date":"2021-11-21","arxiv_id":"2111.10866","n_code_links":0,"syntology":null},{"paper":null,"slug":"dudotrans-dual-domain-transformer-provides","title":"DuDoTrans: Dual-Domain Transformer Provides More Attention for Sinogram Restoration in Sparse-View CT Reconstruction","date":"2021-11-21","arxiv_id":"2111.10790","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-softmax-approximation-for-deep","title":"Efficient Softmax Approximation for Deep Neural Networks with Attention Mechanism","date":"2021-11-21","arxiv_id":"2111.10770","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-vision-transformers-robust-to-patch","title":"Are Vision Transformers Robust to Patch Perturbations?","date":"2021-11-20","arxiv_id":"2111.10659","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-processing-matters-srph-konvergen-ai-s","title":"Data Processing Matters: SRPH-Konvergen AI's Machine Translation System for WMT'21","date":"2021-11-20","arxiv_id":"2111.10513","n_code_links":0,"syntology":null},{"paper":"/paper/discrete-representations-strengthen-vision-1","slug":"discrete-representations-strengthen-vision-1","title":"Discrete Representations Strengthen Vision Transformer Robustness","date":"2021-11-20","arxiv_id":"2111.10493","n_code_links":1,"syntology":null},{"paper":"/paper/advancing-high-resolution-video-language","slug":"advancing-high-resolution-video-language","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","date":"2021-11-19","arxiv_id":"2111.10337","n_code_links":1,"syntology":null},{"paper":null,"slug":"does-bert-look-at-sentiment-lexicon","title":"Does BERT look at sentiment lexicon?","date":"2021-11-19","arxiv_id":"2111.10100","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-graph-representation-learning-via-2","title":"DyFormer: A Scalable Dynamic Graph Transformer with Provable Benefits on Generalization Ability","date":"2021-11-19","arxiv_id":"2111.10447","n_code_links":0,"syntology":null},{"paper":"/paper/generalized-decision-transformer-for-offline","slug":"generalized-decision-transformer-for-offline","title":"Generalized Decision Transformer for Offline Hindsight Information Matching","date":"2021-11-19","arxiv_id":"2111.10364","n_code_links":1,"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":["frt03/generalized_dt"],"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":"/paper/grounded-situation-recognition-with","slug":"grounded-situation-recognition-with","title":"Grounded Situation Recognition with Transformers","date":"2021-11-19","arxiv_id":"2111.10135","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":3,"n_instrument":2,"unverified":4,"pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["jhcho99/gsrtr"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"lexicon-based-methods-vs-bert-for-text","title":"Lexicon-based Methods vs. BERT for Text Sentiment Analysis","date":"2021-11-19","arxiv_id":"2111.10097","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-query-key-and-value-embedding-in","title":"Rethinking Query, Key, and Value Embedding in Vision Transformer under Tiny Model Constraints","date":"2021-11-19","arxiv_id":"2111.10017","n_code_links":0,"syntology":null},{"paper":"/paper/transmorph-transformer-for-unsupervised","slug":"transmorph-transformer-for-unsupervised","title":"TransMorph: Transformer for unsupervised medical image registration","date":"2021-11-19","arxiv_id":"2111.10480","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["junyuchen245/TransMorph_Transformer_for_Medical_Image_Registration"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"zero-shot-certified-defense-against","title":"PatchCensor: Patch Robustness Certification for Transformers via Exhaustive Testing","date":"2021-11-19","arxiv_id":"2111.10481","n_code_links":0,"syntology":null},{"paper":"/paper/clipcap-clip-prefix-for-image-captioning","slug":"clipcap-clip-prefix-for-image-captioning","title":"ClipCap: CLIP Prefix for Image Captioning","date":"2021-11-18","arxiv_id":"2111.09734","n_code_links":4,"syntology":{"ran":6,"of":6,"n_ran_checked":5,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"6 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rmokady/clip_prefix_caption"],"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":["listed","official"]}}},{"paper":"/paper/debertav3-improving-deberta-using-electra","slug":"debertav3-improving-deberta-using-electra","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","date":"2021-11-18","arxiv_id":"2111.09543","n_code_links":3,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["microsoft/DeBERTa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"dynamic-tinybert-boost-tinybert-s-inference","title":"Dynamic-TinyBERT: Boost TinyBERT's Inference Efficiency by Dynamic Sequence Length","date":"2021-11-18","arxiv_id":"2111.09645","n_code_links":0,"syntology":null},{"paper":"/paper/how-emotionally-stable-is-albert-testing-1","slug":"how-emotionally-stable-is-albert-testing-1","title":"How Emotionally Stable is ALBERT? Testing Robustness with Stochastic Weight Averaging on a Sentiment Analysis Task","date":"2021-11-18","arxiv_id":"2111.09612","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-much-do-language-models-copy-from-their","title":"How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN","date":"2021-11-18","arxiv_id":"2111.09509","n_code_links":0,"syntology":null},{"paper":null,"slug":"lanobert-system-log-anomaly-detection-based","title":"LAnoBERT: System Log Anomaly Detection based on BERT Masked Language Model","date":"2021-11-18","arxiv_id":"2111.09564","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-emotion-recognition-on-ravdess","slug":"multimodal-emotion-recognition-on-ravdess","title":"Multimodal Emotion Recognition on RAVDESS Dataset Using Transfer Learning","date":"2021-11-18","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"reference-based-magnetic-resonance-image","title":"Reference-based Magnetic Resonance Image Reconstruction Using Texture Transformer","date":"2021-11-18","arxiv_id":"2111.09492","n_code_links":0,"syntology":null},{"paper":"/paper/restormer-efficient-transformer-for-high","slug":"restormer-efficient-transformer-for-high","title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","date":"2021-11-18","arxiv_id":"2111.09881","n_code_links":13,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["swz30/restormer"],"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":["listed","official"]}}},{"paper":"/paper/robertuito-a-pre-trained-language-model-for","slug":"robertuito-a-pre-trained-language-model-for","title":"RoBERTuito: a pre-trained language model for social media text in Spanish","date":"2021-11-18","arxiv_id":"2111.09453","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["pysentimiento/robertuito"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/swin-transformer-v2-scaling-up-capacity-and","slug":"swin-transformer-v2-scaling-up-capacity-and","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","date":"2021-11-18","arxiv_id":"2111.09883","n_code_links":23,"syntology":{"ran":17,"of":30,"n_ran_checked":17,"n_instrument":0,"unverified":13,"pointer_only":4,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 3 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 13 unverified","official":{"repos":["microsoft/Swin-Transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/the-power-of-selecting-key-blocks-with-local","slug":"the-power-of-selecting-key-blocks-with-local","title":"The Power of Selecting Key Blocks with Local Pre-ranking for Long Document Information Retrieval","date":"2021-11-18","arxiv_id":"2111.09852","n_code_links":1,"syntology":null},{"paper":"/paper/you-only-sample-almost-once-linear-cost-self-1","slug":"you-only-sample-almost-once-linear-cost-self-1","title":"You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling","date":"2021-11-18","arxiv_id":"2111.09714","n_code_links":1,"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":["mlpen/yoso"],"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":"guiding-generative-language-models-for-data","title":"Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification","date":"2021-11-17","arxiv_id":"2111.09064","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-on-transfer-learning-and","title":"A Comparative Study on Transfer Learning and Distance Metrics in Semantic Clustering over the COVID-19 Tweets","date":"2021-11-16","arxiv_id":"2111.08658","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-deep-generative-xai-framework-for-natural","title":"A Deep Generative XAI Framework for Natural Language Inference Explanations Generation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-flexible-multi-task-model-for-bert-serving-1","title":"A Flexible Multi-Task Model for BERT Serving","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-graph-enhanced-bert-model-for-event","title":"A Graph Enhanced BERT Model for Event Prediction","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-sentence-is-worth-128-pseudo-tokens-a","title":"A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence Embeddings","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"13670d66c5569056f778b91af9faa78c6a7d6116595047b9d4d8096eecea9349","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}