{"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/bpe/papers/155","list_of":"/method/bpe","method":"BPE","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":155,"pages_in_order":190,"rows_per_page":100,"rows":[15401,15500],"of":18975,"counts":{"archive_papers_tagged":18975,"with_a_code_link":8675,"where_syntology_ran_a_sample":2895,"not_listed_spam_title":0,"listed":18975,"listed_where_code_ran":2895,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2443,"every_run_a_failure_of_syntologys_instrument":452,"listed_with_a_run_with_no_instrument_failure":2443,"listed_every_run_a_failure_of_syntologys_instrument":452,"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/bpe","prev":"/method/bpe/papers/154","next":"/method/bpe/papers/156","papers":[{"paper":null,"slug":"do-data-based-curricula-work","title":"Do Data-based Curricula Work?","date":"2021-12-13","arxiv_id":"2112.06510","n_code_links":0,"syntology":null},{"paper":"/paper/embracing-single-stride-3d-object-detector","slug":"embracing-single-stride-3d-object-detector","title":"Embracing Single Stride 3D Object Detector with Sparse Transformer","date":"2021-12-13","arxiv_id":"2112.06375","n_code_links":2,"syntology":null},{"paper":"/paper/glam-efficient-scaling-of-language-models","slug":"glam-efficient-scaling-of-language-models","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","date":"2021-12-13","arxiv_id":"2112.06905","n_code_links":0,"syntology":null},{"paper":null,"slug":"hformer-hybrid-cnn-transformer-for-fringe","title":"Hformer: Hybrid CNN-Transformer for Fringe Order Prediction in Phase Unwrapping of Fringe Projection","date":"2021-12-13","arxiv_id":"2112.06759","n_code_links":0,"syntology":null},{"paper":null,"slug":"pedestrian-trajectory-prediction-via-spatial","title":"Pedestrian Trajectory Prediction via Spatial Interaction Transformer Network","date":"2021-12-13","arxiv_id":"2112.06624","n_code_links":0,"syntology":null},{"paper":"/paper/sequential-recommendation-with-bidirectional","slug":"sequential-recommendation-with-bidirectional","title":"Improving Sequential Recommendations via Bidirectional Temporal Data Augmentation with Pre-training","date":"2021-12-13","arxiv_id":"2112.06460","n_code_links":1,"syntology":null},{"paper":"/paper/wechsel-effective-initialization-of-subword-1","slug":"wechsel-effective-initialization-of-subword-1","title":"WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models","date":"2021-12-13","arxiv_id":"2112.06598","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":["cpjku/wechsel"],"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/implicit-transformer-network-for-screen-1","slug":"implicit-transformer-network-for-screen-1","title":"Implicit Transformer Network for Screen Content Image Continuous Super-Resolution","date":"2021-12-12","arxiv_id":"2112.06174","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":3,"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) · 2 unverified","official":{"repos":["codyshen0000/itsrn"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"improving-logical-level-natural-language","title":"Improving Logical-Level Natural Language Generation with Topic-Conditioned Data Augmentation and Logical Form Generation","date":"2021-12-12","arxiv_id":"2112.06240","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-vision-transformers-for-incremental","title":"Improving Vision Transformers for Incremental Learning","date":"2021-12-12","arxiv_id":"2112.06103","n_code_links":0,"syntology":null},{"paper":"/paper/towards-more-efficient-insertion-transformer","slug":"towards-more-efficient-insertion-transformer","title":"Towards More Efficient Insertion Transformer with Fractional Positional Encoding","date":"2021-12-12","arxiv_id":"2112.06295","n_code_links":1,"syntology":null},{"paper":"/paper/composer-compositional-learning-of-group","slug":"composer-compositional-learning-of-group","title":"COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality","date":"2021-12-11","arxiv_id":"2112.05892","n_code_links":1,"syntology":null},{"paper":null,"slug":"attestnet-an-attention-and-subword","title":"AtteSTNet -- An attention and subword tokenization based approach for code-switched text hate speech detection","date":"2021-12-10","arxiv_id":"2112.11479","n_code_links":0,"syntology":null},{"paper":null,"slug":"building-a-great-multi-lingual-teacher-with","title":"Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognition","date":"2021-12-10","arxiv_id":"2112.05820","n_code_links":0,"syntology":null},{"paper":"/paper/couplformer-rethinking-vision-transformer","slug":"couplformer-rethinking-vision-transformer","title":"Couplformer:Rethinking Vision Transformer with Coupling Attention Map","date":"2021-12-10","arxiv_id":"2112.05425","n_code_links":1,"syntology":{"ran":6,"of":12,"n_ran_checked":2,"n_instrument":4,"unverified":6,"pointer_only":12,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","official":{"repos":["wer010/Couplformer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/deep-vit-features-as-dense-visual-descriptors","slug":"deep-vit-features-as-dense-visual-descriptors","title":"Deep ViT Features as Dense Visual Descriptors","date":"2021-12-10","arxiv_id":"2112.05814","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 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) · 1 unverified","official":null}},{"paper":"/paper/pre-training-and-fine-tuning-transformers-for","slug":"pre-training-and-fine-tuning-transformers-for","title":"Self-Supervised Transformers for fMRI representation","date":"2021-12-10","arxiv_id":"2112.05761","n_code_links":2,"syntology":null},{"paper":null,"slug":"vut-versatile-ui-transformer-for-multi-modal","title":"VUT: Versatile UI Transformer for Multi-Modal Multi-Task User Interface Modeling","date":"2021-12-10","arxiv_id":"2112.05692","n_code_links":0,"syntology":null},{"paper":"/paper/3d-medical-point-transformer-introducing","slug":"3d-medical-point-transformer-introducing","title":"3D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud Analysis","date":"2021-12-09","arxiv_id":"2112.04863","n_code_links":1,"syntology":null},{"paper":"/paper/a-bilingual-openworld-video-text-dataset-and","slug":"a-bilingual-openworld-video-text-dataset-and","title":"A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer","date":"2021-12-09","arxiv_id":"2112.04888","n_code_links":3,"syntology":{"ran":16,"of":19,"n_ran_checked":14,"n_instrument":2,"unverified":3,"pointer_only":19,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 9 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["weijiawu/BOVText-Benchmark","weijiawu/transvtspotter"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"extending-adamw-by-leveraging-its-second","title":"Extending AdamW by Leveraging Its Second Moment and Magnitude","date":"2021-12-09","arxiv_id":"2112.06125","n_code_links":0,"syntology":null},{"paper":"/paper/fast-point-transformer","slug":"fast-point-transformer","title":"Fast Point Transformer","date":"2021-12-09","arxiv_id":"2112.04702","n_code_links":1,"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, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["POSTECH-CVLab/FastPointTransformer"],"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/pe-former-pose-estimation-transformer","slug":"pe-former-pose-estimation-transformer","title":"PE-former: Pose Estimation Transformer","date":"2021-12-09","arxiv_id":"2112.04981","n_code_links":1,"syntology":null},{"paper":"/paper/recurrent-glimpse-based-decoder-for-detection","slug":"recurrent-glimpse-based-decoder-for-detection","title":"Recurrent Glimpse-based Decoder for Detection with Transformer","date":"2021-12-09","arxiv_id":"2112.04632","n_code_links":1,"syntology":null},{"paper":"/paper/semi-supervised-medical-image-segmentation-2","slug":"semi-supervised-medical-image-segmentation-2","title":"Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformer","date":"2021-12-09","arxiv_id":"2112.04894","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":1,"n_instrument":4,"unverified":0,"pointer_only":5,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["HiLab-git/SSL4MIS"],"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":null,"slug":"towards-neural-functional-program-evaluation-1","title":"Towards Neural Functional Program Evaluation","date":"2021-12-09","arxiv_id":"2112.04630","n_code_links":0,"syntology":null},{"paper":"/paper/garment4d-garment-reconstruction-from-point-1","slug":"garment4d-garment-reconstruction-from-point-1","title":"Garment4D: Garment Reconstruction from Point Cloud Sequences","date":"2021-12-08","arxiv_id":"2112.04159","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":["hongfz16/garment4d"],"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/improving-language-models-by-retrieving-from","slug":"improving-language-models-by-retrieving-from","title":"Improving language models by retrieving from trillions of tokens","date":"2021-12-08","arxiv_id":"2112.04426","n_code_links":2,"syntology":{"ran":16,"of":23,"n_ran_checked":14,"n_instrument":2,"unverified":7,"pointer_only":3,"phrase":"16 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 3 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","official":null}},{"paper":"/paper/joint-global-and-local-hierarchical-priors","slug":"joint-global-and-local-hierarchical-priors","title":"Joint Global and Local Hierarchical Priors for Learned Image Compression","date":"2021-12-08","arxiv_id":"2112.04487","n_code_links":1,"syntology":null},{"paper":"/paper/staf-a-spatio-temporal-attention-fusion","slug":"staf-a-spatio-temporal-attention-fusion","title":"MASTAF: A Model-Agnostic Spatio-Temporal Attention Fusion Network for Few-shot Video Classification","date":"2021-12-08","arxiv_id":"2112.04585","n_code_links":1,"syntology":null},{"paper":"/paper/transformaly-two-feature-spaces-are-better","slug":"transformaly-two-feature-spaces-are-better","title":"Transformaly -- Two (Feature Spaces) Are Better Than One","date":"2021-12-08","arxiv_id":"2112.04185","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-deep-language-model-to-predict-metabolic","title":"A deep language model to predict metabolic network equilibria","date":"2021-12-07","arxiv_id":"2112.03588","n_code_links":0,"syntology":null},{"paper":"/paper/attention-based-model-and-deep-reinforcement","slug":"attention-based-model-and-deep-reinforcement","title":"Attention-Based Model and Deep Reinforcement Learning for Distribution of Event Processing Tasks","date":"2021-12-07","arxiv_id":"2112.03835","n_code_links":1,"syntology":null},{"paper":"/paper/bootstrapping-vits-towards-liberating-vision","slug":"bootstrapping-vits-towards-liberating-vision","title":"Bootstrapping ViTs: Towards Liberating Vision Transformers from Pre-training","date":"2021-12-07","arxiv_id":"2112.03552","n_code_links":1,"syntology":null},{"paper":"/paper/emulating-spatio-temporal-realizations-of","slug":"emulating-spatio-temporal-realizations-of","title":"Emulating Spatio-Temporal Realizations of Three-Dimensional Isotropic Turbulence via Deep Sequence Learning Models","date":"2021-12-07","arxiv_id":"2112.03469","n_code_links":1,"syntology":null},{"paper":"/paper/regularity-learning-via-explicit-distribution","slug":"regularity-learning-via-explicit-distribution","title":"Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection","date":"2021-12-07","arxiv_id":"2112.03649","n_code_links":1,"syntology":null},{"paper":null,"slug":"relating-transformers-to-models-and-neural-1","title":"Relating transformers to models and neural representations of the hippocampal formation","date":"2021-12-07","arxiv_id":"2112.04035","n_code_links":0,"syntology":null},{"paper":"/paper/ssat-a-symmetric-semantic-aware-transformer","slug":"ssat-a-symmetric-semantic-aware-transformer","title":"SSAT: A Symmetric Semantic-Aware Transformer Network for Makeup Transfer and Removal","date":"2021-12-07","arxiv_id":"2112.03631","n_code_links":2,"syntology":null},{"paper":"/paper/getam-gradient-weighted-element-wise","slug":"getam-gradient-weighted-element-wise","title":"GETAM: Gradient-weighted Element-wise Transformer Attention Map for Weakly-supervised Semantic segmentation","date":"2021-12-06","arxiv_id":"2112.02841","n_code_links":1,"syntology":null},{"paper":"/paper/offline-pre-trained-multi-agent-decision-1","slug":"offline-pre-trained-multi-agent-decision-1","title":"Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Tackles All SMAC Tasks","date":"2021-12-06","arxiv_id":"2112.02845","n_code_links":1,"syntology":null},{"paper":null,"slug":"one-shot-talking-face-generation-from-single","title":"One-shot Talking Face Generation from Single-speaker Audio-Visual Correlation Learning","date":"2021-12-06","arxiv_id":"2112.02749","n_code_links":0,"syntology":null},{"paper":"/paper/pttr-relational-3d-point-cloud-object","slug":"pttr-relational-3d-point-cloud-object","title":"PTTR: Relational 3D Point Cloud Object Tracking with Transformer","date":"2021-12-06","arxiv_id":"2112.02857","n_code_links":1,"syntology":null},{"paper":"/paper/scaling-up-influence-functions","slug":"scaling-up-influence-functions","title":"Scaling Up Influence Functions","date":"2021-12-06","arxiv_id":"2112.03052","n_code_links":2,"syntology":null},{"paper":null,"slug":"stformer-a-noise-aware-efficient-spatio","title":"Spatio-Temporal meets Wavelet: Disentangled Traffic Flow Forecasting via Efficient Spectral Graph Attention Network","date":"2021-12-06","arxiv_id":"2112.02740","n_code_links":0,"syntology":null},{"paper":null,"slug":"team-hitachi-automin-2021-reference-free","title":"Team Hitachi @ AutoMin 2021: Reference-free Automatic Minuting Pipeline with Argument Structure Construction over Topic-based Summarization","date":"2021-12-06","arxiv_id":"2112.02741","n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-token-normalization-improves-vision-1","slug":"dynamic-token-normalization-improves-vision-1","title":"Dynamic Token Normalization Improves Vision Transformers","date":"2021-12-05","arxiv_id":"2112.02624","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result","official":{"repos":["wqshao126/dtn"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gaudi-conversational-interactions-with-deep","title":"Gaudí: Conversational Interactions with Deep Representations to Generate Image Collections","date":"2021-12-05","arxiv_id":"2112.04404","n_code_links":0,"syntology":null},{"paper":"/paper/learning-tracking-representations-via-dual","slug":"learning-tracking-representations-via-dual","title":"Learning Tracking Representations via Dual-Branch Fully Transformer Networks","date":"2021-12-05","arxiv_id":"2112.02571","n_code_links":1,"syntology":null},{"paper":"/paper/pose-guided-feature-disentangling-for","slug":"pose-guided-feature-disentangling-for","title":"Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer","date":"2021-12-05","arxiv_id":"2112.02466","n_code_links":1,"syntology":null},{"paper":"/paper/3rd-place-a-global-and-local-dual-retrieval","slug":"3rd-place-a-global-and-local-dual-retrieval","title":"3rd Place: A Global and Local Dual Retrieval Solution to Facebook AI Image Similarity Challenge","date":"2021-12-04","arxiv_id":"2112.02373","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-multi-strategy-based-pre-training-method","title":"A Multi-Strategy based Pre-Training Method for Cold-Start Recommendation","date":"2021-12-04","arxiv_id":"2112.02275","n_code_links":0,"syntology":null},{"paper":"/paper/lavt-language-aware-vision-transformer-for","slug":"lavt-language-aware-vision-transformer-for","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","date":"2021-12-04","arxiv_id":"2112.02244","n_code_links":1,"syntology":null},{"paper":null,"slug":"representation-learning-for-conversational","title":"Representation Learning for Conversational Data using Discourse Mutual Information Maximization","date":"2021-12-04","arxiv_id":"2112.05787","n_code_links":0,"syntology":null},{"paper":"/paper/u2-former-a-nested-u-shaped-transformer-for","slug":"u2-former-a-nested-u-shaped-transformer-for","title":"U2-Former: A Nested U-shaped Transformer for Image Restoration","date":"2021-12-04","arxiv_id":"2112.02279","n_code_links":0,"syntology":null},{"paper":"/paper/ctin-robust-contextual-transformer-network","slug":"ctin-robust-contextual-transformer-network","title":"CTIN: Robust Contextual Transformer Network for Inertial Navigation","date":"2021-12-03","arxiv_id":"2112.02143","n_code_links":1,"syntology":null},{"paper":null,"slug":"nn-lut-neural-approximation-of-non-linear","title":"NN-LUT: Neural Approximation of Non-Linear Operations for Efficient Transformer Inference","date":"2021-12-03","arxiv_id":"2112.02191","n_code_links":0,"syntology":null},{"paper":null,"slug":"single-shot-black-box-adversarial-attacks","title":"Single-Shot Black-Box Adversarial Attacks Against Malware Detectors: A Causal Language Model Approach","date":"2021-12-03","arxiv_id":"2112.01724","n_code_links":0,"syntology":null},{"paper":"/paper/transzero-attribute-guided-transformer-for","slug":"transzero-attribute-guided-transformer-for","title":"TransZero: Attribute-guided Transformer for Zero-Shot Learning","date":"2021-12-03","arxiv_id":"2112.01683","n_code_links":1,"syntology":null},{"paper":"/paper/masked-attention-mask-transformer-for","slug":"masked-attention-mask-transformer-for","title":"Masked-attention Mask Transformer for Universal Image Segmentation","date":"2021-12-02","arxiv_id":"2112.01527","n_code_links":7,"syntology":{"ran":7,"of":8,"n_ran_checked":5,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"7 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["facebookresearch/Mask2Former"],"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/mtfnet-mutual-transformer-fusion-network-for","slug":"mtfnet-mutual-transformer-fusion-network-for","title":"MutualFormer: Multi-Modality Representation Learning via Cross-Diffusion Attention","date":"2021-12-02","arxiv_id":"2112.01177","n_code_links":1,"syntology":null},{"paper":"/paper/plsum-generating-pt-br-wikipedia-by","slug":"plsum-generating-pt-br-wikipedia-by","title":"PLSUM: Generating PT-BR Wikipedia by Summarizing Multiple Websites","date":"2021-12-02","arxiv_id":"2112.01591","n_code_links":1,"syntology":null},{"paper":null,"slug":"scalevlad-improving-multimodal-sentiment","title":"ScaleVLAD: Improving Multimodal Sentiment Analysis via Multi-Scale Fusion of Locally Descriptors","date":"2021-12-02","arxiv_id":"2112.01368","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-video-transformer","slug":"self-supervised-video-transformer","title":"Self-supervised Video Transformer","date":"2021-12-02","arxiv_id":"2112.01514","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":["kahnchana/svt"],"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/swintrack-a-simple-and-strong-baseline-for","slug":"swintrack-a-simple-and-strong-baseline-for","title":"SwinTrack: A Simple and Strong Baseline for Transformer Tracking","date":"2021-12-02","arxiv_id":"2112.00995","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":["litinglin/swintrack"],"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":"tbn-vit-temporal-bilateral-network-with","title":"TBN-ViT: Temporal Bilateral Network with Vision Transformer for Video Scene Parsing","date":"2021-12-02","arxiv_id":"2112.01033","n_code_links":0,"syntology":null},{"paper":"/paper/tctn-a-3d-temporal-convolutional-transformer","slug":"tctn-a-3d-temporal-convolutional-transformer","title":"PTCT: Patches with 3D-Temporal Convolutional Transformer Network for Precipitation Nowcasting","date":"2021-12-02","arxiv_id":"2112.01085","n_code_links":1,"syntology":null},{"paper":"/paper/uni-perceiver-pre-training-unified","slug":"uni-perceiver-pre-training-unified","title":"Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks","date":"2021-12-02","arxiv_id":"2112.01522","n_code_links":1,"syntology":null},{"paper":null,"slug":"visual-semantic-transformer-for-scene-text","title":"Visual-Semantic Transformer for Scene Text Recognition","date":"2021-12-02","arxiv_id":"2112.00948","n_code_links":0,"syntology":null},{"paper":"/paper/co-evolution-transformer-for-protein-contact","slug":"co-evolution-transformer-for-protein-contact","title":"Co-evolution Transformer for Protein Contact Prediction","date":"2021-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/container-context-aggregation-networks","slug":"container-context-aggregation-networks","title":"Container: Context Aggregation Networks","date":"2021-12-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/controlling-conditional-language-models-with","slug":"controlling-conditional-language-models-with","title":"Controlling Conditional Language Models without Catastrophic Forgetting","date":"2021-12-01","arxiv_id":"2112.00791","n_code_links":2,"syntology":{"ran":7,"of":8,"n_ran_checked":5,"n_instrument":2,"unverified":1,"pointer_only":4,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["naver/gdc"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"cross-view-geo-localization-with-layer-to","title":"Cross-view Geo-localization with Layer-to-Layer Transformer","date":"2021-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"do-transformers-really-perform-badly-for","title":"Do Transformers Really Perform Badly for Graph Representation?","date":"2021-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-split-task-agnostic-vision","title":"Federated Split Task-Agnostic Vision Transformer for COVID-19 CXR Diagnosis","date":"2021-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/focal-attention-for-long-range-interactions","slug":"focal-attention-for-long-range-interactions","title":"Focal Attention for Long-Range Interactions in Vision Transformers","date":"2021-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"gauge-equivariant-transformer","title":"Gauge Equivariant Transformer","date":"2021-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/hrformer-high-resolution-vision-transformer","slug":"hrformer-high-resolution-vision-transformer","title":"HRFormer: High-Resolution Vision Transformer for Dense Predict","date":"2021-12-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/integrating-tree-path-in-transformer-for-code","slug":"integrating-tree-path-in-transformer-for-code","title":"Integrating Tree Path in Transformer for Code Representation","date":"2021-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-view-stereo-with-transformer","title":"Multi-View Stereo with Transformer","date":"2021-12-01","arxiv_id":"2112.00336","n_code_links":0,"syntology":null},{"paper":null,"slug":"raw-nav-merge-seismic-data-to-subsurface","title":"Raw Nav-merge Seismic Data to Subsurface Properties with MLP based Multi-Modal Information Unscrambler","date":"2021-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/score-transformer-generating-musical-score","slug":"score-transformer-generating-musical-score","title":"Score Transformer: Generating Musical Score from Note-level Representation","date":"2021-12-01","arxiv_id":"2112.00355","n_code_links":1,"syntology":null},{"paper":null,"slug":"searching-for-efficient-transformers-for","title":"Searching for Efficient Transformers for Language Modeling","date":"2021-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/shapeshifter-a-parameter-efficient","slug":"shapeshifter-a-parameter-efficient","title":"Shapeshifter: a Parameter-efficient Transformer using Factorized Reshaped Matrices","date":"2021-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"speech-t-transducer-for-text-to-speech-and","title":"Speech-T: Transducer for Text to Speech and Beyond","date":"2021-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/systematic-generalization-with-edge-1","slug":"systematic-generalization-with-edge-1","title":"Systematic Generalization with Edge Transformers","date":"2021-12-01","arxiv_id":"2112.00578","n_code_links":1,"syntology":null},{"paper":null,"slug":"tedge-caching-transformer-based-edge-caching","title":"TEDGE-Caching: Transformer-based Edge Caching Towards 6G Networks","date":"2021-12-01","arxiv_id":"2112.00633","n_code_links":0,"syntology":null},{"paper":"/paper/think-big-teach-small-do-language-models","slug":"think-big-teach-small-do-language-models","title":"Think Big, Teach Small: Do Language Models Distil Occam’s Razor?","date":"2021-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/tuning-large-neural-networks-via-zero-shot","slug":"tuning-large-neural-networks-via-zero-shot","title":"Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","date":"2021-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"unidoc-unified-pretraining-framework-for","title":"UniDoc: Unified Pretraining Framework for Document Understanding","date":"2021-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-transformers-on-word","title":"A Comparative Study of Transformers on Word Sense Disambiguation","date":"2021-11-30","arxiv_id":"2111.15417","n_code_links":0,"syntology":null},{"paper":null,"slug":"chemical-identification-and-indexing-in","title":"Chemical Identification and Indexing in PubMed Articles via BERT and Text-to-Text Approaches","date":"2021-11-30","arxiv_id":"2111.15622","n_code_links":0,"syntology":null},{"paper":"/paper/heat-holistic-edge-attention-transformer-for","slug":"heat-holistic-edge-attention-transformer-for","title":"HEAT: Holistic Edge Attention Transformer for Structured Reconstruction","date":"2021-11-30","arxiv_id":"2111.15143","n_code_links":1,"syntology":null},{"paper":null,"slug":"karl-trans-ner-knowledge-aware-representation","title":"KARL-Trans-NER: Knowledge Aware Representation Learning for Named Entity Recognition using Transformers","date":"2021-11-30","arxiv_id":"2111.15436","n_code_links":0,"syntology":null},{"paper":"/paper/pixelated-butterfly-simple-and-efficient-1","slug":"pixelated-butterfly-simple-and-efficient-1","title":"Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models","date":"2021-11-30","arxiv_id":"2112.00029","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":5,"phrase":"4 ran (of which 4 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; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["HazyResearch/pixelfly"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["found_in_text"]}}},{"paper":"/paper/pyramid-adversarial-training-improves-vit","slug":"pyramid-adversarial-training-improves-vit","title":"Pyramid Adversarial Training Improves ViT Performance","date":"2021-11-30","arxiv_id":"2111.15121","n_code_links":1,"syntology":null},{"paper":"/paper/robust-partial-to-partial-point-cloud","slug":"robust-partial-to-partial-point-cloud","title":"Robust Partial-to-Partial Point Cloud Registration in a Full Range","date":"2021-11-30","arxiv_id":"2111.15606","n_code_links":1,"syntology":null},{"paper":"/paper/shunted-self-attention-via-multi-scale-token","slug":"shunted-self-attention-via-multi-scale-token","title":"Shunted Self-Attention via Multi-Scale Token Aggregation","date":"2021-11-30","arxiv_id":"2111.15193","n_code_links":1,"syntology":null},{"paper":null,"slug":"text-mining-drug-chemical-protein","title":"Text Mining Drug/Chemical-Protein Interactions using an Ensemble of BERT and T5 Based Models","date":"2021-11-30","arxiv_id":"2111.15617","n_code_links":0,"syntology":null},{"paper":null,"slug":"buildformer-automatic-building-extraction","title":"Building extraction with vision transformer","date":"2021-11-29","arxiv_id":"2111.15637","n_code_links":0,"syntology":null},{"paper":"/paper/daformer-improving-network-architectures-and","slug":"daformer-improving-network-architectures-and","title":"DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation","date":"2021-11-29","arxiv_id":"2111.14887","n_code_links":3,"syntology":{"ran":6,"of":6,"n_ran_checked":2,"n_instrument":4,"unverified":0,"pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lhoyer/DAFormer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}}],"record_sha256":"824a5544b6f684cd53e73d732e0e88a26f28e63eee09baf3698f62b7b5cf33a5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}