{"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/109","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":109,"pages_in_order":140,"rows_per_page":100,"rows":[10801,10900],"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/108","next":"/method/transformer/papers/110","papers":[{"paper":"/paper/joint-rotational-invariance-and-adversarial","slug":"joint-rotational-invariance-and-adversarial","title":"Joint rotational invariance and adversarial training of a dual-stream Transformer yields state of the art Brain-Score for Area V4","date":"2022-03-08","arxiv_id":"2203.06649","n_code_links":1,"syntology":null},{"paper":"/paper/lane-detection-with-versatile-atrousformer","slug":"lane-detection-with-versatile-atrousformer","title":"Lane Detection with Versatile AtrousFormer and Local Semantic Guidance","date":"2022-03-08","arxiv_id":"2203.04067","n_code_links":0,"syntology":null},{"paper":"/paper/measuring-the-mixing-of-contextual","slug":"measuring-the-mixing-of-contextual","title":"Measuring the Mixing of Contextual Information in the Transformer","date":"2022-03-08","arxiv_id":"2203.04212","n_code_links":2,"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":["mt-upc/transformer-contributions"],"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/neural-face-identification-in-a-2d-wireframe-1","slug":"neural-face-identification-in-a-2d-wireframe-1","title":"Neural Face Identification in a 2D Wireframe Projection of a Manifold Object","date":"2022-03-08","arxiv_id":"2203.04229","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":5,"n_instrument":1,"unverified":3,"pointer_only":0,"phrase":"6 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; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["manycore-research/faceformer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"monocular-robot-navigation-with-self","title":"Monocular Robot Navigation with Self-Supervised Pretrained Vision Transformers","date":"2022-03-07","arxiv_id":"2203.03682","n_code_links":0,"syntology":null},{"paper":null,"slug":"one-model-multiple-tasks-pathways-for-natural","title":"SkillNet-NLU: A Sparsely Activated Model for General-Purpose Natural Language Understanding","date":"2022-03-07","arxiv_id":"2203.03312","n_code_links":0,"syntology":null},{"paper":"/paper/stepwise-feature-fusion-local-guides-global","slug":"stepwise-feature-fusion-local-guides-global","title":"Stepwise Feature Fusion: Local Guides Global","date":"2022-03-07","arxiv_id":"2203.03635","n_code_links":1,"syntology":null},{"paper":"/paper/tensor-programs-v-tuning-large-neural","slug":"tensor-programs-v-tuning-large-neural","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","date":"2022-03-07","arxiv_id":"2203.03466","n_code_links":7,"syntology":{"ran":3,"of":5,"n_ran_checked":1,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["microsoft/mup"],"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":["listed","official"]}}},{"paper":"/paper/conditional-bilingual-mutual-information","slug":"conditional-bilingual-mutual-information","title":"Conditional Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation","date":"2022-03-06","arxiv_id":"2203.02951","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-dual-task-correlation-for-pose","slug":"exploring-dual-task-correlation-for-pose","title":"Exploring Dual-task Correlation for Pose Guided Person Image Generation","date":"2022-03-06","arxiv_id":"2203.02910","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["pangzecheung/dual-task-pose-transformer-network"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"learnable-irrelevant-modality-dropout-for","title":"Learnable Irrelevant Modality Dropout for Multimodal Action Recognition on Modality-Specific Annotated Videos","date":"2022-03-06","arxiv_id":"2203.03014","n_code_links":0,"syntology":null},{"paper":"/paper/multi-class-token-transformer-for-weakly","slug":"multi-class-token-transformer-for-weakly","title":"Multi-class Token Transformer for Weakly Supervised Semantic Segmentation","date":"2022-03-06","arxiv_id":"2203.02891","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"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) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["xulianuwa/mctformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/panformer-a-transformer-based-model-for-pan","slug":"panformer-a-transformer-based-model-for-pan","title":"PanFormer: a Transformer Based Model for Pan-sharpening","date":"2022-03-06","arxiv_id":"2203.02916","n_code_links":1,"syntology":null},{"paper":"/paper/claret-pre-training-a-correlation-aware","slug":"claret-pre-training-a-correlation-aware","title":"ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification","date":"2022-03-04","arxiv_id":"2203.02225","n_code_links":1,"syntology":null},{"paper":"/paper/dit-self-supervised-pre-training-for-document","slug":"dit-self-supervised-pre-training-for-document","title":"DiT: Self-supervised Pre-training for Document Image Transformer","date":"2022-03-04","arxiv_id":"2203.02378","n_code_links":4,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["microsoft/unilm"],"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/litetransformersearch-training-free-on-device","slug":"litetransformersearch-training-free-on-device","title":"LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models","date":"2022-03-04","arxiv_id":"2203.02094","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":{"repos":["microsoft/archai"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/uvcgan-unet-vision-transformer-cycle","slug":"uvcgan-unet-vision-transformer-cycle","title":"UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation","date":"2022-03-04","arxiv_id":"2203.02557","n_code_links":2,"syntology":null},{"paper":"/paper/lgt-net-indoor-panoramic-room-layout","slug":"lgt-net-indoor-panoramic-room-layout","title":"LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Network","date":"2022-03-03","arxiv_id":"2203.01824","n_code_links":1,"syntology":{"ran":29,"of":41,"n_ran_checked":20,"n_instrument":9,"unverified":12,"pointer_only":0,"phrase":"29 ran (of which 5 constructed an object rather than computing a result; 20 with no instrument failure: 2 honoured, 1 violated, 17 with no contract checked; 9 where Syntology's instrument failed) · 12 unverified","official":{"repos":["zhigangjiang/LGT-Net"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":9,"ran_from_kinds":["found_in_text","official"]}}},{"paper":null,"slug":"multi-tailed-vision-transformer-for-efficient","title":"Multi-Tailed Vision Transformer for Efficient Inference","date":"2022-03-03","arxiv_id":"2203.01587","n_code_links":0,"syntology":null},{"paper":null,"slug":"vitranspad-video-transformer-using","title":"ViTransPAD: Video Transformer using convolution and self-attention for Face Presentation Attack Detection","date":"2022-03-03","arxiv_id":"2203.01562","n_code_links":0,"syntology":null},{"paper":"/paper/3dctn-3d-convolution-transformer-network-for","slug":"3dctn-3d-convolution-transformer-network-for","title":"3DCTN: 3D Convolution-Transformer Network for Point Cloud Classification","date":"2022-03-02","arxiv_id":"2203.00828","n_code_links":1,"syntology":null},{"paper":"/paper/aggregated-pyramid-vision-transformer-split","slug":"aggregated-pyramid-vision-transformer-split","title":"Aggregated Pyramid Vision Transformer: Split-transform-merge Strategy for Image Recognition without Convolutions","date":"2022-03-02","arxiv_id":"2203.00960","n_code_links":0,"syntology":null},{"paper":"/paper/bending-reality-distortion-aware-transformers","slug":"bending-reality-distortion-aware-transformers","title":"Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation","date":"2022-03-02","arxiv_id":"2203.01452","n_code_links":1,"syntology":null},{"paper":"/paper/contextual-attention-network-transformer","slug":"contextual-attention-network-transformer","title":"Contextual Attention Network: Transformer Meets U-Net","date":"2022-03-02","arxiv_id":"2203.01932","n_code_links":3,"syntology":null},{"paper":null,"slug":"d-2etr-decoder-only-detr-with-computationally","title":"D^2ETR: Decoder-Only DETR with Computationally Efficient Cross-Scale Attention","date":"2022-03-02","arxiv_id":"2203.00860","n_code_links":0,"syntology":null},{"paper":"/paper/dn-detr-accelerate-detr-training-by","slug":"dn-detr-accelerate-detr-training-by","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","date":"2022-03-02","arxiv_id":"2203.01305","n_code_links":17,"syntology":{"ran":17,"of":22,"n_ran_checked":6,"n_instrument":11,"unverified":5,"pointer_only":9,"phrase":"17 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 11 where Syntology's instrument failed) · 5 unverified","official":{"repos":["IDEA-Research/detrex","fengli-ust/dn-detr","idea-research/dn-detr"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/fastfold-reducing-alphafold-training-time","slug":"fastfold-reducing-alphafold-training-time","title":"FastFold: Reducing AlphaFold Training Time from 11 Days to 67 Hours","date":"2022-03-02","arxiv_id":"2203.00854","n_code_links":1,"syntology":null},{"paper":"/paper/mtet-multi-domain-translation-for-english","slug":"mtet-multi-domain-translation-for-english","title":"MTet: Multi-domain Translation for English-Vietnamese","date":"2022-03-02","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/protecting-celebrities-with-identity","slug":"protecting-celebrities-with-identity","title":"Protecting Celebrities from DeepFake with Identity Consistency Transformer","date":"2022-03-02","arxiv_id":"2203.01318","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":["lightdxy/ict_deepfake"],"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":"temporal-context-matters-enhancing-single","title":"Temporal Context Matters: Enhancing Single Image Prediction with Disease Progression Representations","date":"2022-03-02","arxiv_id":"2203.01933","n_code_links":0,"syntology":null},{"paper":"/paper/x-trans2cap-cross-modal-knowledge-transfer","slug":"x-trans2cap-cross-modal-knowledge-transfer","title":"X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning","date":"2022-03-02","arxiv_id":"2203.00843","n_code_links":1,"syntology":null},{"paper":"/paper/deepnet-scaling-transformers-to-1000-layers","slug":"deepnet-scaling-transformers-to-1000-layers","title":"DeepNet: Scaling Transformers to 1,000 Layers","date":"2022-03-01","arxiv_id":"2203.00555","n_code_links":6,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/unilm"],"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":["listed","official","unlocated"]}}},{"paper":"/paper/fast-r2d2-a-pretrained-recursive-neural","slug":"fast-r2d2-a-pretrained-recursive-neural","title":"Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representation","date":"2022-03-01","arxiv_id":"2203.00281","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["alipay/StructuredLM_RTDT"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":null,"slug":"temporal-perceiver-a-general-architecture-for","title":"Temporal Perceiver: A General Architecture for Arbitrary Boundary Detection","date":"2022-03-01","arxiv_id":"2203.00307","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-grammars-augmenting-transformer","title":"Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale","date":"2022-03-01","arxiv_id":"2203.00633","n_code_links":0,"syntology":null},{"paper":"/paper/wearable-sensor-based-human-activity","slug":"wearable-sensor-based-human-activity","title":"Wearable Sensor-Based Human Activity Recognition with Transformer Model","date":"2022-03-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/a-multi-scale-transformer-for-medical-image","slug":"a-multi-scale-transformer-for-medical-image","title":"A Data-scalable Transformer for Medical Image Segmentation: Architecture, Model Efficiency, and Benchmark","date":"2022-02-28","arxiv_id":"2203.00131","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":1,"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) · 1 unverified","official":{"repos":["yhygao/cbim-medical-image-segmentation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/ctformer-convolution-free-token2token-dilated","slug":"ctformer-convolution-free-token2token-dilated","title":"CTformer: Convolution-free Token2Token Dilated Vision Transformer for Low-dose CT Denoising","date":"2022-02-28","arxiv_id":"2202.13517","n_code_links":2,"syntology":null},{"paper":"/paper/dropit-dropping-intermediate-tensors-for","slug":"dropit-dropping-intermediate-tensors-for","title":"DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training","date":"2022-02-28","arxiv_id":"2202.13808","n_code_links":1,"syntology":null},{"paper":"/paper/filter-enhanced-mlp-is-all-you-need-for","slug":"filter-enhanced-mlp-is-all-you-need-for","title":"Filter-enhanced MLP is All You Need for Sequential Recommendation","date":"2022-02-28","arxiv_id":"2202.13556","n_code_links":2,"syntology":null},{"paper":"/paper/lilt-a-simple-yet-effective-language","slug":"lilt-a-simple-yet-effective-language","title":"LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding","date":"2022-02-28","arxiv_id":"2202.13669","n_code_links":5,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jpwang/lilt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/lisa-learning-interpretable-skill","slug":"lisa-learning-interpretable-skill","title":"LISA: Learning Interpretable Skill Abstractions from Language","date":"2022-02-28","arxiv_id":"2203.00054","n_code_links":1,"syntology":null},{"paper":"/paper/sunet-swin-transformer-unet-for-image","slug":"sunet-swin-transformer-unet-for-image","title":"SUNet: Swin Transformer UNet for Image Denoising","date":"2022-02-28","arxiv_id":"2202.14009","n_code_links":2,"syntology":null},{"paper":null,"slug":"dxm-transfuse-u-net-dual-cross-modal","title":"DXM-TransFuse U-net: Dual Cross-Modal Transformer Fusion U-net for Automated Nerve Identification","date":"2022-02-27","arxiv_id":"2202.13304","n_code_links":0,"syntology":null},{"paper":null,"slug":"gcn-transformer-for-short-term-passenger-flow","title":"Spatial-Temporal Attention Fusion Network for short-term passenger flow prediction on holidays in urban rail transit systems","date":"2022-02-27","arxiv_id":"2203.00007","n_code_links":0,"syntology":null},{"paper":null,"slug":"short-term-passenger-flow-prediction-for","title":"Short-term passenger flow prediction for multi-traffic modes: A Transformer and residual network based multi-task learning method","date":"2022-02-27","arxiv_id":"2203.00422","n_code_links":0,"syntology":null},{"paper":"/paper/an-end-to-end-transformer-model-for-crowd","slug":"an-end-to-end-transformer-model-for-crowd","title":"An End-to-End Transformer Model for Crowd Localization","date":"2022-02-26","arxiv_id":"2202.13065","n_code_links":1,"syntology":null},{"paper":"/paper/blind-image-super-resolution-with-semantic","slug":"blind-image-super-resolution-with-semantic","title":"Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors","date":"2022-02-26","arxiv_id":"2202.13142","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-hardware-aware-system-for-accelerating-deep","title":"A Hardware-Aware System for Accelerating Deep Neural Network Optimization","date":"2022-02-25","arxiv_id":"2202.12954","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-supervised-and-interpretable-anomaly","title":"Self-Supervised and Interpretable Anomaly Detection using Network Transformers","date":"2022-02-25","arxiv_id":"2202.12997","n_code_links":0,"syntology":null},{"paper":"/paper/instantaneous-physiological-estimation-using","slug":"instantaneous-physiological-estimation-using","title":"Instantaneous Physiological Estimation using Video Transformers","date":"2022-02-24","arxiv_id":"2202.12368","n_code_links":1,"syntology":null},{"paper":null,"slug":"openfeat-improving-speaker-identification-by","title":"openFEAT: Improving Speaker Identification by Open-set Few-shot Embedding Adaptation with Transformer","date":"2022-02-24","arxiv_id":"2202.12349","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformers-in-medical-image-analysis-a","title":"Transformers in Medical Image Analysis: A Review","date":"2022-02-24","arxiv_id":"2202.12165","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-differential-attention-fusion-model-based","title":"A Differential Attention Fusion Model Based on Transformer for Time Series Forecasting","date":"2022-02-23","arxiv_id":"2202.11402","n_code_links":0,"syntology":null},{"paper":"/paper/fastrpb-a-scalable-relative-positional-1","slug":"fastrpb-a-scalable-relative-positional-1","title":"FastRPB: a Scalable Relative Positional Encoding for Long Sequence Tasks","date":"2022-02-23","arxiv_id":"2202.11364","n_code_links":1,"syntology":null},{"paper":null,"slug":"paying-u-attention-to-textures-multi-stage","title":"Paying U-Attention to Textures: Multi-Stage Hourglass Vision Transformer for Universal Texture Synthesis","date":"2022-02-23","arxiv_id":"2202.11703","n_code_links":0,"syntology":null},{"paper":null,"slug":"refining-the-state-of-the-art-in-machine","title":"Refining the state-of-the-art in Machine Translation, optimizing NMT for the JA <-> EN language pair by leveraging personal domain expertise","date":"2022-02-23","arxiv_id":"2202.11669","n_code_links":0,"syntology":null},{"paper":"/paper/think-global-act-local-dual-scale-graph","slug":"think-global-act-local-dual-scale-graph","title":"Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation","date":"2022-02-23","arxiv_id":"2202.11742","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"a-new-generation-of-perspective-api-efficient","title":"A New Generation of Perspective API: Efficient Multilingual Character-level Transformers","date":"2022-02-22","arxiv_id":"2202.11176","n_code_links":0,"syntology":null},{"paper":"/paper/groupvit-semantic-segmentation-emerges-from","slug":"groupvit-semantic-segmentation-emerges-from","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","date":"2022-02-22","arxiv_id":"2202.11094","n_code_links":6,"syntology":null},{"paper":"/paper/one-shot-scene-graph-generation","slug":"one-shot-scene-graph-generation","title":"One-shot Scene Graph Generation","date":"2022-02-22","arxiv_id":"2202.10824","n_code_links":1,"syntology":null},{"paper":null,"slug":"social-computational-design-method-for","title":"Social Computational Design Method for Generating Product Shapes with GAN and Transformer Models","date":"2022-02-22","arxiv_id":"2202.10774","n_code_links":0,"syntology":null},{"paper":"/paper/socialformer-social-network-inspired-long","slug":"socialformer-social-network-inspired-long","title":"Socialformer: Social Network Inspired Long Document Modeling for Document Ranking","date":"2022-02-22","arxiv_id":"2202.10870","n_code_links":1,"syntology":null},{"paper":"/paper/embarrassingly-simple-performance-prediction","slug":"embarrassingly-simple-performance-prediction","title":"Embarrassingly Simple Performance Prediction for Abductive Natural Language Inference","date":"2022-02-21","arxiv_id":"2202.10408","n_code_links":1,"syntology":null},{"paper":null,"slug":"rethinking-the-zigzag-flattening-for-image","title":"Rethinking the Zigzag Flattening for Image Reading","date":"2022-02-21","arxiv_id":"2202.10240","n_code_links":0,"syntology":null},{"paper":"/paper/s3t-self-supervised-pre-training-with-swin","slug":"s3t-self-supervised-pre-training-with-swin","title":"S3T: Self-Supervised Pre-training with Swin Transformer for Music Classification","date":"2022-02-21","arxiv_id":"2202.10139","n_code_links":1,"syntology":null},{"paper":"/paper/vitaev2-vision-transformer-advanced-by","slug":"vitaev2-vision-transformer-advanced-by","title":"ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond","date":"2022-02-21","arxiv_id":"2202.10108","n_code_links":8,"syntology":{"ran":22,"of":25,"n_ran_checked":16,"n_instrument":6,"unverified":3,"pointer_only":4,"phrase":"22 ran (of which 8 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","official":{"repos":["ViTAE-Transformer/ViTAE-Transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community","listed"]}}},{"paper":"/paper/arm3d-attention-based-relation-module-for","slug":"arm3d-attention-based-relation-module-for","title":"ARM3D: Attention-based relation module for indoor 3D object detection","date":"2022-02-20","arxiv_id":"2202.09715","n_code_links":1,"syntology":null},{"paper":null,"slug":"do-transformers-use-variable-binding","title":"Do Transformers know symbolic rules, and would we know if they did?","date":"2022-02-19","arxiv_id":"2203.00162","n_code_links":0,"syntology":null},{"paper":"/paper/transdreamer-reinforcement-learning-with-1","slug":"transdreamer-reinforcement-learning-with-1","title":"TransDreamer: Reinforcement Learning with Transformer World Models","date":"2022-02-19","arxiv_id":"2202.09481","n_code_links":0,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"a-survey-of-vision-language-pre-trained","title":"A Survey of Vision-Language Pre-Trained Models","date":"2022-02-18","arxiv_id":"2202.10936","n_code_links":0,"syntology":null},{"paper":null,"slug":"mixture-of-experts-with-expert-choice-routing","title":"Mixture-of-Experts with Expert Choice Routing","date":"2022-02-18","arxiv_id":"2202.09368","n_code_links":0,"syntology":null},{"paper":"/paper/task-specific-attention-is-one-more-thing-you","slug":"task-specific-attention-is-one-more-thing-you","title":"Task Specific Attention is one more thing you need for object detection","date":"2022-02-18","arxiv_id":"2202.09048","n_code_links":1,"syntology":null},{"paper":null,"slug":"unleashing-the-power-of-transformer-for","title":"Unleashing the Power of Transformer for Graphs","date":"2022-02-18","arxiv_id":"2202.10581","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-hybrid-2-stage-vision-transformer-for-ai","title":"Multi-Scale Hybrid Vision Transformer for Learning Gastric Histology: AI-Based Decision Support System for Gastric Cancer Treatment","date":"2022-02-17","arxiv_id":"2202.08510","n_code_links":0,"syntology":null},{"paper":"/paper/designing-effective-sparse-expert-models","slug":"designing-effective-sparse-expert-models","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","date":"2022-02-17","arxiv_id":"2202.08906","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tensorflow/mesh"],"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-masked-autoencoder","slug":"graph-masked-autoencoder","title":"Graph Masked Autoencoders with Transformers","date":"2022-02-17","arxiv_id":"2202.08391","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-english-to-sinhala-neural-machine","title":"Improving English to Sinhala Neural Machine Translation using Part-of-Speech Tag","date":"2022-02-17","arxiv_id":"2202.08882","n_code_links":0,"syntology":null},{"paper":null,"slug":"revisiting-over-smoothing-in-bert-from-the-1","title":"Revisiting Over-smoothing in BERT from the Perspective of Graph","date":"2022-02-17","arxiv_id":"2202.08625","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-for-graphs-an-overview-from","slug":"transformer-for-graphs-an-overview-from","title":"Transformer for Graphs: An Overview from Architecture Perspective","date":"2022-02-17","arxiv_id":"2202.08455","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":["qwerfdsaplking/graph-trans"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"trasetr-track-to-segment-transformer-with","title":"TraSeTR: Track-to-Segment Transformer with Contrastive Query for Instance-level Instrument Segmentation in Robotic Surgery","date":"2022-02-17","arxiv_id":"2202.08453","n_code_links":0,"syntology":null},{"paper":"/paper/actionformer-localizing-moments-of-actions","slug":"actionformer-localizing-moments-of-actions","title":"ActionFormer: Localizing Moments of Actions with Transformers","date":"2022-02-16","arxiv_id":"2202.07925","n_code_links":1,"syntology":null},{"paper":"/paper/edgeformer-a-parameter-efficient-transformer","slug":"edgeformer-a-parameter-efficient-transformer","title":"EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation","date":"2022-02-16","arxiv_id":"2202.07959","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["microsoft/unilm"],"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":["found_in_text"]}}},{"paper":null,"slug":"the-nlp-task-effectiveness-of-long-range","title":"The NLP Task Effectiveness of Long-Range Transformers","date":"2022-02-16","arxiv_id":"2202.07856","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-on-dynamic-neural-networks-for","title":"A Survey on Dynamic Neural Networks for Natural Language Processing","date":"2022-02-15","arxiv_id":"2202.07101","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-on-model-compression-for-natural","title":"A Survey on Model Compression and Acceleration for Pretrained Language Models","date":"2022-02-15","arxiv_id":"2202.07105","n_code_links":0,"syntology":null},{"paper":"/paper/personalized-prompt-learning-for-explainable","slug":"personalized-prompt-learning-for-explainable","title":"Personalized Prompt Learning for Explainable Recommendation","date":"2022-02-15","arxiv_id":"2202.07371","n_code_links":1,"syntology":null},{"paper":"/paper/transformers-in-time-series-a-survey","slug":"transformers-in-time-series-a-survey","title":"Transformers in Time Series: A Survey","date":"2022-02-15","arxiv_id":"2202.07125","n_code_links":11,"syntology":null},{"paper":null,"slug":"vinter-image-narrative-generation-with","title":"ViNTER: Image Narrative Generation with Emotion-Arc-Aware Transformer","date":"2022-02-15","arxiv_id":"2202.07305","n_code_links":0,"syntology":null},{"paper":"/paper/xai-for-transformers-better-explanations","slug":"xai-for-transformers-better-explanations","title":"XAI for Transformers: Better Explanations through Conservative Propagation","date":"2022-02-15","arxiv_id":"2202.07304","n_code_links":1,"syntology":{"ran":10,"of":12,"n_ran_checked":10,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ameenali/xai_transformers"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/codefill-multi-token-code-completion-by","slug":"codefill-multi-token-code-completion-by","title":"CodeFill: Multi-token Code Completion by Jointly Learning from Structure and Naming Sequences","date":"2022-02-14","arxiv_id":"2202.06689","n_code_links":1,"syntology":null},{"paper":"/paper/geometric-transformer-for-fast-and-robust","slug":"geometric-transformer-for-fast-and-robust","title":"Geometric Transformer for Fast and Robust Point Cloud Registration","date":"2022-02-14","arxiv_id":"2202.06688","n_code_links":2,"syntology":{"ran":4,"of":9,"n_ran_checked":4,"n_instrument":0,"unverified":5,"pointer_only":9,"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) · 5 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["qinzheng93/geotransformer"],"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/handcrafted-histological-transformer-h2t","slug":"handcrafted-histological-transformer-h2t","title":"Handcrafted Histological Transformer (H2T): Unsupervised Representation of Whole Slide Images","date":"2022-02-14","arxiv_id":"2202.07001","n_code_links":1,"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":["vqdang/h2t"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/mixing-and-shifting-exploiting-global-and","slug":"mixing-and-shifting-exploiting-global-and","title":"Mixing and Shifting: Exploiting Global and Local Dependencies in Vision MLPs","date":"2022-02-14","arxiv_id":"2202.06510","n_code_links":2,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":6,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["jegzheng/ms-mlp"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/source-code-summarization-with-structural","slug":"source-code-summarization-with-structural","title":"Source Code Summarization with Structural Relative Position Guided Transformer","date":"2022-02-14","arxiv_id":"2202.06521","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-memory-as-a-differentiable-search","slug":"transformer-memory-as-a-differentiable-search","title":"Transformer Memory as a Differentiable Search Index","date":"2022-02-14","arxiv_id":"2202.06991","n_code_links":1,"syntology":null},{"paper":"/paper/what-do-they-capture-a-structural-analysis-of","slug":"what-do-they-capture-a-structural-analysis-of","title":"What Do They Capture? -- A Structural Analysis of Pre-Trained Language Models for Source Code","date":"2022-02-14","arxiv_id":"2202.06840","n_code_links":1,"syntology":null},{"paper":"/paper/bvit-broad-attention-based-vision-transformer","slug":"bvit-broad-attention-based-vision-transformer","title":"BViT: Broad Attention based Vision Transformer","date":"2022-02-13","arxiv_id":"2202.06268","n_code_links":1,"syntology":null},{"paper":"/paper/et-bert-a-contextualized-datagram","slug":"et-bert-a-contextualized-datagram","title":"ET-BERT: A Contextualized Datagram Representation with Pre-training Transformers for Encrypted Traffic Classification","date":"2022-02-13","arxiv_id":"2202.06335","n_code_links":1,"syntology":null},{"paper":null,"slug":"lightn-light-weight-transformer-network-for","title":"LighTN: Light-weight Transformer Network for Performance-overhead Tradeoff in Point Cloud Downsampling","date":"2022-02-13","arxiv_id":"2202.06263","n_code_links":0,"syntology":null}],"record_sha256":"12589c574510bced5fb3c87c09932ea3b38ac856c286534155e36c8f1c785496","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}