{"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/layer-normalization/papers/180","list_of":"/method/layer-normalization","method":"Layer Normalization","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":180,"pages_in_order":250,"rows_per_page":100,"rows":[17901,18000],"of":24980,"counts":{"archive_papers_tagged":24980,"with_a_code_link":11273,"where_syntology_ran_a_sample":3471,"not_listed_spam_title":0,"listed":24980,"listed_where_code_ran":3471,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2923,"every_run_a_failure_of_syntologys_instrument":548,"listed_with_a_run_with_no_instrument_failure":2923,"listed_every_run_a_failure_of_syntologys_instrument":548,"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/layer-normalization","prev":"/method/layer-normalization/papers/179","next":"/method/layer-normalization/papers/181","papers":[{"paper":"/paper/chitransformer-towards-reliable-stereo-from","slug":"chitransformer-towards-reliable-stereo-from","title":"ChiTransformer:Towards Reliable Stereo from Cues","date":"2022-03-09","arxiv_id":"2203.04554","n_code_links":1,"syntology":null},{"paper":"/paper/coarse-to-fine-sparse-transformer-for","slug":"coarse-to-fine-sparse-transformer-for","title":"Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction","date":"2022-03-09","arxiv_id":"2203.04845","n_code_links":1,"syntology":{"ran":13,"of":16,"n_ran_checked":9,"n_instrument":4,"unverified":3,"pointer_only":0,"phrase":"13 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["caiyuanhao1998/MST"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":8,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"detecting-and-diagnosing-terrestrial","title":"Detecting and Diagnosing Terrestrial Gravitational-Wave Mimics Through Feature Learning","date":"2022-03-09","arxiv_id":"2203.05086","n_code_links":0,"syntology":null},{"paper":null,"slug":"multiscale-convolutional-transformer-with","title":"Multiscale Convolutional Transformer with Center Mask Pretraining for Hyperspectral Image Classification","date":"2022-03-09","arxiv_id":"2203.04771","n_code_links":0,"syntology":null},{"paper":"/paper/nlx-gpt-a-model-for-natural-language","slug":"nlx-gpt-a-model-for-natural-language","title":"NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks","date":"2022-03-09","arxiv_id":"2203.05081","n_code_links":1,"syntology":null},{"paper":"/paper/phtrans-parallelly-aggregating-global-and","slug":"phtrans-parallelly-aggregating-global-and","title":"PHTrans: Parallelly Aggregating Global and Local Representations for Medical Image Segmentation","date":"2022-03-09","arxiv_id":"2203.04568","n_code_links":2,"syntology":null},{"paper":null,"slug":"region-aware-face-swapping","title":"Region-Aware Face Swapping","date":"2022-03-09","arxiv_id":"2203.04564","n_code_links":0,"syntology":null},{"paper":"/paper/the-evolution-evolvability-and-engineering-of","slug":"the-evolution-evolvability-and-engineering-of","title":"The evolution, evolvability and engineering of gene regulatory DNA","date":"2022-03-09","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"uni4eye-unified-2d-and-3d-self-supervised-pre","title":"Uni4Eye: Unified 2D and 3D Self-supervised Pre-training via Masked Image Modeling Transformer for Ophthalmic Image Classification","date":"2022-03-09","arxiv_id":"2203.04614","n_code_links":0,"syntology":null},{"paper":null,"slug":"cass-a-channel-aware-self-supervised","title":"CaSS: A Channel-aware Self-supervised Representation Learning Framework for Multivariate Time Series Classification","date":"2022-03-08","arxiv_id":"2203.04298","n_code_links":0,"syntology":null},{"paper":"/paper/coarse-to-fine-vision-transformer","slug":"coarse-to-fine-vision-transformer","title":"CF-ViT: A General Coarse-to-Fine Method for Vision Transformer","date":"2022-03-08","arxiv_id":"2203.03821","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["chenmnz/cf-vit"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"deep-multi-branch-aggregation-network-for","title":"Deep Multi-Branch Aggregation Network for Real-Time Semantic Segmentation in Street Scenes","date":"2022-03-08","arxiv_id":"2203.04037","n_code_links":0,"syntology":null},{"paper":"/paper/dumlp-pin-a-dual-mlp-dot-product-permutation","slug":"dumlp-pin-a-dual-mlp-dot-product-permutation","title":"DuMLP-Pin: A Dual-MLP-dot-product Permutation-invariant Network for Set Feature Extraction","date":"2022-03-08","arxiv_id":"2203.04007","n_code_links":1,"syntology":null},{"paper":null,"slug":"dynamic-group-transformer-a-general-vision","title":"Dynamic Group Transformer: A General Vision Transformer Backbone with Dynamic Group Attention","date":"2022-03-08","arxiv_id":"2203.03937","n_code_links":0,"syntology":null},{"paper":"/paper/edgeformer-improving-light-weight-convnets-by","slug":"edgeformer-improving-light-weight-convnets-by","title":"ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer","date":"2022-03-08","arxiv_id":"2203.03952","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 4 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":["hkzhang91/edgeformer","hkzhang91/pacc-net","hkzhang91/parc-net"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/graph-attention-transformer-network-for-multi","slug":"graph-attention-transformer-network-for-multi","title":"Graph Attention Transformer Network for Multi-Label Image Classification","date":"2022-03-08","arxiv_id":"2203.04049","n_code_links":1,"syntology":null},{"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":null,"slug":"towards-generalized-models-for-task-oriented","title":"Towards Generalized Models for Task-oriented Dialogue Modeling on Spoken Conversations","date":"2022-03-08","arxiv_id":"2203.04045","n_code_links":0,"syntology":null},{"paper":"/paper/it5-large-scale-text-to-text-pretraining-for","slug":"it5-large-scale-text-to-text-pretraining-for","title":"IT5: Text-to-text Pretraining for Italian Language Understanding and Generation","date":"2022-03-07","arxiv_id":"2203.03759","n_code_links":3,"syntology":null},{"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/pre-trained-token-replaced-detection-model-as","slug":"pre-trained-token-replaced-detection-model-as","title":"Pre-trained Token-replaced Detection Model as Few-shot Learner","date":"2022-03-07","arxiv_id":"2203.03235","n_code_links":1,"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/wavemix-resource-efficient-token-mixing-for","slug":"wavemix-resource-efficient-token-mixing-for","title":"WaveMix: Resource-efficient Token Mixing for Images","date":"2022-03-07","arxiv_id":"2203.03689","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":1,"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":["pranavphoenix/WaveMix"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/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/divide-and-conquer-text-semantic-matching-1","slug":"divide-and-conquer-text-semantic-matching-1","title":"Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents","date":"2022-03-06","arxiv_id":"2203.02898","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":"graph-neural-network-enhanced-language-models","title":"Graph Neural Network Enhanced Language Models for Efficient Multilingual Text Classification","date":"2022-03-06","arxiv_id":"2203.02912","n_code_links":0,"syntology":null},{"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":null,"slug":"leveraging-pre-trained-bert-for-audio","title":"Leveraging Pre-trained BERT for Audio Captioning","date":"2022-03-06","arxiv_id":"2203.02838","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":null,"slug":"automo-mixer-an-automated-multi-objective-1","title":"AutoMO-Mixer: An automated multi-objective Mixer model for balanced, safe and robust prediction in medicine","date":"2022-03-04","arxiv_id":"2203.02384","n_code_links":0,"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":null,"slug":"detecting-offensive-language-on-social","title":"Detecting Offensive Language on Social Networks: An End-to-end Detection Method based on Graph Attention Networks","date":"2022-03-04","arxiv_id":"2203.02123","n_code_links":0,"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/gcnet-graph-completion-network-for-incomplete","slug":"gcnet-graph-completion-network-for-incomplete","title":"GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversation","date":"2022-03-04","arxiv_id":"2203.02177","n_code_links":1,"syntology":null},{"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/training-language-models-to-follow","slug":"training-language-models-to-follow","title":"Training language models to follow instructions with human feedback","date":"2022-03-04","arxiv_id":"2203.02155","n_code_links":11,"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":["openai/following-instructions-human-feedback"],"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/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":null,"slug":"etcetera-beyond-event-triggered-control","title":"ETCetera: beyond Event-Triggered Control","date":"2022-03-03","arxiv_id":"2203.01623","n_code_links":0,"syntology":null},{"paper":"/paper/generative-modeling-for-low-dimensional","slug":"generative-modeling-for-low-dimensional","title":"Generative Modeling for Low Dimensional Speech Attributes with Neural Spline Flows","date":"2022-03-03","arxiv_id":"2203.01786","n_code_links":1,"syntology":null},{"paper":null,"slug":"latentformer-multi-agent-transformer-based","title":"LatentFormer: Multi-Agent Transformer-Based Interaction Modeling and Trajectory Prediction","date":"2022-03-03","arxiv_id":"2203.01880","n_code_links":0,"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":"/paper/new-crfs-neural-window-fully-connected-crfs-1","slug":"new-crfs-neural-window-fully-connected-crfs-1","title":"NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation","date":"2022-03-03","arxiv_id":"2203.01502","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":4,"n_instrument":2,"unverified":4,"pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["aliyun/NeWCRFs"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/semantic-guided-image-virtual-attribute","slug":"semantic-guided-image-virtual-attribute","title":"BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classification","date":"2022-03-03","arxiv_id":"2203.01937","n_code_links":2,"syntology":null},{"paper":null,"slug":"understanding-failure-modes-of-self","title":"Measuring Self-Supervised Representation Quality for Downstream Classification using Discriminative Features","date":"2022-03-03","arxiv_id":"2203.01881","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/discontinuous-constituency-and-bert-a-case-1","slug":"discontinuous-constituency-and-bert-a-case-1","title":"Discontinuous Constituency and BERT: A Case Study of Dutch","date":"2022-03-02","arxiv_id":"2203.01063","n_code_links":1,"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/parameter-efficient-mixture-of-experts","slug":"parameter-efficient-mixture-of-experts","title":"Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models","date":"2022-03-02","arxiv_id":"2203.01104","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rucaibox/mpo","rucaibox/mpoe"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/bert-lid-leveraging-bert-to-improve-spoken","slug":"bert-lid-leveraging-bert-to-improve-spoken","title":"BERT-LID: Leveraging BERT to Improve Spoken Language Identification","date":"2022-03-01","arxiv_id":"2203.00328","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":null,"slug":"e-lang-energy-based-joint-inferencing-of-1","title":"E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models","date":"2022-03-01","arxiv_id":"2203.00748","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-and-adapting-chinese-gpt-to-pinyin-1","slug":"exploring-and-adapting-chinese-gpt-to-pinyin-1","title":"Exploring and Adapting Chinese GPT to Pinyin Input Method","date":"2022-03-01","arxiv_id":"2203.00249","n_code_links":1,"syntology":null},{"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":"hyperprompt-prompt-based-task-conditioning-of","title":"HyperPrompt: Prompt-based Task-Conditioning of Transformers","date":"2022-03-01","arxiv_id":"2203.00759","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-whole-word-masking-always-better-for-1","title":"\"Is Whole Word Masking Always Better for Chinese BERT?\": Probing on Chinese Grammatical Error Correction","date":"2022-03-01","arxiv_id":"2203.00286","n_code_links":0,"syntology":null},{"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/deep-deep-learning-with-bart","slug":"deep-deep-learning-with-bart","title":"Deep, Deep Learning with BART","date":"2022-02-28","arxiv_id":"2202.14005","n_code_links":1,"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":"/paper/the-impact-of-lexical-and-grammatical-1","slug":"the-impact-of-lexical-and-grammatical-1","title":"The impact of lexical and grammatical processing on generating code from natural language","date":"2022-02-28","arxiv_id":"2202.13972","n_code_links":2,"syntology":null},{"paper":null,"slug":"using-multi-scale-swintransformer-htc-with","title":"Using Multi-scale SwinTransformer-HTC with Data augmentation in CoNIC Challenge","date":"2022-02-28","arxiv_id":"2202.13588","n_code_links":0,"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":"/paper/enhancing-legal-argument-mining-with-domain","slug":"enhancing-legal-argument-mining-with-domain","title":"Enhancing Legal Argument Mining with Domain Pre-training and Neural Networks","date":"2022-02-27","arxiv_id":"2202.13457","n_code_links":1,"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/a-systematic-evaluation-of-large-language","slug":"a-systematic-evaluation-of-large-language","title":"A Systematic Evaluation of Large Language Models of Code","date":"2022-02-26","arxiv_id":"2202.13169","n_code_links":3,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["eleutherai/gpt-neox","vhellendoorn/code-lms"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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":null,"slug":"bi-directional-joint-neural-networks-for","title":"Bi-directional Joint Neural Networks for Intent Classification and Slot Filling","date":"2022-02-26","arxiv_id":"2202.13079","n_code_links":0,"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":"multi-level-contrastive-learning-for-cross","title":"Multi-Level Contrastive Learning for Cross-Lingual Alignment","date":"2022-02-26","arxiv_id":"2202.13083","n_code_links":0,"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":"/paper/apeach-attacking-pejorative-expressions-with","slug":"apeach-attacking-pejorative-expressions-with","title":"APEACH: Attacking Pejorative Expressions with Analysis on Crowd-Generated Hate Speech Evaluation Datasets","date":"2022-02-25","arxiv_id":"2202.12459","n_code_links":1,"syntology":null},{"paper":"/paper/rethinking-the-role-of-demonstrations-what","slug":"rethinking-the-role-of-demonstrations-what","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","date":"2022-02-25","arxiv_id":"2202.12837","n_code_links":2,"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/bertvision-a-parameter-efficient-approach-for","slug":"bertvision-a-parameter-efficient-approach-for","title":"BERTVision -- A Parameter-Efficient Approach for Question Answering","date":"2022-02-24","arxiv_id":"2202.12210","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":["cbenge509/bertvision"],"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":"finding-inverse-document-frequency","title":"Finding Inverse Document Frequency Information in BERT","date":"2022-02-24","arxiv_id":"2202.12191","n_code_links":0,"syntology":null}],"record_sha256":"63818d70f07fb24d0e5a15d042db766a1d86408fd58fc1c147dc3553e0ddebd4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}