{"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/91","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":91,"pages_in_order":144,"rows_per_page":100,"rows":[9001,9100],"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/90","next":"/method/label-smoothing/papers/92","papers":[{"paper":null,"slug":"mulgt-multi-task-graph-transformer-with-task","title":"MulGT: Multi-task Graph-Transformer with Task-aware Knowledge Injection and Domain Knowledge-driven Pooling for Whole Slide Image Analysis","date":"2023-02-21","arxiv_id":"2302.10574","n_code_links":0,"syntology":null},{"paper":"/paper/mvmtnet-a-multi-variate-multi-modal","slug":"mvmtnet-a-multi-variate-multi-modal","title":"MVMTnet: A Multi-variate Multi-modal Transformer for Multi-class Classification of Cardiac Irregularities Using ECG Waveforms and Clinical Notes","date":"2023-02-21","arxiv_id":"2302.11021","n_code_links":1,"syntology":null},{"paper":null,"slug":"time-to-embrace-natural-language-processing","title":"Time to Embrace Natural Language Processing (NLP)-based Digital Pathology: Benchmarking NLP- and Convolutional Neural Network-based Deep Learning Pipelines","date":"2023-02-21","arxiv_id":"2302.10406","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-the-advantages-of-transformers-for","slug":"exploring-the-advantages-of-transformers-for","title":"Exploring the Advantages of Transformers for High-Frequency Trading","date":"2023-02-20","arxiv_id":"2302.13850","n_code_links":1,"syntology":null},{"paper":"/paper/friend-recall-in-online-games-via-pre","slug":"friend-recall-in-online-games-via-pre","title":"Friend Ranking in Online Games via Pre-training Edge Transformers","date":"2023-02-20","arxiv_id":"2302.10043","n_code_links":2,"syntology":null},{"paper":null,"slug":"glocalfuse-depth-fusing-transformers-and-cnns","title":"GlocalFuse-Depth: Fusing Transformers and CNNs for All-day Self-supervised Monocular Depth Estimation","date":"2023-02-20","arxiv_id":"2302.09884","n_code_links":0,"syntology":null},{"paper":null,"slug":"optical-transformers","title":"Optical Transformers","date":"2023-02-20","arxiv_id":"2302.10360","n_code_links":0,"syntology":null},{"paper":"/paper/stb-vmm-swin-transformer-based-video-motion","slug":"stb-vmm-swin-transformer-based-video-motion","title":"STB-VMM: Swin Transformer Based Video Motion Magnification","date":"2023-02-20","arxiv_id":"2302.10001","n_code_links":1,"syntology":null},{"paper":"/paper/medvit-a-robust-vision-transformer-for","slug":"medvit-a-robust-vision-transformer-for","title":"MedViT: A Robust Vision Transformer for Generalized Medical Image Classification","date":"2023-02-19","arxiv_id":"2302.09462","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["Omid-Nejati/MedViT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"table-tennis-stroke-detection-and-recognition","title":"Table Tennis Stroke Detection and Recognition Using Ball Trajectory Data","date":"2023-02-19","arxiv_id":"2302.09657","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comprehensive-survey-on-pretrained","title":"A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT","date":"2023-02-18","arxiv_id":"2302.09419","n_code_links":0,"syntology":null},{"paper":null,"slug":"bag-of-tricks-for-effective-language-model","title":"Bag of Tricks for Effective Language Model Pretraining and Downstream Adaptation: A Case Study on GLUE","date":"2023-02-18","arxiv_id":"2302.09268","n_code_links":0,"syntology":null},{"paper":"/paper/bbt-fin-comprehensive-construction-of-chinese","slug":"bbt-fin-comprehensive-construction-of-chinese","title":"BBT-Fin: Comprehensive Construction of Chinese Financial Domain Pre-trained Language Model, Corpus and Benchmark","date":"2023-02-18","arxiv_id":"2302.09432","n_code_links":2,"syntology":null},{"paper":"/paper/how-good-are-gpt-models-at-machine","slug":"how-good-are-gpt-models-at-machine","title":"How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation","date":"2023-02-18","arxiv_id":"2302.09210","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"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":["microsoft/gpt-mt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hyneter-hybrid-network-transformer-for-object","title":"Hyneter: Hybrid Network Transformer for Object Detection","date":"2023-02-18","arxiv_id":"2302.09365","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-attention-memory","title":"Neural Attention Memory","date":"2023-02-18","arxiv_id":"2302.09422","n_code_links":0,"syntology":null},{"paper":"/paper/dtaad-dual-tcn-attention-networks-for-anomaly","slug":"dtaad-dual-tcn-attention-networks-for-anomaly","title":"DTAAD: Dual Tcn-Attention Networks for Anomaly Detection in Multivariate Time Series Data","date":"2023-02-17","arxiv_id":"2302.10753","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt4mia-utilizing-geneative-pre-trained","title":"GPT4MIA: Utilizing Generative Pre-trained Transformer (GPT-3) as A Plug-and-Play Transductive Model for Medical Image Analysis","date":"2023-02-17","arxiv_id":"2302.08722","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-transformer-based-networks-with","title":"Improving Transformer-based Networks With Locality For Automatic Speaker Verification","date":"2023-02-17","arxiv_id":"2302.08639","n_code_links":0,"syntology":null},{"paper":"/paper/like-a-good-nearest-neighbor-practical","slug":"like-a-good-nearest-neighbor-practical","title":"Like a Good Nearest Neighbor: Practical Content Moderation and Text Classification","date":"2023-02-17","arxiv_id":"2302.08957","n_code_links":1,"syntology":null},{"paper":null,"slug":"mcae-masked-contrastive-autoencoder-for-face","title":"EnfoMax: Domain Entropy and Mutual Information Maximization for Domain Generalized Face Anti-spoofing","date":"2023-02-17","arxiv_id":"2302.08674","n_code_links":0,"syntology":null},{"paper":"/paper/multiresolution-graph-transformers-and","slug":"multiresolution-graph-transformers-and","title":"Multiresolution Graph Transformers and Wavelet Positional Encoding for Learning Hierarchical Structures","date":"2023-02-17","arxiv_id":"2302.08647","n_code_links":2,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["hysonlab/multires-graph-transformer","vijaydwivedi75/lrgb"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transformer-based-generative-adversarial-1","title":"Transformer-based Generative Adversarial Networks in Computer Vision: A Comprehensive Survey","date":"2023-02-17","arxiv_id":"2302.08641","n_code_links":0,"syntology":null},{"paper":null,"slug":"vita-a-vision-transformer-inference","title":"ViTA: A Vision Transformer Inference Accelerator for Edge Applications","date":"2023-02-17","arxiv_id":"2302.09108","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-transformer-based-deep-learning-algorithm","title":"A Transformer-based Deep Learning Algorithm to Auto-record Undocumented Clinical One-Lung Ventilation Events","date":"2023-02-16","arxiv_id":"2302.12713","n_code_links":0,"syntology":null},{"paper":null,"slug":"document-flattening-beyond-concatenating","title":"Document Flattening: Beyond Concatenating Context for Document-Level Neural Machine Translation","date":"2023-02-16","arxiv_id":"2302.08079","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-cross-modal-transformer-for-rgb","title":"Hierarchical Cross-modal Transformer for RGB-D Salient Object Detection","date":"2023-02-16","arxiv_id":"2302.08052","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-from-biased-soft-labels","title":"Learning From Biased Soft Labels","date":"2023-02-16","arxiv_id":"2302.08155","n_code_links":0,"syntology":null},{"paper":"/paper/learning-non-local-spatial-angular","slug":"learning-non-local-spatial-angular","title":"Learning Non-Local Spatial-Angular Correlation for Light Field Image Super-Resolution","date":"2023-02-16","arxiv_id":"2302.08058","n_code_links":1,"syntology":null},{"paper":null,"slug":"prompt-tuning-of-deep-neural-networks-for","title":"Prompt Tuning of Deep Neural Networks for Speaker-adaptive Visual Speech Recognition","date":"2023-02-16","arxiv_id":"2302.08102","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-human-motion-forecasting-using","title":"Robust Human Motion Forecasting using Transformer-based Model","date":"2023-02-16","arxiv_id":"2302.08274","n_code_links":0,"syntology":null},{"paper":null,"slug":"short-term-and-long-term-memory-self","title":"Short-term and long-term memory self-attention network for segmentation of tumours in 3D medical images","date":"2023-02-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"speaker-change-detection-for-transformer","title":"Speaker Change Detection for Transformer Transducer ASR","date":"2023-02-16","arxiv_id":"2302.08549","n_code_links":0,"syntology":null},{"paper":"/paper/urcdc-depth-uncertainty-rectified-cross","slug":"urcdc-depth-uncertainty-rectified-cross","title":"URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth Estimation","date":"2023-02-16","arxiv_id":"2302.08149","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":5,"n_instrument":2,"unverified":4,"pointer_only":5,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["shuweishao/urcdc-depth"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/confidence-score-based-speaker-adaptation-of","slug":"confidence-score-based-speaker-adaptation-of","title":"Confidence Score Based Speaker Adaptation of Conformer Speech Recognition Systems","date":"2023-02-15","arxiv_id":"2302.07521","n_code_links":1,"syntology":null},{"paper":null,"slug":"pose-oriented-transformer-with-uncertainty","title":"Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation","date":"2023-02-15","arxiv_id":"2302.07408","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-supervised-learning-for-modeling-gamma","title":"Self-Supervised Learning for Modeling Gamma-ray Variability in Blazars","date":"2023-02-15","arxiv_id":"2302.07700","n_code_links":0,"syntology":null},{"paper":"/paper/speculative-decoding-with-big-little-decoder-1","slug":"speculative-decoding-with-big-little-decoder-1","title":"Speculative Decoding with Big Little Decoder","date":"2023-02-15","arxiv_id":"2302.07863","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["kssteven418/biglittledecoder"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"deep-learning-based-modeling-of-5g-core","title":"Deep Learning-Based Modeling of 5G Core Control Plane for 5G Network Digital Twin","date":"2023-02-14","arxiv_id":"2302.06980","n_code_links":0,"syntology":null},{"paper":"/paper/difffashion-reference-based-fashion-design","slug":"difffashion-reference-based-fashion-design","title":"DiffFashion: Reference-based Fashion Design with Structure-aware Transfer by Diffusion Models","date":"2023-02-14","arxiv_id":"2302.06826","n_code_links":1,"syntology":null},{"paper":"/paper/energy-transformer","slug":"energy-transformer","title":"Energy Transformer","date":"2023-02-14","arxiv_id":"2302.07253","n_code_links":4,"syntology":{"ran":13,"of":13,"n_ran_checked":7,"n_instrument":6,"unverified":0,"pointer_only":3,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","official":{"repos":["bhoov/energy-transformer-jax","zhuergou/energy-transformer-for-graph-anomaly-detection","Lemon-cmd/energy-transformer-graph","Lemon-cmd/energy-transformer-torch"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/polyformer-referring-image-segmentation-as","slug":"polyformer-referring-image-segmentation-as","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","date":"2023-02-14","arxiv_id":"2302.07387","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["amazon-science/polygon-transformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/team-detr-guide-queries-as-a-professional","slug":"team-detr-guide-queries-as-a-professional","title":"Team DETR: Guide Queries as a Professional Team in Detection Transformers","date":"2023-02-14","arxiv_id":"2302.07116","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comprehensive-study-of-modern-architectures","title":"A Comprehensive Study of Modern Architectures and Regularization Approaches on CheXpert5000","date":"2023-02-13","arxiv_id":"2302.06684","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-study-on-relu-and-softmax-in-transformer","title":"A Study on ReLU and Softmax in Transformer","date":"2023-02-13","arxiv_id":"2302.06461","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-unified-view-of-long-sequence-models","title":"A Unified View of Long-Sequence Models towards Modeling Million-Scale Dependencies","date":"2023-02-13","arxiv_id":"2302.06218","n_code_links":0,"syntology":null},{"paper":"/paper/cholectriplet2022-show-me-a-tool-and-tell-me","slug":"cholectriplet2022-show-me-a-tool-and-tell-me","title":"CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection","date":"2023-02-13","arxiv_id":"2302.06294","n_code_links":2,"syntology":null},{"paper":null,"slug":"clip-rr-improved-clip-network-for-relation","title":"VITR: Augmenting Vision Transformers with Relation-Focused Learning for Cross-Modal Information Retrieval","date":"2023-02-13","arxiv_id":"2302.06350","n_code_links":0,"syntology":null},{"paper":null,"slug":"detection-and-segmentation-of-pancreas-using","title":"Detection and Segmentation of Pancreas using Morphological Snakes and Deep Convolutional Neural Networks","date":"2023-02-13","arxiv_id":"2302.06356","n_code_links":0,"syntology":null},{"paper":"/paper/encoding-sentence-position-in-context-aware","slug":"encoding-sentence-position-in-context-aware","title":"Encoding Sentence Position in Context-Aware Neural Machine Translation with Concatenation","date":"2023-02-13","arxiv_id":"2302.06459","n_code_links":1,"syntology":null},{"paper":null,"slug":"linguistic-ambiguity-analysis-in-chatgpt","title":"Linguistic ambiguity analysis in ChatGPT","date":"2023-02-13","arxiv_id":"2302.06426","n_code_links":0,"syntology":null},{"paper":"/paper/one-transformer-for-all-time-series","slug":"one-transformer-for-all-time-series","title":"One Transformer for All Time Series: Representing and Training with Time-Dependent Heterogeneous Tabular Data","date":"2023-02-13","arxiv_id":"2302.06375","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/simple-hardware-efficient-long-convolutions","slug":"simple-hardware-efficient-long-convolutions","title":"Simple Hardware-Efficient Long Convolutions for Sequence Modeling","date":"2023-02-13","arxiv_id":"2302.06646","n_code_links":1,"syntology":null},{"paper":"/paper/towards-local-visual-modeling-for-image","slug":"towards-local-visual-modeling-for-image","title":"Towards Local Visual Modeling for Image Captioning","date":"2023-02-13","arxiv_id":"2302.06098","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-shap-values-and-machine-learning-to","title":"Using SHAP Values and Machine Learning to Understand Trends in the Transient Stability Limit","date":"2023-02-13","arxiv_id":"2302.06274","n_code_links":0,"syntology":null},{"paper":"/paper/generalized-few-shot-continual-learning-with","slug":"generalized-few-shot-continual-learning-with","title":"Generalized Few-Shot Continual Learning with Contrastive Mixture of Adapters","date":"2023-02-12","arxiv_id":"2302.05936","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-models-an-introduction-and","title":"Transformer models: an introduction and catalog","date":"2023-02-12","arxiv_id":"2302.07730","n_code_links":0,"syntology":null},{"paper":"/paper/differentiable-outlier-detection-enable","slug":"differentiable-outlier-detection-enable","title":"Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis","date":"2023-02-11","arxiv_id":"2302.05608","n_code_links":1,"syntology":null},{"paper":"/paper/docile-benchmark-for-document-information","slug":"docile-benchmark-for-document-information","title":"DocILE Benchmark for Document Information Localization and Extraction","date":"2023-02-11","arxiv_id":"2302.05658","n_code_links":1,"syntology":null},{"paper":null,"slug":"best-bert-pre-training-for-sign-language","title":"BEST: BERT Pre-Training for Sign Language Recognition with Coupling Tokenization","date":"2023-02-10","arxiv_id":"2302.05075","n_code_links":0,"syntology":null},{"paper":"/paper/dual-memory-units-with-uncertainty-regulation","slug":"dual-memory-units-with-uncertainty-regulation","title":"Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detection","date":"2023-02-10","arxiv_id":"2302.05160","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 6 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["henrryzh1/UR-DMU"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/effective-document-image-enhancement-using","slug":"effective-document-image-enhancement-using","title":"Effective Document Image Enhancement Using tokens-to-token Transformer Network","date":"2023-02-10","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"patcorrect-non-autoregressive-phoneme","title":"PATCorrect: Non-autoregressive Phoneme-augmented Transformer for ASR Error Correction","date":"2023-02-10","arxiv_id":"2302.05040","n_code_links":0,"syntology":null},{"paper":"/paper/binarized-neural-machine-translation-1","slug":"binarized-neural-machine-translation-1","title":"Binarized Neural Machine Translation","date":"2023-02-09","arxiv_id":"2302.04907","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["google/aqt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/hybrik-transformer","slug":"hybrik-transformer","title":"3D Human Pose and Shape Estimation via HybrIK-Transformer","date":"2023-02-09","arxiv_id":"2302.04774","n_code_links":1,"syntology":null},{"paper":"/paper/reversible-vision-transformers-1","slug":"reversible-vision-transformers-1","title":"Reversible Vision Transformers","date":"2023-02-09","arxiv_id":"2302.04869","n_code_links":4,"syntology":{"ran":24,"of":29,"n_ran_checked":23,"n_instrument":1,"unverified":5,"pointer_only":26,"phrase":"24 ran (of which 5 constructed an object rather than computing a result; 23 with no instrument failure: 0 honoured, 0 violated, 23 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["karttikeya/minrev","facebookresearch/SlowFast","facebookresearch/mvit"],"state":"official (archive's flag): 22 ran","n_ran":22,"n_constructed":5,"n_ran_no_instrument_failure":21,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/adapting-pre-trained-vision-transformers-from","slug":"adapting-pre-trained-vision-transformers-from","title":"Adapting Pre-trained Vision Transformers from 2D to 3D through Weight Inflation Improves Medical Image Segmentation","date":"2023-02-08","arxiv_id":"2302.04303","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-empirical-study-of-uniform-architecture","title":"An Empirical Study of Uniform-Architecture Knowledge Distillation in Document Ranking","date":"2023-02-08","arxiv_id":"2302.04112","n_code_links":0,"syntology":null},{"paper":"/paper/attending-to-graph-transformers","slug":"attending-to-graph-transformers","title":"Attending to Graph Transformers","date":"2023-02-08","arxiv_id":"2302.04181","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":4,"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) · 3 unverified","official":{"repos":["luis-mueller/probing-graph-transformers"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"auto-learning-an-adversarial-process-of-two","title":"EvoText: Enhancing Natural Language Generation Models via Self-Escalation Learning for Up-to-Date Knowledge and Improved Performance","date":"2023-02-08","arxiv_id":"2302.03896","n_code_links":0,"syntology":null},{"paper":"/paper/dual-interest-factorization-heads-attention","slug":"dual-interest-factorization-heads-attention","title":"Dual-interest Factorization-heads Attention for Sequential Recommendation","date":"2023-02-08","arxiv_id":"2302.03965","n_code_links":1,"syntology":null},{"paper":null,"slug":"swincross-cross-modal-swin-transformer-for","title":"SwinCross: Cross-modal Swin Transformer for Head-and-Neck Tumor Segmentation in PET/CT Images","date":"2023-02-08","arxiv_id":"2302.03861","n_code_links":0,"syntology":null},{"paper":"/paper/osrt-omnidirectional-image-super-resolution","slug":"osrt-omnidirectional-image-super-resolution","title":"OSRT: Omnidirectional Image Super-Resolution with Distortion-aware Transformer","date":"2023-02-07","arxiv_id":"2302.03453","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":10,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["fanghua-yu/osrt"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/gps-reviving-the-art-of-message-passing-for","slug":"gps-reviving-the-art-of-message-passing-for","title":"GPS++: Reviving the Art of Message Passing for Molecular Property Prediction","date":"2023-02-06","arxiv_id":"2302.02947","n_code_links":1,"syntology":null},{"paper":"/paper/v1t-large-scale-mouse-v1-response-prediction","slug":"v1t-large-scale-mouse-v1-response-prediction","title":"V1T: large-scale mouse V1 response prediction using a Vision Transformer","date":"2023-02-06","arxiv_id":"2302.03023","n_code_links":1,"syntology":{"ran":16,"of":17,"n_ran_checked":16,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["bryanlimy/V1T"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"learning-to-agree-on-vision-attention-for","title":"Learning to Agree on Vision Attention for Visual Commonsense Reasoning","date":"2023-02-04","arxiv_id":"2302.02117","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-image-deblurring-with-an-efficient","slug":"revisiting-image-deblurring-with-an-efficient","title":"Revisiting Image Deblurring with an Efficient ConvNet","date":"2023-02-04","arxiv_id":"2302.02234","n_code_links":1,"syntology":null},{"paper":null,"slug":"weight-is-attention-all-we-need-aeiuorder","title":"Greedy Ordering of Layer Weight Matrices in Transformers Improves Translation","date":"2023-02-04","arxiv_id":"2302.02123","n_code_links":0,"syntology":null},{"paper":null,"slug":"cfft-gan-cross-domain-feature-fusion","title":"CFFT-GAN: Cross-domain Feature Fusion Transformer for Exemplar-based Image Translation","date":"2023-02-03","arxiv_id":"2302.01608","n_code_links":0,"syntology":null},{"paper":null,"slug":"coinductive-guide-to-inductive-transformer","title":"Coinductive guide to inductive transformer heads","date":"2023-02-03","arxiv_id":"2302.01834","n_code_links":0,"syntology":null},{"paper":null,"slug":"device-depth-and-visual-concepts-aware","title":"DEVICE: DEpth and VIsual ConcEpts Aware Transformer for TextCaps","date":"2023-02-03","arxiv_id":"2302.01540","n_code_links":0,"syntology":null},{"paper":"/paper/dilateformer-multi-scale-dilated-transformer","slug":"dilateformer-multi-scale-dilated-transformer","title":"DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition","date":"2023-02-03","arxiv_id":"2302.01791","n_code_links":1,"syntology":null},{"paper":"/paper/hdformer-high-order-directed-transformer-for","slug":"hdformer-high-order-directed-transformer-for","title":"HDFormer: High-order Directed Transformer for 3D Human Pose Estimation","date":"2023-02-03","arxiv_id":"2302.01825","n_code_links":1,"syntology":{"ran":6,"of":12,"n_ran_checked":4,"n_instrument":2,"unverified":6,"pointer_only":12,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","official":{"repos":["hyer/hdformer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/revisiting-intermediate-layer-distillation","slug":"revisiting-intermediate-layer-distillation","title":"Revisiting Intermediate Layer Distillation for Compressing Language Models: An Overfitting Perspective","date":"2023-02-03","arxiv_id":"2302.01530","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-on-efficient-training-of","title":"A Survey on Efficient Training of Transformers","date":"2023-02-02","arxiv_id":"2302.01107","n_code_links":0,"syntology":null},{"paper":null,"slug":"boosting-low-data-instance-segmentation-by","title":"Boosting Low-Data Instance Segmentation by Unsupervised Pre-training with Saliency Prompt","date":"2023-02-02","arxiv_id":"2302.01171","n_code_links":0,"syntology":null},{"paper":null,"slug":"curriculum-guided-abstractive-summarization-1","title":"Curriculum-Guided Abstractive Summarization","date":"2023-02-02","arxiv_id":"2302.01342","n_code_links":0,"syntology":null},{"paper":"/paper/dual-patchnorm","slug":"dual-patchnorm","title":"Dual PatchNorm","date":"2023-02-02","arxiv_id":"2302.01327","n_code_links":7,"syntology":{"ran":7,"of":9,"n_ran_checked":6,"n_instrument":1,"unverified":2,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 4 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["google-research/big_vision"],"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/fcb-swinv2-transformer-for-polyp-segmentation","slug":"fcb-swinv2-transformer-for-polyp-segmentation","title":"FCB-SwinV2 Transformer for Polyp Segmentation","date":"2023-02-02","arxiv_id":"2302.01027","n_code_links":0,"syntology":null},{"paper":null,"slug":"history-aware-hierarchical-transformer-for","title":"History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue System","date":"2023-02-02","arxiv_id":"2302.00907","n_code_links":0,"syntology":null},{"paper":null,"slug":"idt5-indonesian-version-of-multilingual-t5","title":"idT5: Indonesian Version of Multilingual T5 Transformer","date":"2023-02-02","arxiv_id":"2302.00856","n_code_links":0,"syntology":null},{"paper":null,"slug":"molecular-geometry-aware-transformer-for","title":"Molecular Geometry-aware Transformer for accurate 3D Atomic System modeling","date":"2023-02-02","arxiv_id":"2302.00855","n_code_links":0,"syntology":null},{"paper":"/paper/paced-curriculum-distillation-with-prediction","slug":"paced-curriculum-distillation-with-prediction","title":"Paced-Curriculum Distillation with Prediction and Label Uncertainty for Image Segmentation","date":"2023-02-02","arxiv_id":"2302.01049","n_code_links":1,"syntology":null},{"paper":null,"slug":"vision-transformer-based-feature-extraction","title":"Vision Transformer-based Feature Extraction for Generalized Zero-Shot Learning","date":"2023-02-02","arxiv_id":"2302.00875","n_code_links":0,"syntology":null},{"paper":null,"slug":"clinical-decision-transformer-intended","title":"Clinical Decision Transformer: Intended Treatment Recommendation through Goal Prompting","date":"2023-02-01","arxiv_id":"2302.00612","n_code_links":0,"syntology":null},{"paper":"/paper/feed-forward-blocks-control-contextualization","slug":"feed-forward-blocks-control-contextualization","title":"Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Maps","date":"2023-02-01","arxiv_id":"2302.00456","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gorokoba560/norm-analysis-of-transformer"],"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":"/paper/free-lunch-for-domain-adversarial-training-1","slug":"free-lunch-for-domain-adversarial-training-1","title":"Free Lunch for Domain Adversarial Training: Environment Label Smoothing","date":"2023-02-01","arxiv_id":"2302.00194","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"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":["yfzhang114/Environment-Label-Smoothing"],"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/multispectral-pedestrian-detection-via-1","slug":"multispectral-pedestrian-detection-via-1","title":"MS-DETR: Multispectral Pedestrian Detection Transformer with Loosely Coupled Fusion and Modality-Balanced Optimization","date":"2023-02-01","arxiv_id":"2302.00290","n_code_links":1,"syntology":null},{"paper":"/paper/continuous-spatiotemporal-transformers","slug":"continuous-spatiotemporal-transformers","title":"Continuous Spatiotemporal Transformers","date":"2023-01-31","arxiv_id":"2301.13338","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: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["vandijklab/cst"],"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","unlocated"]}}},{"paper":"/paper/fairness-aware-vision-transformer-via","slug":"fairness-aware-vision-transformer-via","title":"Fairness-aware Vision Transformer via Debiased Self-Attention","date":"2023-01-31","arxiv_id":"2301.13803","n_code_links":1,"syntology":null}],"record_sha256":"3e98d1002dc942e2b907a214a76fbc7e90c15d854bf9c782ad5231f08e3cf9b4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}