{"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/label-smoothing/papers/105","list_of":"/method/label-smoothing","method":"Label Smoothing","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":105,"pages_in_order":144,"rows_per_page":100,"rows":[10401,10500],"of":14327,"counts":{"archive_papers_tagged":14327,"with_a_code_link":6651,"where_syntology_ran_a_sample":2259,"not_listed_spam_title":0,"listed":14327,"listed_where_code_ran":2259,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1920,"every_run_a_failure_of_syntologys_instrument":339,"listed_with_a_run_with_no_instrument_failure":1920,"listed_every_run_a_failure_of_syntologys_instrument":339,"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/label-smoothing","prev":"/method/label-smoothing/papers/104","next":"/method/label-smoothing/papers/106","papers":[{"paper":null,"slug":"set-interdependence-transformer-set-to","title":"Set Interdependence Transformer: Set-to-Sequence Neural Networks for Permutation Learning and Structure Prediction","date":"2022-06-08","arxiv_id":"2206.03720","n_code_links":0,"syntology":null},{"paper":null,"slug":"detr-taming-your-multi-scale-detection","title":"DETR++: Taming Your Multi-Scale Detection Transformer","date":"2022-06-07","arxiv_id":"2206.02977","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-to-dissect-a-muppet-the-structure-of","title":"How to Dissect a Muppet: The Structure of Transformer Embedding Spaces","date":"2022-06-07","arxiv_id":"2206.03529","n_code_links":0,"syntology":null},{"paper":null,"slug":"parotid-gland-mri-segmentation-based-on-swin","title":"Parotid Gland MRI Segmentation Based on Swin-Unet and Multimodal Images","date":"2022-06-07","arxiv_id":"2206.03336","n_code_links":0,"syntology":null},{"paper":null,"slug":"portfolio-transformer-for-attention-based","title":"Portfolio Transformer for Attention-Based Asset Allocation","date":"2022-06-07","arxiv_id":"2206.03246","n_code_links":0,"syntology":null},{"paper":"/paper/raat-relation-augmented-attention-transformer","slug":"raat-relation-augmented-attention-transformer","title":"RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event Extraction","date":"2022-06-07","arxiv_id":"2206.03377","n_code_links":1,"syntology":null},{"paper":null,"slug":"structured-context-transformer-for-generic","title":"Structured Context Transformer for Generic Event Boundary Detection","date":"2022-06-07","arxiv_id":"2206.02985","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-based-personalized-attention","slug":"transformer-based-personalized-attention","title":"Transformer-based Personalized Attention Mechanism for Medical Images with Clinical Records","date":"2022-06-07","arxiv_id":"2206.03003","n_code_links":1,"syntology":null},{"paper":"/paper/tutel-adaptive-mixture-of-experts-at-scale","slug":"tutel-adaptive-mixture-of-experts-at-scale","title":"Tutel: Adaptive Mixture-of-Experts at Scale","date":"2022-06-07","arxiv_id":"2206.03382","n_code_links":2,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"pointer_only":3,"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":["microsoft/Swin-Transformer","microsoft/tutel"],"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":"/paper/a-computational-psycholinguistic-evaluation","slug":"a-computational-psycholinguistic-evaluation","title":"A computational psycholinguistic evaluation of the syntactic abilities of Galician BERT models at the interface of dependency resolution and training time","date":"2022-06-06","arxiv_id":"2206.02440","n_code_links":1,"syntology":null},{"paper":"/paper/mmformer-multimodal-medical-transformer-for","slug":"mmformer-multimodal-medical-transformer-for","title":"mmFormer: Multimodal Medical Transformer for Incomplete Multimodal Learning of Brain Tumor Segmentation","date":"2022-06-06","arxiv_id":"2206.02425","n_code_links":1,"syntology":{"ran":13,"of":17,"n_ran_checked":12,"n_instrument":1,"unverified":4,"pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["yaozhang93/mmformer"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/multi-behavior-sequential-recommendation-with","slug":"multi-behavior-sequential-recommendation-with","title":"Multi-Behavior Sequential Recommendation with Temporal Graph Transformer","date":"2022-06-06","arxiv_id":"2206.02687","n_code_links":1,"syntology":null},{"paper":"/paper/scaling-vision-transformers-to-gigapixel-1","slug":"scaling-vision-transformers-to-gigapixel-1","title":"Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning","date":"2022-06-06","arxiv_id":"2206.02647","n_code_links":2,"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":["mahmoodlab/hipt"],"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":"spam-detection-using-bert","title":"Spam Detection Using BERT","date":"2022-06-06","arxiv_id":"2206.02443","n_code_links":0,"syntology":null},{"paper":null,"slug":"cainnflow-convolutional-block-attention","title":"CAINNFlow: Convolutional block Attention modules and Invertible Neural Networks Flow for anomaly detection and localization tasks","date":"2022-06-04","arxiv_id":"2206.01992","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-modal-clinical-graph-transformer-for-1","title":"Cross-modal Clinical Graph Transformer for Ophthalmic Report Generation","date":"2022-06-04","arxiv_id":"2206.01988","n_code_links":0,"syntology":null},{"paper":null,"slug":"video-based-human-object-interaction","title":"Video-based Human-Object Interaction Detection from Tubelet Tokens","date":"2022-06-04","arxiv_id":"2206.01908","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-transformers-for-behavioural","title":"Exploring Transformers for Behavioural Biometrics: A Case Study in Gait Recognition","date":"2022-06-03","arxiv_id":"2206.01441","n_code_links":0,"syntology":null},{"paper":"/paper/patcher-patch-transformers-with-mixture-of","slug":"patcher-patch-transformers-with-mixture-of","title":"Patcher: Patch Transformers with Mixture of Experts for Precise Medical Image Segmentation","date":"2022-06-03","arxiv_id":"2206.01741","n_code_links":1,"syntology":null},{"paper":null,"slug":"uncertainty-estimation-in-machine-learning","title":"Uncertainty Estimation in Machine Learning","date":"2022-06-03","arxiv_id":"2206.01749","n_code_links":0,"syntology":null},{"paper":null,"slug":"yolov5s-gtb-light-weighted-and-improved","title":"YOLOv5s-GTB: light-weighted and improved YOLOv5s for bridge crack detection","date":"2022-06-03","arxiv_id":"2206.01498","n_code_links":0,"syntology":null},{"paper":null,"slug":"bayesformer-transformer-with-uncertainty","title":"BayesFormer: Transformer with Uncertainty Estimation","date":"2022-06-02","arxiv_id":"2206.00826","n_code_links":0,"syntology":null},{"paper":null,"slug":"cvm-cervix-a-hybrid-cervical-pap-smear-image","title":"CVM-Cervix: A Hybrid Cervical Pap-Smear Image Classification Framework Using CNN, Visual Transformer and Multilayer Perceptron","date":"2022-06-02","arxiv_id":"2206.00971","n_code_links":0,"syntology":null},{"paper":"/paper/deep-transformer-q-networks-for-partially","slug":"deep-transformer-q-networks-for-partially","title":"Deep Transformer Q-Networks for Partially Observable Reinforcement Learning","date":"2022-06-02","arxiv_id":"2206.01078","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":["kevslinger/dtqn"],"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":"/paper/fast-benchmarking-of-accuracy-vs-training","slug":"fast-benchmarking-of-accuracy-vs-training","title":"Fast Benchmarking of Accuracy vs. Training Time with Cyclic Learning Rates","date":"2022-06-02","arxiv_id":"2206.00832","n_code_links":1,"syntology":null},{"paper":"/paper/kpgt-knowledge-guided-pre-training-of-graph","slug":"kpgt-knowledge-guided-pre-training-of-graph","title":"KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction","date":"2022-06-02","arxiv_id":"2206.03364","n_code_links":1,"syntology":null},{"paper":"/paper/missu-3d-medical-image-segmentation-via-self","slug":"missu-3d-medical-image-segmentation-via-self","title":"MISSU: 3D Medical Image Segmentation via Self-distilling TransUNet","date":"2022-06-02","arxiv_id":"2206.00902","n_code_links":1,"syntology":null},{"paper":"/paper/modeling-image-composition-for-complex-scene","slug":"modeling-image-composition-for-complex-scene","title":"Modeling Image Composition for Complex Scene Generation","date":"2022-06-02","arxiv_id":"2206.00923","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["johndreamer/twfa"],"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":["official"]}}},{"paper":"/paper/optimizing-relevance-maps-of-vision","slug":"optimizing-relevance-maps-of-vision","title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","date":"2022-06-02","arxiv_id":"2206.01161","n_code_links":1,"syntology":null},{"paper":null,"slug":"transforming-medical-imaging-with","title":"Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives","date":"2022-06-02","arxiv_id":"2206.01136","n_code_links":0,"syntology":null},{"paper":null,"slug":"vl-beit-generative-vision-language","title":"VL-BEiT: Generative Vision-Language Pretraining","date":"2022-06-02","arxiv_id":"2206.01127","n_code_links":0,"syntology":null},{"paper":"/paper/clip4idc-clip-for-image-difference-captioning","slug":"clip4idc-clip-for-image-difference-captioning","title":"CLIP4IDC: CLIP for Image Difference Captioning","date":"2022-06-01","arxiv_id":"2206.00629","n_code_links":1,"syntology":null},{"paper":null,"slug":"cross-domain-detection-transformer-based-on","title":"Cross-domain Detection Transformer based on Spatial-aware and Semantic-aware Token Alignment","date":"2022-06-01","arxiv_id":"2206.00222","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-self-supervised-vision-pretraining","slug":"efficient-self-supervised-vision-pretraining","title":"Efficient Self-supervised Vision Pretraining with Local Masked Reconstruction","date":"2022-06-01","arxiv_id":"2206.00790","n_code_links":1,"syntology":null},{"paper":"/paper/entity-resolution-with-hierarchical-graph","slug":"entity-resolution-with-hierarchical-graph","title":"Entity Resolution with Hierarchical Graph Attention Networks","date":"2022-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"extreme-floorplan-reconstruction-by-structure","title":"Floorplan Restoration by Structure Hallucinating Transformer Cascades","date":"2022-06-01","arxiv_id":"2206.00645","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-sequential-contexts-using","title":"Learning Sequential Contexts using Transformer for 3D Hand Pose Estimation","date":"2022-06-01","arxiv_id":"2206.00171","n_code_links":0,"syntology":null},{"paper":null,"slug":"research-on-smoking-behavior-detection-system","title":"Research on Smoking Behavior Detection System Based on Deep Learning","date":"2022-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/the-fully-convolutional-transformer-for","slug":"the-fully-convolutional-transformer-for","title":"The Fully Convolutional Transformer for Medical Image Segmentation","date":"2022-06-01","arxiv_id":"2206.00566","n_code_links":2,"syntology":null},{"paper":"/paper/gatenlp-ushef-at-semeval-2022-task-8-entity","slug":"gatenlp-ushef-at-semeval-2022-task-8-entity","title":"GateNLP-UShef at SemEval-2022 Task 8: Entity-Enriched Siamese Transformer for Multilingual News Article Similarity","date":"2022-05-31","arxiv_id":"2205.15812","n_code_links":1,"syntology":null},{"paper":null,"slug":"inferring-3d-change-detection-from-bitemporal","title":"Inferring 3D change detection from bitemporal optical images","date":"2022-05-31","arxiv_id":"2205.15903","n_code_links":0,"syntology":null},{"paper":"/paper/joint-spatial-temporal-and-appearance","slug":"joint-spatial-temporal-and-appearance","title":"Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking","date":"2022-05-31","arxiv_id":"2205.15495","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-represent-programs-with-code","title":"HierarchyNet: Learning to Summarize Source Code with Heterogeneous Representations","date":"2022-05-31","arxiv_id":"2205.15479","n_code_links":0,"syntology":null},{"paper":null,"slug":"multilingual-transformers-for-product","title":"Multilingual Transformers for Product Matching -- Experiments and a New Benchmark in Polish","date":"2022-05-31","arxiv_id":"2205.15712","n_code_links":0,"syntology":null},{"paper":"/paper/surface-analysis-with-vision-transformers","slug":"surface-analysis-with-vision-transformers","title":"Surface Analysis with Vision Transformers","date":"2022-05-31","arxiv_id":"2205.15836","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"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":["metrics-lab/surface-vision-transformers"],"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":null,"slug":"you-can-t-count-on-luck-why-decision","title":"You Can't Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environments","date":"2022-05-31","arxiv_id":"2205.15967","n_code_links":0,"syntology":null},{"paper":"/paper/attention-flows-for-general-transformers","slug":"attention-flows-for-general-transformers","title":"Attention Flows for General Transformers","date":"2022-05-30","arxiv_id":"2205.15389","n_code_links":1,"syntology":null},{"paper":"/paper/can-transformer-be-too-compositional-1","slug":"can-transformer-be-too-compositional-1","title":"Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translation","date":"2022-05-30","arxiv_id":"2205.15301","n_code_links":1,"syntology":null},{"paper":"/paper/few-shot-diffusion-models","slug":"few-shot-diffusion-models","title":"Few-Shot Diffusion Models","date":"2022-05-30","arxiv_id":"2205.15463","n_code_links":1,"syntology":null},{"paper":"/paper/hivit-hierarchical-vision-transformer-meets","slug":"hivit-hierarchical-vision-transformer-meets","title":"HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling","date":"2022-05-30","arxiv_id":"2205.14949","n_code_links":1,"syntology":null},{"paper":"/paper/illumination-adaptive-transformer","slug":"illumination-adaptive-transformer","title":"You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction","date":"2022-05-30","arxiv_id":"2205.14871","n_code_links":1,"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":["cuiziteng/illumination-adaptive-transformer"],"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/multi-agent-reinforcement-learning-is-a","slug":"multi-agent-reinforcement-learning-is-a","title":"Multi-Agent Reinforcement Learning is a Sequence Modeling Problem","date":"2022-05-30","arxiv_id":"2205.14953","n_code_links":1,"syntology":null},{"paper":"/paper/multi-game-decision-transformers","slug":"multi-game-decision-transformers","title":"Multi-Game Decision Transformers","date":"2022-05-30","arxiv_id":"2205.15241","n_code_links":1,"syntology":null},{"paper":"/paper/temporal-latent-bottleneck-synthesis-of-fast","slug":"temporal-latent-bottleneck-synthesis-of-fast","title":"Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning","date":"2022-05-30","arxiv_id":"2205.14794","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":null}},{"paper":"/paper/transformer-with-tree-order-encoding-for","slug":"transformer-with-tree-order-encoding-for","title":"Transformer with Tree-order Encoding for Neural Program Generation","date":"2022-05-30","arxiv_id":"2206.13354","n_code_links":1,"syntology":null},{"paper":null,"slug":"zero-shot-and-few-shot-learning-for-lung","title":"Zero-Shot and Few-Shot Learning for Lung Cancer Multi-Label Classification using Vision Transformer","date":"2022-05-30","arxiv_id":"2205.15290","n_code_links":0,"syntology":null},{"paper":"/paper/efficientvit-enhanced-linear-attention-for","slug":"efficientvit-enhanced-linear-attention-for","title":"EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction","date":"2022-05-29","arxiv_id":"2205.14756","n_code_links":6,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["mit-han-lab/efficientvit","rwightman/pytorch-image-models"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-locality-and-isotropy-in-dialogue","slug":"learning-locality-and-isotropy-in-dialogue","title":"Learning Locality and Isotropy in Dialogue Modeling","date":"2022-05-29","arxiv_id":"2205.14583","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["hahahawu/simdrc"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"sfe-ai-at-semeval-2022-task-11-low-resource","title":"SFE-AI at SemEval-2022 Task 11: Low-Resource Named Entity Recognition using Large Pre-trained Language Models","date":"2022-05-29","arxiv_id":"2205.14660","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformap-transformer-for-memory-access","title":"TransforMAP: Transformer for Memory Access Prediction","date":"2022-05-29","arxiv_id":"2205.14778","n_code_links":0,"syntology":null},{"paper":null,"slug":"approximate-conditional-coverage-via-neural","title":"Approximate Conditional Coverage & Calibration via Neural Model Approximations","date":"2022-05-28","arxiv_id":"2205.14310","n_code_links":0,"syntology":null},{"paper":"/paper/learning-non-autoregressive-models-from-2","slug":"learning-non-autoregressive-models-from-2","title":"Learning Non-Autoregressive Models from Search for Unsupervised Sentence Summarization","date":"2022-05-28","arxiv_id":"2205.14521","n_code_links":1,"syntology":null},{"paper":"/paper/mdmlp-image-classification-from-scratch-on","slug":"mdmlp-image-classification-from-scratch-on","title":"MDMLP: Image Classification from Scratch on Small Datasets with MLP","date":"2022-05-28","arxiv_id":"2205.14477","n_code_links":2,"syntology":null},{"paper":"/paper/multi-task-learning-with-multi-query","slug":"multi-task-learning-with-multi-query","title":"Multi-Task Learning with Multi-Query Transformer for Dense Prediction","date":"2022-05-28","arxiv_id":"2205.14354","n_code_links":1,"syntology":null},{"paper":"/paper/non-stationary-transformers-rethinking-the","slug":"non-stationary-transformers-rethinking-the","title":"Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting","date":"2022-05-28","arxiv_id":"2205.14415","n_code_links":2,"syntology":null},{"paper":"/paper/variational-transformer-a-framework-beyond","slug":"variational-transformer-a-framework-beyond","title":"Variational Transformer: A Framework Beyond the Trade-off between Accuracy and Diversity for Image Captioning","date":"2022-05-28","arxiv_id":"2205.14458","n_code_links":1,"syntology":null},{"paper":null,"slug":"wt-mvsnet-window-based-transformers-for-multi","title":"WT-MVSNet: Window-based Transformers for Multi-view Stereo","date":"2022-05-28","arxiv_id":"2205.14319","n_code_links":0,"syntology":null},{"paper":"/paper/architecture-agnostic-masked-image-modeling","slug":"architecture-agnostic-masked-image-modeling","title":"Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN","date":"2022-05-27","arxiv_id":"2205.13943","n_code_links":3,"syntology":null},{"paper":"/paper/fedformer-contextual-federation-with","slug":"fedformer-contextual-federation-with","title":"FedFormer: Contextual Federation with Attention in Reinforcement Learning","date":"2022-05-27","arxiv_id":"2205.13697","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":2,"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":["liamhebert/FedFormer"],"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/future-transformer-for-long-term-action","slug":"future-transformer-for-long-term-action","title":"Future Transformer for Long-term Action Anticipation","date":"2022-05-27","arxiv_id":"2205.14022","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":8,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/git-a-generative-image-to-text-transformer","slug":"git-a-generative-image-to-text-transformer","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","date":"2022-05-27","arxiv_id":"2205.14100","n_code_links":1,"syntology":{"ran":14,"of":21,"n_ran_checked":14,"n_instrument":0,"unverified":7,"pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","official":{"repos":["microsoft/GenerativeImage2Text"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/momentum-stiefel-optimizer-with-applications","slug":"momentum-stiefel-optimizer-with-applications","title":"Momentum Stiefel Optimizer, with Applications to Suitably-Orthogonal Attention, and Optimal Transport","date":"2022-05-27","arxiv_id":"2205.14173","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["konglk1203/variationalstiefeloptimizer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"nlu-for-game-based-learning-in-real-initial","title":"NLU for Game-based Learning in Real: Initial Evaluations","date":"2022-05-27","arxiv_id":"2205.13754","n_code_links":0,"syntology":null},{"paper":"/paper/patching-leaks-in-the-charformer-for-1","slug":"patching-leaks-in-the-charformer-for-1","title":"Patching Leaks in the Charformer for Efficient Character-Level Generation","date":"2022-05-27","arxiv_id":"2205.14086","n_code_links":1,"syntology":null},{"paper":"/paper/probabilistic-transformer-modelling","slug":"probabilistic-transformer-modelling","title":"Probabilistic Transformer: Modelling Ambiguities and Distributions for RNA Folding and Molecule Design","date":"2022-05-27","arxiv_id":"2205.13927","n_code_links":1,"syntology":null},{"paper":"/paper/transformers-from-an-optimization-perspective","slug":"transformers-from-an-optimization-perspective","title":"Transformers from an Optimization Perspective","date":"2022-05-27","arxiv_id":"2205.13891","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["fftyyy/transformers-from-optimization"],"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":["official"]}}},{"paper":"/paper/turjuman-a-public-toolkit-for-neural-arabic","slug":"turjuman-a-public-toolkit-for-neural-arabic","title":"TURJUMAN: A Public Toolkit for Neural Arabic Machine Translation","date":"2022-05-27","arxiv_id":"2206.03933","n_code_links":1,"syntology":null},{"paper":"/paper/understanding-long-programming-languages-with","slug":"understanding-long-programming-languages-with","title":"Understanding Long Programming Languages with Structure-Aware Sparse Attention","date":"2022-05-27","arxiv_id":"2205.13730","n_code_links":1,"syntology":null},{"paper":"/paper/what-dense-graph-do-you-need-for-self","slug":"what-dense-graph-do-you-need-for-self","title":"What Dense Graph Do You Need for Self-Attention?","date":"2022-05-27","arxiv_id":"2205.14014","n_code_links":1,"syntology":null},{"paper":"/paper/adaptformer-adapting-vision-transformers-for","slug":"adaptformer-adapting-vision-transformers-for","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","date":"2022-05-26","arxiv_id":"2205.13535","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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) · 0 unverified","official":{"repos":["ShoufaChen/AdaptFormer"],"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":"/paper/are-transformers-effective-for-time-series","slug":"are-transformers-effective-for-time-series","title":"Are Transformers Effective for Time Series Forecasting?","date":"2022-05-26","arxiv_id":"2205.13504","n_code_links":10,"syntology":{"ran":13,"of":19,"n_ran_checked":13,"n_instrument":0,"unverified":6,"pointer_only":13,"phrase":"13 ran (of which 4 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["WenjieDu/PyPOTS"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","named_in_paper"]}}},{"paper":null,"slug":"benchmarking-of-deep-learning-models-on-2d","title":"Benchmarking of Deep Learning models on 2D Laminar Flow behind Cylinder","date":"2022-05-26","arxiv_id":"2205.13485","n_code_links":0,"syntology":null},{"paper":null,"slug":"dt-sv-a-transformer-based-time-domain","title":"DT-SV: A Transformer-based Time-domain Approach for Speaker Verification","date":"2022-05-26","arxiv_id":"2205.13249","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-u-transformer-with-boundary-aware","slug":"efficient-u-transformer-with-boundary-aware","title":"Do we really need temporal convolutions in action segmentation?","date":"2022-05-26","arxiv_id":"2205.13425","n_code_links":1,"syntology":null},{"paper":"/paper/green-hierarchical-vision-transformer-for","slug":"green-hierarchical-vision-transformer-for","title":"Green Hierarchical Vision Transformer for Masked Image Modeling","date":"2022-05-26","arxiv_id":"2205.13515","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["layneh/greenmim"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/mixmim-mixed-and-masked-image-modeling-for","slug":"mixmim-mixed-and-masked-image-modeling-for","title":"MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers","date":"2022-05-26","arxiv_id":"2205.13137","n_code_links":1,"syntology":null},{"paper":"/paper/semaffinet-semantic-affine-transformation-for","slug":"semaffinet-semantic-affine-transformation-for","title":"SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation","date":"2022-05-26","arxiv_id":"2205.13490","n_code_links":1,"syntology":{"ran":11,"of":11,"n_ran_checked":11,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wangzy22/SemAffiNet"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-learning-universal-hyperparameter","slug":"towards-learning-universal-hyperparameter","title":"Towards Learning Universal Hyperparameter Optimizers with Transformers","date":"2022-05-26","arxiv_id":"2205.13320","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-for-partial-differential","slug":"transformer-for-partial-differential","title":"Transformer for Partial Differential Equations' Operator Learning","date":"2022-05-26","arxiv_id":"2205.13671","n_code_links":1,"syntology":{"ran":12,"of":13,"n_ran_checked":12,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["BaratiLab/OFormer"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/vidi-a-video-dataset-of-incidents","slug":"vidi-a-video-dataset-of-incidents","title":"VIDI: A Video Dataset of Incidents","date":"2022-05-26","arxiv_id":"2205.13277","n_code_links":1,"syntology":null},{"paper":"/paper/your-transformer-may-not-be-as-powerful-as","slug":"your-transformer-may-not-be-as-powerful-as","title":"Your Transformer May Not be as Powerful as You Expect","date":"2022-05-26","arxiv_id":"2205.13401","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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) · 0 unverified","official":{"repos":["lsj2408/urpe"],"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":"/paper/inception-transformer","slug":"inception-transformer","title":"Inception Transformer","date":"2022-05-25","arxiv_id":"2205.12956","n_code_links":4,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["sail-sg/iformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/mocovit-mobile-convolutional-vision","slug":"mocovit-mobile-convolutional-vision","title":"MoCoViT: Mobile Convolutional Vision Transformer","date":"2022-05-25","arxiv_id":"2205.12635","n_code_links":1,"syntology":null},{"paper":"/paper/transcormer-transformer-for-sentence-scoring","slug":"transcormer-transformer-for-sentence-scoring","title":"Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling","date":"2022-05-25","arxiv_id":"2205.12986","n_code_links":1,"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":null}},{"paper":"/paper/vtp-volumetric-transformer-for-multi-view","slug":"vtp-volumetric-transformer-for-multi-view","title":"VTP: Volumetric Transformer for Multi-view Multi-person 3D Pose Estimation","date":"2022-05-25","arxiv_id":"2205.12602","n_code_links":0,"syntology":null},{"paper":"/paper/adamix-mixture-of-adapter-for-parameter","slug":"adamix-mixture-of-adapter-for-parameter","title":"AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning","date":"2022-05-24","arxiv_id":"2205.12410","n_code_links":1,"syntology":null},{"paper":"/paper/history-compression-via-language-models-in","slug":"history-compression-via-language-models-in","title":"History Compression via Language Models in Reinforcement Learning","date":"2022-05-24","arxiv_id":"2205.12258","n_code_links":2,"syntology":{"ran":4,"of":6,"n_ran_checked":3,"n_instrument":1,"unverified":2,"pointer_only":6,"phrase":"4 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ml-jku/helm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"multi-level-modeling-units-for-end-to-end","title":"Multi-Level Modeling Units for End-to-End Mandarin Speech Recognition","date":"2022-05-24","arxiv_id":"2205.11998","n_code_links":0,"syntology":null},{"paper":null,"slug":"symbolic-expression-transformer-a-computer","title":"Symbolic Expression Transformer: A Computer Vision Approach for Symbolic Regression","date":"2022-05-24","arxiv_id":"2205.11798","n_code_links":0,"syntology":null},{"paper":null,"slug":"umsnet-an-universal-multi-sensor-network-for","title":"UMSNet: An Universal Multi-sensor Network for Human Activity Recognition","date":"2022-05-24","arxiv_id":"2205.11756","n_code_links":0,"syntology":null}],"record_sha256":"89fe752ae5ebeeab0be5132fdaa0492516dcb06e916c4ed60417a492b545e4d0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}