{"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/softmax/papers/295","list_of":"/method/softmax","method":"Softmax","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":295,"pages_in_order":375,"rows_per_page":100,"rows":[29401,29500],"of":37443,"counts":{"archive_papers_tagged":37443,"with_a_code_link":15869,"where_syntology_ran_a_sample":4578,"not_listed_spam_title":0,"listed":37443,"listed_where_code_ran":4578,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3835,"every_run_a_failure_of_syntologys_instrument":743,"listed_with_a_run_with_no_instrument_failure":3835,"listed_every_run_a_failure_of_syntologys_instrument":743,"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/softmax","prev":"/method/softmax/papers/294","next":"/method/softmax/papers/296","papers":[{"paper":"/paper/a-flexible-multi-task-model-for-bert-serving","slug":"a-flexible-multi-task-model-for-bert-serving","title":"A Flexible Multi-Task Model for BERT Serving","date":"2021-07-12","arxiv_id":"2107.05377","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-efficient-method-of-detection-of-covid-19","title":"An efficient method of detection of COVID-19 using Mask R-CNN on chest X-Ray images","date":"2021-07-12","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"asking-clarifying-questions-based-on-negative","title":"Asking Clarifying Questions Based on Negative Feedback in Conversational Search","date":"2021-07-12","arxiv_id":"2107.05760","n_code_links":0,"syntology":null},{"paper":"/paper/coberl-contrastive-bert-for-reinforcement","slug":"coberl-contrastive-bert-for-reinforcement","title":"CoBERL: Contrastive BERT for Reinforcement Learning","date":"2021-07-12","arxiv_id":"2107.05431","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["deepmind/dm_control"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/coper-a-query-adaptable-semantics-based","slug":"coper-a-query-adaptable-semantics-based","title":"COPER: a Query-adaptable Semantics-based Search Engine for Persian COVID-19 Articles","date":"2021-07-12","arxiv_id":"2107.05722","n_code_links":1,"syntology":null},{"paper":"/paper/mect-multi-metadata-embedding-based-cross","slug":"mect-multi-metadata-embedding-based-cross","title":"MECT: Multi-Metadata Embedding based Cross-Transformer for Chinese Named Entity Recognition","date":"2021-07-12","arxiv_id":"2107.05418","n_code_links":1,"syntology":null},{"paper":"/paper/midibert-piano-large-scale-pre-training-for","slug":"midibert-piano-large-scale-pre-training-for","title":"BERT-like Pre-training for Symbolic Piano Music Classification Tasks","date":"2021-07-12","arxiv_id":"2107.05223","n_code_links":1,"syntology":null},{"paper":"/paper/moocrep-a-unified-pre-trained-embedding-of","slug":"moocrep-a-unified-pre-trained-embedding-of","title":"MOOCRep: A Unified Pre-trained Embedding of MOOC Entities","date":"2021-07-12","arxiv_id":"2107.05154","n_code_links":1,"syntology":null},{"paper":"/paper/quantifying-explainability-in-nlp-and","slug":"quantifying-explainability-in-nlp-and","title":"Quantifying Explainability in NLP and Analyzing Algorithms for Performance-Explainability Tradeoff","date":"2021-07-12","arxiv_id":"2107.05693","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":1,"n_instrument":3,"unverified":1,"pointer_only":5,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["mnaylor5/quantifying-explainability"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/split-embed-and-merge-an-accurate-table","slug":"split-embed-and-merge-an-accurate-table","title":"Split, embed and merge: An accurate table structure recognizer","date":"2021-07-12","arxiv_id":"2107.05214","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-brownian-motion-in-the-transformer-model","title":"The Brownian motion in the transformer model","date":"2021-07-12","arxiv_id":"2107.05264","n_code_links":0,"syntology":null},{"paper":"/paper/transattunet-multi-level-attention-guided-u","slug":"transattunet-multi-level-attention-guided-u","title":"TransAttUnet: Multi-level Attention-guided U-Net with Transformer for Medical Image Segmentation","date":"2021-07-12","arxiv_id":"2107.05274","n_code_links":1,"syntology":null},{"paper":"/paper/uncertainty-based-query-strategies-for-active","slug":"uncertainty-based-query-strategies-for-active","title":"Revisiting Uncertainty-based Query Strategies for Active Learning with Transformers","date":"2021-07-12","arxiv_id":"2107.05687","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["webis-de/acl22-revisiting-uncertainty-based-query-strategies-for-active-learning-with-transformers"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"visual-transformer-with-statistical-test-for","title":"Visual Transformer with Statistical Test for COVID-19 Classification","date":"2021-07-12","arxiv_id":"2107.05334","n_code_links":0,"syntology":null},{"paper":"/paper/transformers-with-multi-modal-features-and","slug":"transformers-with-multi-modal-features-and","title":"Transformers with multi-modal features and post-fusion context for e-commerce session-based recommendation","date":"2021-07-11","arxiv_id":"2107.05124","n_code_links":0,"syntology":null},{"paper":"/paper/consensual-collaborative-training-and","slug":"consensual-collaborative-training-and","title":"Consensual Collaborative Training And Knowledge Distillation Based Facial Expression Recognition Under Noisy Annotations","date":"2021-07-10","arxiv_id":"2107.04746","n_code_links":3,"syntology":null},{"paper":"/paper/few-shot-domain-adaptation-with-polymorphic","slug":"few-shot-domain-adaptation-with-polymorphic","title":"Few-Shot Domain Adaptation with Polymorphic Transformers","date":"2021-07-10","arxiv_id":"2107.04805","n_code_links":1,"syntology":null},{"paper":null,"slug":"identifying-layers-susceptible-to-adversarial","title":"Identifying Layers Susceptible to Adversarial Attacks","date":"2021-07-10","arxiv_id":"2107.04827","n_code_links":0,"syntology":null},{"paper":null,"slug":"local-to-global-self-attention-in-vision","title":"Local-to-Global Self-Attention in Vision Transformers","date":"2021-07-10","arxiv_id":"2107.04735","n_code_links":0,"syntology":null},{"paper":null,"slug":"noise-stability-regularization-for-improving-1","title":"Noise Stability Regularization for Improving BERT Fine-tuning","date":"2021-07-10","arxiv_id":"2107.04835","n_code_links":0,"syntology":null},{"paper":"/paper/read-attend-and-code-pushing-the-limits-of","slug":"read-attend-and-code-pushing-the-limits-of","title":"Read, Attend, and Code: Pushing the Limits of Medical Codes Prediction from Clinical Notes by Machines","date":"2021-07-10","arxiv_id":"2107.10650","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-initial-investigation-of-non-native-spoken","title":"An Initial Investigation of Non-Native Spoken Question-Answering","date":"2021-07-09","arxiv_id":"2107.04691","n_code_links":0,"syntology":null},{"paper":"/paper/can-deep-neural-networks-predict-data","slug":"can-deep-neural-networks-predict-data","title":"Can Deep Neural Networks Predict Data Correlations from Column Names?","date":"2021-07-09","arxiv_id":"2107.04553","n_code_links":1,"syntology":null},{"paper":"/paper/model-compression-as-constrained-optimization-2","slug":"model-compression-as-constrained-optimization-2","title":"Model compression as constrained optimization, with application to neural nets. Part V: combining compressions","date":"2021-07-09","arxiv_id":"2107.04380","n_code_links":1,"syntology":null},{"paper":"/paper/a-review-of-bangla-natural-language","slug":"a-review-of-bangla-natural-language","title":"A Review of Bangla Natural Language Processing Tasks and the Utility of Transformer Models","date":"2021-07-08","arxiv_id":"2107.03844","n_code_links":2,"syntology":null},{"paper":"/paper/affect-expression-behaviour-analysis-in-the-1","slug":"affect-expression-behaviour-analysis-in-the-1","title":"Affect Expression Behaviour Analysis in the Wild using Consensual Collaborative Training","date":"2021-07-08","arxiv_id":"2107.05736","n_code_links":1,"syntology":null},{"paper":null,"slug":"automated-gain-control-through-deep","title":"Automated Gain Control Through Deep Reinforcement Learning for Downstream Radar Object Detection","date":"2021-07-08","arxiv_id":"2107.03792","n_code_links":0,"syntology":null},{"paper":null,"slug":"calliope-a-polyphonic-music-transformer","title":"Calliope -- A Polyphonic Music Transformer","date":"2021-07-08","arxiv_id":"2107.05546","n_code_links":0,"syntology":null},{"paper":"/paper/eeg-convtransformer-for-single-trial-eeg","slug":"eeg-convtransformer-for-single-trial-eeg","title":"EEG-ConvTransformer for Single-Trial EEG based Visual Stimuli Classification","date":"2021-07-08","arxiv_id":"2107.03983","n_code_links":1,"syntology":null},{"paper":null,"slug":"instance-level-relative-saliency-ranking-with","title":"Instance-Level Relative Saliency Ranking with Graph Reasoning","date":"2021-07-08","arxiv_id":"2107.03824","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-delegate-for-large-scale-vehicle","slug":"learning-to-delegate-for-large-scale-vehicle","title":"Learning to Delegate for Large-scale Vehicle Routing","date":"2021-07-08","arxiv_id":"2107.04139","n_code_links":1,"syntology":{"ran":0,"of":6,"n_ran_checked":0,"n_instrument":0,"unverified":6,"pointer_only":6,"phrase":"0 ran · 6 unverified","official":{"repos":["mit-wu-lab/learning-to-delegate"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":[]}}},{"paper":null,"slug":"malware-classification-using-deep-boosted","title":"Malware Classification Using Deep Boosted Learning","date":"2021-07-08","arxiv_id":"2107.04008","n_code_links":0,"syntology":null},{"paper":null,"slug":"quadruplet-deep-metric-learning-model-for","title":"Deep Metric Learning Model for Imbalanced Fault Diagnosis","date":"2021-07-08","arxiv_id":"2107.03786","n_code_links":0,"syntology":null},{"paper":null,"slug":"bumblebee-a-transformer-for-music","title":"BumbleBee: A Transformer for Music","date":"2021-07-07","arxiv_id":"2107.03443","n_code_links":0,"syntology":null},{"paper":"/paper/can-transformer-models-measure-coherence-in-1","slug":"can-transformer-models-measure-coherence-in-1","title":"Can Transformer Models Measure Coherence In Text? Re-Thinking the Shuffle Test","date":"2021-07-07","arxiv_id":"2107.03448","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-transformer-for-direct-speech","title":"Efficient Transformer for Direct Speech Translation","date":"2021-07-07","arxiv_id":"2107.03069","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-large-language-models-trained-on","slug":"evaluating-large-language-models-trained-on","title":"Evaluating Large Language Models Trained on Code","date":"2021-07-07","arxiv_id":"2107.03374","n_code_links":13,"syntology":{"ran":26,"of":39,"n_ran_checked":24,"n_instrument":2,"unverified":13,"pointer_only":4,"phrase":"26 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 1 honoured, 0 violated, 23 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified","official":{"repos":["openai/human-eval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["found_in_text","listed","official"]}}},{"paper":"/paper/glit-neural-architecture-search-for-global","slug":"glit-neural-architecture-search-for-global","title":"GLiT: Neural Architecture Search for Global and Local Image Transformer","date":"2021-07-07","arxiv_id":"2107.02960","n_code_links":2,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":0,"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) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["bychen515/glit"],"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":"identifying-hijacked-reviews","title":"Identifying Hijacked Reviews","date":"2021-07-07","arxiv_id":"2107.05385","n_code_links":0,"syntology":null},{"paper":null,"slug":"languagerefer-spatial-language-model-for-3d","title":"LanguageRefer: Spatial-Language Model for 3D Visual Grounding","date":"2021-07-07","arxiv_id":"2107.03438","n_code_links":0,"syntology":null},{"paper":"/paper/learning-vision-transformer-with-squeeze-and","slug":"learning-vision-transformer-with-squeeze-and","title":"Learning Vision Transformer with Squeeze and Excitation for Facial Expression Recognition","date":"2021-07-07","arxiv_id":"2107.03107","n_code_links":0,"syntology":null},{"paper":null,"slug":"maccif-tdnn-multi-aspect-aggregation-of","title":"MACCIF-TDNN: Multi aspect aggregation of channel and context interdependence features in TDNN-based speaker verification","date":"2021-07-07","arxiv_id":"2107.03104","n_code_links":0,"syntology":null},{"paper":null,"slug":"model-selection-for-generic-contextual","title":"Model Selection for Generic Contextual Bandits","date":"2021-07-07","arxiv_id":"2107.03455","n_code_links":0,"syntology":null},{"paper":null,"slug":"not-quite-ask-a-librarian-ai-on-the-nature","title":"Not Quite 'Ask a Librarian': AI on the Nature, Value, and Future of LIS","date":"2021-07-07","arxiv_id":"2107.05383","n_code_links":0,"syntology":null},{"paper":null,"slug":"scopeformer-n-cnn-vit-hybrid-model-for","title":"Scopeformer: n-CNN-ViT Hybrid Model for Intracranial Hemorrhage Classification","date":"2021-07-07","arxiv_id":"2107.04575","n_code_links":0,"syntology":null},{"paper":"/paper/trans4trans-efficient-transformer-for","slug":"trans4trans-efficient-transformer-for","title":"Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World","date":"2021-07-07","arxiv_id":"2107.03172","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-network-for-significant-stenosis","slug":"transformer-network-for-significant-stenosis","title":"Transformer Network for Significant Stenosis Detection in CCTA of Coronary Arteries","date":"2021-07-07","arxiv_id":"2107.03035","n_code_links":1,"syntology":null},{"paper":null,"slug":"urban-tree-species-classification-using","title":"Urban Tree Species Classification Using Aerial Imagery","date":"2021-07-07","arxiv_id":"2107.03182","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-size-and-pose-homogenization-with","title":"Automatic size and pose homogenization with spatial transformer network to improve and accelerate pediatric segmentation","date":"2021-07-06","arxiv_id":"2107.02655","n_code_links":0,"syntology":null},{"paper":null,"slug":"covid-19-pneumonia-severity-prediction-using","title":"COVID-19 Pneumonia Severity Prediction using Hybrid Convolution-Attention Neural Architectures","date":"2021-07-06","arxiv_id":"2107.02672","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-hypo-plastic-left-heart-syndrome-in","title":"Detecting Hypo-plastic Left Heart Syndrome in Fetal Ultrasound via Disease-specific Atlas Maps","date":"2021-07-06","arxiv_id":"2107.02643","n_code_links":0,"syntology":null},{"paper":"/paper/feature-fusion-vision-transformer-fine","slug":"feature-fusion-vision-transformer-fine","title":"Feature Fusion Vision Transformer for Fine-Grained Visual Categorization","date":"2021-07-06","arxiv_id":"2107.02341","n_code_links":1,"syntology":null},{"paper":"/paper/point-cloud-registration-using-representative","slug":"point-cloud-registration-using-representative","title":"Point Cloud Registration using Representative Overlapping Points","date":"2021-07-06","arxiv_id":"2107.02583","n_code_links":1,"syntology":{"ran":4,"of":9,"n_ran_checked":4,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["zhulf0804/ROPNet"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"are-standard-object-segmentation-models","title":"Are standard Object Segmentation models sufficient for Learning Affordance Segmentation?","date":"2021-07-05","arxiv_id":"2107.02095","n_code_links":0,"syntology":null},{"paper":null,"slug":"contradiction-detection-in-persian-text","title":"Contradiction Detection in Persian Text","date":"2021-07-05","arxiv_id":"2107.01987","n_code_links":0,"syntology":null},{"paper":"/paper/ernie-3-0-large-scale-knowledge-enhanced-pre","slug":"ernie-3-0-large-scale-knowledge-enhanced-pre","title":"ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","date":"2021-07-05","arxiv_id":"2107.02137","n_code_links":2,"syntology":null},{"paper":null,"slug":"experiments-with-adversarial-attacks-on-text","title":"Experiments with adversarial attacks on text genres","date":"2021-07-05","arxiv_id":"2107.02246","n_code_links":0,"syntology":null},{"paper":"/paper/faster-ltn-a-neuro-symbolic-end-to-end-object","slug":"faster-ltn-a-neuro-symbolic-end-to-end-object","title":"Faster-LTN: a neuro-symbolic, end-to-end object detection architecture","date":"2021-07-05","arxiv_id":"2107.01877","n_code_links":2,"syntology":null},{"paper":null,"slug":"graspme-grasp-manifold-estimator","title":"GraspME -- Grasp Manifold Estimator","date":"2021-07-05","arxiv_id":"2107.01836","n_code_links":0,"syntology":null},{"paper":"/paper/long-short-transformer-efficient-transformers","slug":"long-short-transformer-efficient-transformers","title":"Long-Short Transformer: Efficient Transformers for Language and Vision","date":"2021-07-05","arxiv_id":"2107.02192","n_code_links":3,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["NVIDIA/transformer-ls"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":null,"slug":"on-the-efficiency-of-various-deep-transfer","title":"A Deep Transfer Learning Approach on Identifying Glitch Wave-form in Gravitational Wave Data","date":"2021-07-05","arxiv_id":"2107.01863","n_code_links":0,"syntology":null},{"paper":null,"slug":"test-time-personalization-with-a-transformer","title":"Test-Time Personalization with a Transformer for Human Pose Estimation","date":"2021-07-05","arxiv_id":"2107.02133","n_code_links":0,"syntology":null},{"paper":"/paper/vision-xformers-efficient-attention-for-image","slug":"vision-xformers-efficient-attention-for-image","title":"Vision Xformers: Efficient Attention for Image Classification","date":"2021-07-05","arxiv_id":"2107.02239","n_code_links":2,"syntology":null},{"paper":"/paper/what-helps-transformers-recognize","slug":"what-helps-transformers-recognize","title":"What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition","date":"2021-07-05","arxiv_id":"2107.02294","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-makes-for-hierarchical-vision","title":"What Makes for Hierarchical Vision Transformer?","date":"2021-07-05","arxiv_id":"2107.02174","n_code_links":0,"syntology":null},{"paper":"/paper/covid-vit-classification-of-covid-19-from-ct","slug":"covid-vit-classification-of-covid-19-from-ct","title":"COVID-VIT: Classification of COVID-19 from CT chest images based on vision transformer models","date":"2021-07-04","arxiv_id":"2107.01682","n_code_links":1,"syntology":null},{"paper":null,"slug":"end-to-end-neural-coreference-resolution-1","title":"End-to-end Neural Coreference Resolution Revisited: A Simple yet Effective Baseline","date":"2021-07-04","arxiv_id":"2107.01700","n_code_links":0,"syntology":null},{"paper":"/paper/improved-representation-learning-for-session","slug":"improved-representation-learning-for-session","title":"Introducing Self-Attention to Target Attentive Graph Neural Networks","date":"2021-07-04","arxiv_id":"2107.01516","n_code_links":1,"syntology":null},{"paper":"/paper/kaisa-an-adaptive-second-order-optimizer","slug":"kaisa-an-adaptive-second-order-optimizer","title":"KAISA: An Adaptive Second-Order Optimizer Framework for Deep Neural Networks","date":"2021-07-04","arxiv_id":"2107.01739","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gpauloski/kfac_pytorch"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"can-transformers-jump-around-right-in-natural","title":"Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN","date":"2021-07-03","arxiv_id":"2107.01366","n_code_links":0,"syntology":null},{"paper":null,"slug":"custom-deep-neural-network-for-3d-covid-chest","title":"Custom Deep Neural Network for 3D Covid Chest CT-scan Classification","date":"2021-07-03","arxiv_id":"2107.01456","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-vision-transformers-via-fine","slug":"efficient-vision-transformers-via-fine","title":"Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation","date":"2021-07-03","arxiv_id":"2107.01378","n_code_links":1,"syntology":null},{"paper":"/paper/supervised-off-policy-ranking","slug":"supervised-off-policy-ranking","title":"Supervised Off-Policy Ranking","date":"2021-07-03","arxiv_id":"2107.01360","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["SOPR-T/SOPR-T"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/brain-over-brawn-using-a-stereo-camera-to","slug":"brain-over-brawn-using-a-stereo-camera-to","title":"Brain over Brawn: Using a Stereo Camera to Detect, Track, and Intercept a Faster UAV by Reconstructing the Intruder's Trajectory","date":"2021-07-02","arxiv_id":"2107.00962","n_code_links":1,"syntology":null},{"paper":null,"slug":"case-relation-transformer-a-crossmodal","title":"Case Relation Transformer: A Crossmodal Language Generation Model for Fetching Instructions","date":"2021-07-02","arxiv_id":"2107.00789","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-view-geo-localization-with-evolving","title":"Cross-view Geo-localization with Evolving Transformer","date":"2021-07-02","arxiv_id":"2107.00842","n_code_links":0,"syntology":null},{"paper":"/paper/he-thinks-he-knows-better-than-the-doctors","slug":"he-thinks-he-knows-better-than-the-doctors","title":"He Thinks He Knows Better than the Doctors: BERT for Event Factuality Fails on Pragmatics","date":"2021-07-02","arxiv_id":"2107.00807","n_code_links":1,"syntology":null},{"paper":null,"slug":"language-identification-of-hindi-english","title":"Language Identification of Hindi-English tweets using code-mixed BERT","date":"2021-07-02","arxiv_id":"2107.01202","n_code_links":0,"syntology":null},{"paper":"/paper/online-metro-origin-destination-prediction","slug":"online-metro-origin-destination-prediction","title":"Online Metro Origin-Destination Prediction via Heterogeneous Information Aggregation","date":"2021-07-02","arxiv_id":"2107.00946","n_code_links":1,"syntology":null},{"paper":"/paper/r2d2-recursive-transformer-based-on","slug":"r2d2-recursive-transformer-based-on","title":"R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling","date":"2021-07-02","arxiv_id":"2107.00967","n_code_links":1,"syntology":null},{"paper":"/paper/relaxed-attention-a-simple-method-to-boost","slug":"relaxed-attention-a-simple-method-to-boost","title":"Relaxed Attention: A Simple Method to Boost Performance of End-to-End Automatic Speech Recognition","date":"2021-07-02","arxiv_id":"2107.01275","n_code_links":1,"syntology":null},{"paper":null,"slug":"scarecrow-a-framework-for-scrutinizing","title":"Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Text","date":"2021-07-02","arxiv_id":"2107.01294","n_code_links":0,"syntology":null},{"paper":"/paper/solving-machine-learning-problems","slug":"solving-machine-learning-problems","title":"Solving Machine Learning Problems","date":"2021-07-02","arxiv_id":"2107.01238","n_code_links":1,"syntology":null},{"paper":null,"slug":"target-dependent-uniter-a-transformer-based","title":"Target-dependent UNITER: A Transformer-Based Multimodal Language Comprehension Model for Domestic Service Robots","date":"2021-07-02","arxiv_id":"2107.00811","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-f-a-transformer-network-with","title":"Transformer-F: A Transformer network with effective methods for learning universal sentence representation","date":"2021-07-02","arxiv_id":"2107.00653","n_code_links":0,"syntology":null},{"paper":"/paper/ultrasound-video-transformers-for-cardiac","slug":"ultrasound-video-transformers-for-cardiac","title":"Ultrasound Video Transformers for Cardiac Ejection Fraction Estimation","date":"2021-07-02","arxiv_id":"2107.00977","n_code_links":1,"syntology":null},{"paper":null,"slug":"unsupervised-spoken-utterance-classification","title":"Unsupervised Spoken Utterance Classification","date":"2021-07-02","arxiv_id":"2107.01068","n_code_links":0,"syntology":null},{"paper":"/paper/utnet-a-hybrid-transformer-architecture-for","slug":"utnet-a-hybrid-transformer-architecture-for","title":"UTNet: A Hybrid Transformer Architecture for Medical Image Segmentation","date":"2021-07-02","arxiv_id":"2107.00781","n_code_links":1,"syntology":null},{"paper":null,"slug":"visual-relationship-forecasting-in-videos","title":"Visual Relationship Forecasting in Videos","date":"2021-07-02","arxiv_id":"2107.01181","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-primer-on-pretrained-multilingual-language","title":"A Primer on Pretrained Multilingual Language Models","date":"2021-07-01","arxiv_id":"2107.00676","n_code_links":0,"syntology":null},{"paper":"/paper/action-transformer-a-self-attention-model-for","slug":"action-transformer-a-self-attention-model-for","title":"Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition","date":"2021-07-01","arxiv_id":"2107.00606","n_code_links":4,"syntology":null},{"paper":"/paper/autoformer-searching-transformers-for-visual","slug":"autoformer-searching-transformers-for-visual","title":"AutoFormer: Searching Transformers for Visual Recognition","date":"2021-07-01","arxiv_id":"2107.00651","n_code_links":2,"syntology":null},{"paper":null,"slug":"cross-lingual-adaptation-for-type-inference","title":"Cross-Lingual Transfer Learning for Statistical Type Inference","date":"2021-07-01","arxiv_id":"2107.00157","n_code_links":0,"syntology":null},{"paper":"/paper/cswin-transformer-a-general-vision","slug":"cswin-transformer-a-general-vision","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","date":"2021-07-01","arxiv_id":"2107.00652","n_code_links":7,"syntology":{"ran":4,"of":6,"n_ran_checked":2,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["microsoft/CSWin-Transformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"deep-learning-for-breast-cancer","title":"Deep Learning for Breast Cancer Classification: Enhanced Tangent Function","date":"2021-07-01","arxiv_id":"2108.04663","n_code_links":0,"syntology":null},{"paper":null,"slug":"elbert-fast-albert-with-confidence-window","title":"Elbert: Fast Albert with Confidence-Window Based Early Exit","date":"2021-07-01","arxiv_id":"2107.00175","n_code_links":0,"syntology":null},{"paper":"/paper/focal-self-attention-for-local-global","slug":"focal-self-attention-for-local-global","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","date":"2021-07-01","arxiv_id":"2107.00641","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/Focal-Transformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"glyphcrm-bidirectional-encoder-representation","title":"GlyphCRM: Bidirectional Encoder Representation for Chinese Character with its Glyph","date":"2021-07-01","arxiv_id":"2107.00395","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-domain-agnostic-and-specific","title":"Leveraging Domain Agnostic and Specific Knowledge for Acronym Disambiguation","date":"2021-07-01","arxiv_id":"2107.00316","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-graph-based-transformer-framework","slug":"multimodal-graph-based-transformer-framework","title":"Multimodal Graph-based Transformer Framework for Biomedical Relation Extraction","date":"2021-07-01","arxiv_id":"2107.00596","n_code_links":1,"syntology":null}],"record_sha256":"9792b60d8118778be1dd2e76ee27aa07298e9ed432a496bef6c1fc26118cb6e6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}