{"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/transformer/papers/110","list_of":"/method/transformer","method":"Transformer","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":110,"pages_in_order":140,"rows_per_page":100,"rows":[10901,11000],"of":13999,"counts":{"archive_papers_tagged":13999,"with_a_code_link":6572,"where_syntology_ran_a_sample":2248,"not_listed_spam_title":0,"listed":13999,"listed_where_code_ran":2248,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1919,"every_run_a_failure_of_syntologys_instrument":329,"listed_with_a_run_with_no_instrument_failure":1919,"listed_every_run_a_failure_of_syntologys_instrument":329,"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/transformer","prev":"/method/transformer/papers/109","next":"/method/transformer/papers/111","papers":[{"paper":null,"slug":"lmn-at-semeval-2022-task-11-a-transformer","title":"LMN at SemEval-2022 Task 11: A Transformer-based System for English Named Entity Recognition","date":"2022-02-13","arxiv_id":"2203.03546","n_code_links":0,"syntology":null},{"paper":null,"slug":"benchmark-assessment-for-deepspeed","title":"Benchmark Assessment for DeepSpeed Optimization Library","date":"2022-02-12","arxiv_id":"2202.12831","n_code_links":0,"syntology":null},{"paper":"/paper/multi-direction-and-multi-scale-pyramid-in","slug":"multi-direction-and-multi-scale-pyramid-in","title":"Multi-direction and Multi-scale Pyramid in Transformer for Video-based Pedestrian Retrieval","date":"2022-02-12","arxiv_id":"2202.06014","n_code_links":1,"syntology":null},{"paper":"/paper/multi-direction-and-multi-scale-pyramid-in-1","slug":"multi-direction-and-multi-scale-pyramid-in-1","title":"Multi-direction and Multi-scale Pyramid in Transformer for Video-based Pedestrian Retrieval","date":"2022-02-12","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"including-facial-expressions-in-contextual","title":"Including Facial Expressions in Contextual Embeddings for Sign Language Generation","date":"2022-02-11","arxiv_id":"2202.05383","n_code_links":0,"syntology":null},{"paper":"/paper/aa-transunet-attention-augmented-transunet","slug":"aa-transunet-attention-augmented-transunet","title":"AA-TransUNet: Attention Augmented TransUNet For Nowcasting Tasks","date":"2022-02-10","arxiv_id":"2202.04996","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-volcspeech-system-for-the-icassp-2022","title":"The Volcspeech system for the ICASSP 2022 multi-channel multi-party meeting transcription challenge","date":"2022-02-09","arxiv_id":"2202.04261","n_code_links":0,"syntology":null},{"paper":null,"slug":"calm-contrastive-aligned-audio-language","title":"CALM: Contrastive Aligned Audio-Language Multirate and Multimodal Representations","date":"2022-02-08","arxiv_id":"2202.03587","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficacy-of-transformer-networks-for","title":"Efficacy of Transformer Networks for Classification of Raw EEG Data","date":"2022-02-08","arxiv_id":"2202.05170","n_code_links":0,"syntology":null},{"paper":"/paper/particle-transformer-for-jet-tagging","slug":"particle-transformer-for-jet-tagging","title":"Particle Transformer for Jet Tagging","date":"2022-02-08","arxiv_id":"2202.03772","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":["jet-universe/particle_transformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/data2vec-a-general-framework-for-self-1","slug":"data2vec-a-general-framework-for-self-1","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","date":"2022-02-07","arxiv_id":"2202.03555","n_code_links":12,"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":["pytorch/fairseq"],"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/efficient-adapter-transfer-of-self-supervised","slug":"efficient-adapter-transfer-of-self-supervised","title":"Efficient Adapter Transfer of Self-Supervised Speech Models for Automatic Speech Recognition","date":"2022-02-07","arxiv_id":"2202.03218","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":null}},{"paper":null,"slug":"recent-trends-in-2d-object-detection-and","title":"Recent Trends in 2D Object Detection and Applications in Video Event Recognition","date":"2022-02-07","arxiv_id":"2202.03206","n_code_links":0,"syntology":null},{"paper":"/paper/structure-aware-transformer-for-graph","slug":"structure-aware-transformer-for-graph","title":"Structure-Aware Transformer for Graph Representation Learning","date":"2022-02-07","arxiv_id":"2202.03036","n_code_links":3,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["borgwardtlab/sat"],"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":["listed","official"]}}},{"paper":"/paper/user-satisfaction-estimation-with-sequential","slug":"user-satisfaction-estimation-with-sequential","title":"User Satisfaction Estimation with Sequential Dialogue Act Modeling in Goal-oriented Conversational Systems","date":"2022-02-07","arxiv_id":"2202.02912","n_code_links":1,"syntology":null},{"paper":"/paper/no-parameters-left-behind-sensitivity-guided-1","slug":"no-parameters-left-behind-sensitivity-guided-1","title":"No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models","date":"2022-02-06","arxiv_id":"2202.02664","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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["cliang1453/sage"],"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":null,"slug":"pre-trained-neural-language-models-for","title":"Pre-Trained Neural Language Models for Automatic Mobile App User Feedback Answer Generation","date":"2022-02-04","arxiv_id":"2202.02294","n_code_links":0,"syntology":null},{"paper":"/paper/supervised-contrastive-learning-for-product","slug":"supervised-contrastive-learning-for-product","title":"Supervised Contrastive Learning for Product Matching","date":"2022-02-04","arxiv_id":"2202.02098","n_code_links":1,"syntology":null},{"paper":null,"slug":"transfollower-long-sequence-car-following","title":"TransFollower: Long-Sequence Car-Following Trajectory Prediction through Transformer","date":"2022-02-04","arxiv_id":"2202.03183","n_code_links":0,"syntology":null},{"paper":null,"slug":"brain-cancer-survival-prediction-on-treatment","title":"Brain Cancer Survival Prediction on Treatment-na ive MRI using Deep Anchor Attention Learning with Vision Transformer","date":"2022-02-03","arxiv_id":"2202.01857","n_code_links":0,"syntology":null},{"paper":"/paper/etsformer-exponential-smoothing-transformers","slug":"etsformer-exponential-smoothing-transformers","title":"ETSformer: Exponential Smoothing Transformers for Time-series Forecasting","date":"2022-02-03","arxiv_id":"2202.01381","n_code_links":3,"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: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 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":"/paper/can-transformers-be-strong-treatment-effect","slug":"can-transformers-be-strong-treatment-effect","title":"Exploring Transformer Backbones for Heterogeneous Treatment Effect Estimation","date":"2022-02-02","arxiv_id":"2202.01336","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hlzhang109/transtee"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/alphadesign-a-graph-protein-design-method-and","slug":"alphadesign-a-graph-protein-design-method-and","title":"AlphaDesign: A graph protein design method and benchmark on AlphaFoldDB","date":"2022-02-01","arxiv_id":"2202.01079","n_code_links":1,"syntology":null},{"paper":"/paper/atek-augmenting-transformers-with-expert","slug":"atek-augmenting-transformers-with-expert","title":"LayoutEnhancer: Generating Good Indoor Layouts from Imperfect Data","date":"2022-02-01","arxiv_id":"2202.00185","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["kleimertu/humancentriclayouts"],"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":"/paper/is-the-performance-of-my-deep-network-too","slug":"is-the-performance-of-my-deep-network-too","title":"Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification","date":"2022-02-01","arxiv_id":"2202.00395","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["takashiishida/irreducible"],"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/local-feature-matching-with-transformers-for","slug":"local-feature-matching-with-transformers-for","title":"Local Feature Matching with Transformers for low-end devices","date":"2022-02-01","arxiv_id":"2202.00770","n_code_links":1,"syntology":null},{"paper":"/paper/regression-transformer-concurrent-conditional","slug":"regression-transformer-concurrent-conditional","title":"Regression Transformer: Concurrent sequence regression and generation for molecular language modeling","date":"2022-02-01","arxiv_id":"2202.01338","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ibm/regression-transformer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transformer-based-models-of-text","title":"Transformer-based Models of Text Normalization for Speech Applications","date":"2022-02-01","arxiv_id":"2202.00153","n_code_links":0,"syntology":null},{"paper":"/paper/boat-bilateral-local-attention-vision","slug":"boat-bilateral-local-attention-vision","title":"BOAT: Bilateral Local Attention Vision Transformer","date":"2022-01-31","arxiv_id":"2201.13027","n_code_links":1,"syntology":null},{"paper":null,"slug":"fast-monte-carlo-approximation-of-the","title":"Fast Monte-Carlo Approximation of the Attention Mechanism","date":"2022-01-30","arxiv_id":"2201.12854","n_code_links":0,"syntology":null},{"paper":"/paper/fedformer-frequency-enhanced-decomposed","slug":"fedformer-frequency-enhanced-decomposed","title":"FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting","date":"2022-01-30","arxiv_id":"2201.12740","n_code_links":3,"syntology":{"ran":14,"of":18,"n_ran_checked":11,"n_instrument":3,"unverified":4,"pointer_only":0,"phrase":"14 ran (of which 8 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["WenjieDu/PyPOTS"],"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/graph-self-attention-for-learning-graph","slug":"graph-self-attention-for-learning-graph","title":"GRPE: Relative Positional Encoding for Graph Transformer","date":"2022-01-30","arxiv_id":"2201.12787","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["lenscloth/grpe"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/n-hits-neural-hierarchical-interpolation-for","slug":"n-hits-neural-hierarchical-interpolation-for","title":"N-HiTS: Neural Hierarchical Interpolation for Time Series Forecasting","date":"2022-01-30","arxiv_id":"2201.12886","n_code_links":4,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["cchallu/n-hits"],"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/transbtsv2-wider-instead-of-deeper","slug":"transbtsv2-wider-instead-of-deeper","title":"TransBTSV2: Towards Better and More Efficient Volumetric Segmentation of Medical Images","date":"2022-01-30","arxiv_id":"2201.12785","n_code_links":2,"syntology":null},{"paper":null,"slug":"autodistil-few-shot-task-agnostic-neural","title":"AutoDistil: Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models","date":"2022-01-29","arxiv_id":"2201.12507","n_code_links":0,"syntology":null},{"paper":"/paper/decepticons-corrupted-transformers-breach","slug":"decepticons-corrupted-transformers-breach","title":"Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models","date":"2022-01-29","arxiv_id":"2201.12675","n_code_links":1,"syntology":null},{"paper":null,"slug":"research-on-patch-attentive-neural-process","title":"Research on Patch Attentive Neural Process","date":"2022-01-29","arxiv_id":"2202.01884","n_code_links":0,"syntology":null},{"paper":null,"slug":"rewiring-with-positional-encodings-for-graph","title":"Rewiring with Positional Encodings for Graph Neural Networks","date":"2022-01-29","arxiv_id":"2201.12674","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-robustness-of-3d-point-cloud","slug":"benchmarking-robustness-of-3d-point-cloud","title":"Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions","date":"2022-01-28","arxiv_id":"2201.12296","n_code_links":6,"syntology":{"ran":24,"of":29,"n_ran_checked":16,"n_instrument":8,"unverified":5,"pointer_only":7,"phrase":"24 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 0 violated, 14 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified","official":{"repos":["jiachens/ModelNet40-C"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/can-wikipedia-help-offline-reinforcement","slug":"can-wikipedia-help-offline-reinforcement","title":"Can Wikipedia Help Offline Reinforcement Learning?","date":"2022-01-28","arxiv_id":"2201.12122","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["machelreid/can-wikipedia-help-offline-rl"],"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/dab-detr-dynamic-anchor-boxes-are-better-1","slug":"dab-detr-dynamic-anchor-boxes-are-better-1","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","date":"2022-01-28","arxiv_id":"2201.12329","n_code_links":8,"syntology":{"ran":6,"of":11,"n_ran_checked":4,"n_instrument":2,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["slongliu/dab-detr"],"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":"o-vit-orthogonal-vision-transformer","title":"O-ViT: Orthogonal Vision Transformer","date":"2022-01-28","arxiv_id":"2201.12133","n_code_links":0,"syntology":null},{"paper":"/paper/vrt-a-video-restoration-transformer","slug":"vrt-a-video-restoration-transformer","title":"VRT: A Video Restoration Transformer","date":"2022-01-28","arxiv_id":"2201.12288","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":0,"n_instrument":4,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["jingyunliang/vrt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/generalised-image-outpainting-with-u","slug":"generalised-image-outpainting-with-u","title":"Generalised Image Outpainting with U-Transformer","date":"2022-01-27","arxiv_id":"2201.11403","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-module-networks-for-systematic","slug":"transformer-module-networks-for-systematic","title":"Transformer Module Networks for Systematic Generalization in Visual Question Answering","date":"2022-01-27","arxiv_id":"2201.11316","n_code_links":1,"syntology":null},{"paper":null,"slug":"dnnfuser-generative-pre-trained-transformer","title":"DNNFuser: Generative Pre-Trained Transformer as a Generalized Mapper for Layer Fusion in DNN Accelerators","date":"2022-01-26","arxiv_id":"2201.11218","n_code_links":0,"syntology":null},{"paper":null,"slug":"dual-decoder-transformer-for-end-to-end","title":"On the Effectiveness of Pinyin-Character Dual-Decoding for End-to-End Mandarin Chinese ASR","date":"2022-01-26","arxiv_id":"2201.10792","n_code_links":0,"syntology":null},{"paper":"/paper/dual-tasks-siamese-transformer-framework-for","slug":"dual-tasks-siamese-transformer-framework-for","title":"Dual-Tasks Siamese Transformer Framework for Building Damage Assessment","date":"2022-01-26","arxiv_id":"2201.10953","n_code_links":0,"syntology":null},{"paper":"/paper/neural-grapheme-to-phoneme-conversion-with","slug":"neural-grapheme-to-phoneme-conversion-with","title":"Neural Grapheme-to-Phoneme Conversion with Pre-trained Grapheme Models","date":"2022-01-26","arxiv_id":"2201.10716","n_code_links":1,"syntology":null},{"paper":"/paper/predicting-knee-osteoarthritis-progression","slug":"predicting-knee-osteoarthritis-progression","title":"Predicting Knee Osteoarthritis Progression from Structural MRI using Deep Learning","date":"2022-01-26","arxiv_id":"2201.10849","n_code_links":1,"syntology":null},{"paper":null,"slug":"transppg-two-stream-transformer-for-remote","title":"TransPPG: Two-stream Transformer for Remote Heart Rate Estimate","date":"2022-01-26","arxiv_id":"2201.10873","n_code_links":0,"syntology":null},{"paper":"/paper/when-shift-operation-meets-vision-transformer","slug":"when-shift-operation-meets-vision-transformer","title":"When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism","date":"2022-01-26","arxiv_id":"2201.10801","n_code_links":2,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 6 samples that ran constructed an object rather than computing a result","official":{"repos":["microsoft/SPACH"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":6,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/convolutional-xformers-for-vision","slug":"convolutional-xformers-for-vision","title":"Convolutional Xformers for Vision","date":"2022-01-25","arxiv_id":"2201.10271","n_code_links":1,"syntology":null},{"paper":"/paper/explore-and-match-end-to-end-video-grounding","slug":"explore-and-match-end-to-end-video-grounding","title":"Explore-And-Match: Bridging Proposal-Based and Proposal-Free With Transformer for Sentence Grounding in Videos","date":"2022-01-25","arxiv_id":"2201.10168","n_code_links":1,"syntology":null},{"paper":null,"slug":"masked-transformer-for-neighhourhood-aware","title":"Neighbour Interaction based Click-Through Rate Prediction via Graph-masked Transformer","date":"2022-01-25","arxiv_id":"2201.13311","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimal-transport-based-data-augmentation-for","title":"Cardiac Disease Diagnosis on Imbalanced Electrocardiography Data Through Optimal Transport Augmentation","date":"2022-01-25","arxiv_id":"2202.00567","n_code_links":0,"syntology":null},{"paper":"/paper/vit-hgr-vision-transformer-based-hand-gesture","slug":"vit-hgr-vision-transformer-based-hand-gesture","title":"ViT-HGR: Vision Transformer-based Hand Gesture Recognition from High Density Surface EMG Signals","date":"2022-01-25","arxiv_id":"2201.10060","n_code_links":1,"syntology":null},{"paper":null,"slug":"zero-shot-sketch-based-image-retrieval-using","title":"Zero-Shot Sketch Based Image Retrieval using Graph Transformer","date":"2022-01-25","arxiv_id":"2201.10185","n_code_links":0,"syntology":null},{"paper":"/paper/improving-chest-x-ray-report-generation-by","slug":"improving-chest-x-ray-report-generation-by","title":"Improving Chest X-Ray Report Generation by Leveraging Warm Starting","date":"2022-01-24","arxiv_id":"2201.09405","n_code_links":1,"syntology":null},{"paper":"/paper/patches-are-all-you-need-1","slug":"patches-are-all-you-need-1","title":"Patches Are All You Need?","date":"2022-01-24","arxiv_id":"2201.09792","n_code_links":12,"syntology":{"ran":8,"of":8,"n_ran_checked":7,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 5 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["locuslab/convmixer","tmp-iclr/convmixer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/transformers-in-medical-imaging-a-survey","slug":"transformers-in-medical-imaging-a-survey","title":"Transformers in Medical Imaging: A Survey","date":"2022-01-24","arxiv_id":"2201.09873","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-pre-trained-audio-visual-transformer-for","title":"A Pre-trained Audio-Visual Transformer for Emotion Recognition","date":"2022-01-23","arxiv_id":"2201.09165","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-for-deep-rgbt-tracking","title":"A Survey for Deep RGBT Tracking","date":"2022-01-23","arxiv_id":"2201.09296","n_code_links":0,"syntology":null},{"paper":"/paper/investigating-expressiveness-of-transformer","slug":"investigating-expressiveness-of-transformer","title":"How Expressive are Transformers in Spectral Domain for Graphs?","date":"2022-01-23","arxiv_id":"2201.09332","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":["ansonb/FeTA_TMLR"],"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/reconformer-accelerated-mri-reconstruction","slug":"reconformer-accelerated-mri-reconstruction","title":"ReconFormer: Accelerated MRI Reconstruction Using Recurrent Transformer","date":"2022-01-23","arxiv_id":"2201.09376","n_code_links":1,"syntology":null},{"paper":null,"slug":"dual-flattening-transformers-through","title":"Dual-Flattening Transformers through Decomposed Row and Column Queries for Semantic Segmentation","date":"2022-01-22","arxiv_id":"2201.09139","n_code_links":0,"syntology":null},{"paper":"/paper/representing-long-range-context-for-graph-1","slug":"representing-long-range-context-for-graph-1","title":"Representing Long-Range Context for Graph Neural Networks with Global Attention","date":"2022-01-21","arxiv_id":"2201.08821","n_code_links":1,"syntology":{"ran":7,"of":14,"n_ran_checked":6,"n_instrument":1,"unverified":7,"pointer_only":0,"phrase":"7 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","official":{"repos":["ucbrise/graphtrans"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/memvit-memory-augmented-multiscale-vision","slug":"memvit-memory-augmented-multiscale-vision","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","date":"2022-01-20","arxiv_id":"2201.08383","n_code_links":1,"syntology":null},{"paper":null,"slug":"meta-learning-for-code-summarization-1","title":"Meta Learning for Code Summarization","date":"2022-01-20","arxiv_id":"2201.08310","n_code_links":0,"syntology":null},{"paper":"/paper/poseur-direct-human-pose-regression-with","slug":"poseur-direct-human-pose-regression-with","title":"Poseur: Direct Human Pose Regression with Transformers","date":"2022-01-19","arxiv_id":"2201.07412","n_code_links":1,"syntology":null},{"paper":"/paper/q-vit-fully-differentiable-quantization-for","slug":"q-vit-fully-differentiable-quantization-for","title":"Q-ViT: Fully Differentiable Quantization for Vision Transformer","date":"2022-01-19","arxiv_id":"2201.07703","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":5,"n_instrument":2,"unverified":2,"pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zhexinli/Q-ViT-DeiT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"swin-pose-swin-transformer-based-human-pose","title":"Swin-Pose: Swin Transformer Based Human Pose Estimation","date":"2022-01-19","arxiv_id":"2201.07384","n_code_links":0,"syntology":null},{"paper":null,"slug":"transfuse-a-unified-transformer-based-image","title":"TransFuse: A Unified Transformer-based Image Fusion Framework using Self-supervised Learning","date":"2022-01-19","arxiv_id":"2201.07451","n_code_links":0,"syntology":null},{"paper":null,"slug":"gtrans-spatiotemporal-autoregressive","title":"GTrans: Spatiotemporal Autoregressive Transformer with Graph Embeddings for Nowcasting Extreme Events","date":"2022-01-18","arxiv_id":"2201.06717","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-neural-network-approaches-for","title":"Hierarchical Neural Network Approaches for Long Document Classification","date":"2022-01-18","arxiv_id":"2201.06774","n_code_links":0,"syntology":null},{"paper":"/paper/motion-inbetweening-via-deep-d-interpolator","slug":"motion-inbetweening-via-deep-d-interpolator","title":"Motion Inbetweening via Deep $Δ$-Interpolator","date":"2022-01-18","arxiv_id":"2201.06701","n_code_links":1,"syntology":null},{"paper":"/paper/resistance-training-using-prior-bias-toward","slug":"resistance-training-using-prior-bias-toward","title":"Resistance Training using Prior Bias: toward Unbiased Scene Graph Generation","date":"2022-01-18","arxiv_id":"2201.06794","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"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":["chch1999/rtpb"],"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":null,"slug":"towards-controllable-protein-design-with","title":"Controllable Protein Design with Language Models","date":"2022-01-18","arxiv_id":"2201.07338","n_code_links":0,"syntology":null},{"paper":"/paper/tranad-deep-transformer-networks-for-anomaly","slug":"tranad-deep-transformer-networks-for-anomaly","title":"TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data","date":"2022-01-18","arxiv_id":"2201.07284","n_code_links":2,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["imperial-qore/tranad"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/continual-transformers-redundancy-free","slug":"continual-transformers-redundancy-free","title":"Continual Transformers: Redundancy-Free Attention for Online Inference","date":"2022-01-17","arxiv_id":"2201.06268","n_code_links":1,"syntology":null},{"paper":null,"slug":"disentangled-latent-transformer-for","title":"Disentangled Latent Transformer for Interpretable Monocular Height Estimation","date":"2022-01-17","arxiv_id":"2201.06357","n_code_links":0,"syntology":null},{"paper":"/paper/korean-specific-dataset-for-table-question","slug":"korean-specific-dataset-for-table-question","title":"Korean-Specific Dataset for Table Question Answering","date":"2022-01-17","arxiv_id":"2201.06223","n_code_links":1,"syntology":null},{"paper":null,"slug":"looking-at-the-performer-from-a-hopfield","title":"Looking at the Performer from a Hopfield Point of View","date":"2022-01-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/squire-a-sequence-to-sequence-framework-for","slug":"squire-a-sequence-to-sequence-framework-for","title":"SQUIRE: A Sequence-to-sequence Framework for Multi-hop Knowledge Graph Reasoning","date":"2022-01-17","arxiv_id":"2201.06206","n_code_links":1,"syntology":null},{"paper":null,"slug":"conventional-clustering-based-method-for","title":"Conventional clustering-based method for event detection on social networks","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/ernie-layout-layout-knowledge-enhanced-multi","slug":"ernie-layout-layout-knowledge-enhanced-multi","title":"ERNIE-Layout: Layout-Knowledge Enhanced Multi-modal Pre-training for Document Understanding","date":"2022-01-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"hierarchical-transformers-are-more-efficient-1","title":"Hierarchical Transformers Are More Efficient Language Models","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"kat-a-knowledge-augmented-transformer-for-1","title":"KAT: A Knowledge Augmented Transformer for Vision-and-Language","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"kd-vlp-improving-end-to-end-vision-and-1","title":"KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"lope-learnable-sinusoidal-positional-encoding","title":"LoPE: Learnable Sinusoidal Positional Encoding for Improving Document Transformer Model","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"must-a-framework-for-training-task-oriented","title":"MUST: A Framework for Training Task-oriented Dialogue Systems with Multiple User SimulaTors","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"non-autoregressive-neural-machine-translation-2","title":"Non-Autoregressive Neural Machine Translation with Consistency Regularization Optimized Variational Framework","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"patching-leaks-in-the-charformer-for","title":"Patching Leaks in the Charformer for Generative Tasks","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"polling-latent-opinions-a-method-for","title":"Polling Latent Opinions: A Method for Computational Sociolinguistics Using Transformer Language Models","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"s5-framework-a-review-of-self-supervised","title":"S5 Framework: A Review of Self-Supervised Shared Semantic Space Optimization for Multimodal Zero-Shot Learning","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"surprisingly-simple-adapter-ensembling-for","title":"Surprisingly Simple Adapter Ensembling for Zero-Shot Cross-Lingual Sequence Tagging","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tree-knowledge-distillation-for-compressing","title":"Tree Knowledge Distillation for Compressing Transformer-Based Language Models","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"video-transformers-a-survey","title":"Video Transformers: A Survey","date":"2022-01-16","arxiv_id":"2201.05991","n_code_links":0,"syntology":null},{"paper":null,"slug":"domain-adaptation-via-bidirectional-cross","title":"Domain Adaptation via Bidirectional Cross-Attention Transformer","date":"2022-01-15","arxiv_id":"2201.05887","n_code_links":0,"syntology":null},{"paper":"/paper/kformer-knowledge-injection-in-transformer","slug":"kformer-knowledge-injection-in-transformer","title":"Kformer: Knowledge Injection in Transformer Feed-Forward Layers","date":"2022-01-15","arxiv_id":"2201.05742","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 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":["zjunlp/Kformer"],"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"]}}}],"record_sha256":"d678fa3ce299453685cf6a2c6342454c70209802063985130f3152fa72ecfd3a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}