{"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/position-wise-feed-forward-layer/papers/92","list_of":"/method/position-wise-feed-forward-layer","method":"Position-Wise Feed-Forward Layer","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":92,"pages_in_order":139,"rows_per_page":100,"rows":[9101,9200],"of":13895,"counts":{"archive_papers_tagged":13895,"with_a_code_link":6514,"where_syntology_ran_a_sample":2229,"not_listed_spam_title":0,"listed":13895,"listed_where_code_ran":2229,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1902,"every_run_a_failure_of_syntologys_instrument":327,"listed_with_a_run_with_no_instrument_failure":1902,"listed_every_run_a_failure_of_syntologys_instrument":327,"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/position-wise-feed-forward-layer","prev":"/method/position-wise-feed-forward-layer/papers/91","next":"/method/position-wise-feed-forward-layer/papers/93","papers":[{"paper":"/paper/automated-icd-coding-using-extreme-multi","slug":"automated-icd-coding-using-extreme-multi","title":"Automated ICD Coding using Extreme Multi-label Long Text Transformer-based Models","date":"2022-12-12","arxiv_id":"2212.05857","n_code_links":1,"syntology":null},{"paper":"/paper/beautyrec-robust-efficient-and-content","slug":"beautyrec-robust-efficient-and-content","title":"BeautyREC: Robust, Efficient, and Content-preserving Makeup Transfer","date":"2022-12-12","arxiv_id":"2212.05855","n_code_links":0,"syntology":null},{"paper":"/paper/ctt-net-a-multi-view-cross-token-transformer","slug":"ctt-net-a-multi-view-cross-token-transformer","title":"CTT-Net: A Multi-view Cross-token Transformer for Cataract Postoperative Visual Acuity Prediction","date":"2022-12-12","arxiv_id":"2212.05794","n_code_links":1,"syntology":null},{"paper":"/paper/deep-learning-approaches-to-building-rooftop","slug":"deep-learning-approaches-to-building-rooftop","title":"Deep learning approaches to building rooftop thermal bridge detection from aerial images","date":"2022-12-12","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/nms-strikes-back","slug":"nms-strikes-back","title":"NMS Strikes Back","date":"2022-12-12","arxiv_id":"2212.06137","n_code_links":1,"syntology":null},{"paper":"/paper/p-transformer-towards-better-document-to","slug":"p-transformer-towards-better-document-to","title":"P-Transformer: Towards Better Document-to-Document Neural Machine Translation","date":"2022-12-12","arxiv_id":"2212.05830","n_code_links":1,"syntology":null},{"paper":null,"slug":"roiformer-semantic-aware-region-of-interest","title":"ROIFormer: Semantic-Aware Region of Interest Transformer for Efficient Self-Supervised Monocular Depth Estimation","date":"2022-12-12","arxiv_id":"2212.05729","n_code_links":0,"syntology":null},{"paper":"/paper/video-prediction-by-efficient-transformers","slug":"video-prediction-by-efficient-transformers","title":"Video Prediction by Efficient Transformers","date":"2022-12-12","arxiv_id":"2212.06026","n_code_links":1,"syntology":{"ran":0,"of":7,"n_ran_checked":0,"n_instrument":0,"unverified":7,"pointer_only":0,"phrase":"0 ran · 7 unverified","official":{"repos":["xiye20/vptr"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":[]}}},{"paper":null,"slug":"extending-trocr-for-text-localization-free","title":"Extending TrOCR for Text Localization-Free OCR of Full-Page Scanned Receipt Images","date":"2022-12-11","arxiv_id":"2212.05525","n_code_links":0,"syntology":null},{"paper":"/paper/joint-spatio-temporal-modeling-for-semantic","slug":"joint-spatio-temporal-modeling-for-semantic","title":"Joint Spatio-Temporal Modeling for the Semantic Change Detection in Remote Sensing Images","date":"2022-12-10","arxiv_id":"2212.05245","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ggsding/scannet"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":null,"slug":"machine-intuition-uncovering-human-like","title":"Thinking Fast and Slow in Large Language Models","date":"2022-12-10","arxiv_id":"2212.05206","n_code_links":0,"syntology":null},{"paper":"/paper/magvit-masked-generative-video-transformer","slug":"magvit-masked-generative-video-transformer","title":"MAGVIT: Masked Generative Video Transformer","date":"2022-12-10","arxiv_id":"2212.05199","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":9,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"10 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-research/magvit"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/position-embedding-needs-an-independent-layer","slug":"position-embedding-needs-an-independent-layer","title":"Position Embedding Needs an Independent Layer Normalization","date":"2022-12-10","arxiv_id":"2212.05262","n_code_links":1,"syntology":null},{"paper":null,"slug":"smile-scaling-mixture-of-experts-with","title":"SMILE: Scaling Mixture-of-Experts with Efficient Bi-level Routing","date":"2022-12-10","arxiv_id":"2212.05191","n_code_links":0,"syntology":null},{"paper":"/paper/augnet-dynamic-test-time-augmentation-via","slug":"augnet-dynamic-test-time-augmentation-via","title":"Dynamic Test-Time Augmentation via Differentiable Functions","date":"2022-12-09","arxiv_id":"2212.04681","n_code_links":1,"syntology":null},{"paper":null,"slug":"masked-lip-sync-prediction-by-audio-visual","title":"Masked Lip-Sync Prediction by Audio-Visual Contextual Exploitation in Transformers","date":"2022-12-09","arxiv_id":"2212.04970","n_code_links":0,"syntology":null},{"paper":"/paper/mimo-is-all-you-need-a-strong-multi-in-multi","slug":"mimo-is-all-you-need-a-strong-multi-in-multi","title":"MIMO Is All You Need : A Strong Multi-In-Multi-Out Baseline for Video Prediction","date":"2022-12-09","arxiv_id":"2212.04655","n_code_links":1,"syntology":null},{"paper":null,"slug":"omnihorizon-in-the-wild-outdoors-depth-and","title":"Cross-Domain Synthetic-to-Real In-the-Wild Depth and Normal Estimation for 3D Scene Understanding","date":"2022-12-09","arxiv_id":"2212.05040","n_code_links":0,"syntology":null},{"paper":"/paper/rcdt-relational-remote-sensing-change","slug":"rcdt-relational-remote-sensing-change","title":"RCDT: Relational Remote Sensing Change Detection with Transformer","date":"2022-12-09","arxiv_id":"2212.04869","n_code_links":1,"syntology":null},{"paper":"/paper/sparse-upcycling-training-mixture-of-experts","slug":"sparse-upcycling-training-mixture-of-experts","title":"Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints","date":"2022-12-09","arxiv_id":"2212.05055","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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-research/vmoe"],"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":"trbllmaker-transformer-reads-between-lyrics","title":"TRBLLmaker -- Transformer Reads Between Lyrics Lines maker","date":"2022-12-09","arxiv_id":"2212.04917","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-learning-for-inference-at-anytime","title":"Federated Learning for Inference at Anytime and Anywhere","date":"2022-12-08","arxiv_id":"2212.04084","n_code_links":0,"syntology":null},{"paper":null,"slug":"group-generalized-mean-pooling-for-vision","title":"Group Generalized Mean Pooling for Vision Transformer","date":"2022-12-08","arxiv_id":"2212.04114","n_code_links":0,"syntology":null},{"paper":"/paper/harnessing-the-power-of-multi-task","slug":"harnessing-the-power-of-multi-task","title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","date":"2022-12-08","arxiv_id":"2212.04231","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ofa-x/ofa-x"],"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":"nrtr-neuron-reconstruction-with-transformer","title":"NRTR: Neuron Reconstruction with Transformer from 3D Optical Microscopy Images","date":"2022-12-08","arxiv_id":"2212.04163","n_code_links":0,"syntology":null},{"paper":null,"slug":"gaussian-radar-transformer-for-semantic","title":"Gaussian Radar Transformer for Semantic Segmentation in Noisy Radar Data","date":"2022-12-07","arxiv_id":"2212.03690","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-embed-adopting-transformer-based","title":"Learning-To-Embed: Adopting Transformer based models for E-commerce Products Representation Learning","date":"2022-12-07","arxiv_id":"2212.03725","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-vision-transformers-with-forced","title":"Multimodal Vision Transformers with Forced Attention for Behavior Analysis","date":"2022-12-07","arxiv_id":"2212.03968","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-k-variate-time-series-is-worth-k-words","title":"A K-variate Time Series Is Worth K Words: Evolution of the Vanilla Transformer Architecture for Long-term Multivariate Time Series Forecasting","date":"2022-12-06","arxiv_id":"2212.02789","n_code_links":0,"syntology":null},{"paper":null,"slug":"abhe-all-attention-based-homography","title":"AbHE: All Attention-based Homography Estimation","date":"2022-12-06","arxiv_id":"2212.03029","n_code_links":0,"syntology":null},{"paper":"/paper/document-level-abstractive-summarization","slug":"document-level-abstractive-summarization","title":"Document-Level Abstractive Summarization","date":"2022-12-06","arxiv_id":"2212.03013","n_code_links":1,"syntology":null},{"paper":"/paper/incepformer-efficient-inception-transformer","slug":"incepformer-efficient-inception-transformer","title":"IncepFormer: Efficient Inception Transformer with Pyramid Pooling for Semantic Segmentation","date":"2022-12-06","arxiv_id":"2212.03035","n_code_links":1,"syntology":null},{"paper":null,"slug":"open-world-detr-transformer-based-open-world","title":"Open World DETR: Transformer based Open World Object Detection","date":"2022-12-06","arxiv_id":"2212.02969","n_code_links":0,"syntology":null},{"paper":null,"slug":"pretrained-diffusion-models-for-unified-human","title":"Pretrained Diffusion Models for Unified Human Motion Synthesis","date":"2022-12-06","arxiv_id":"2212.02837","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-conditional-diffusion-networks-for","slug":"semantic-conditional-diffusion-networks-for","title":"Semantic-Conditional Diffusion Networks for Image Captioning","date":"2022-12-06","arxiv_id":"2212.03099","n_code_links":2,"syntology":null},{"paper":"/paper/simple-baseline-for-weather-forecasting-using","slug":"simple-baseline-for-weather-forecasting-using","title":"Simple Baseline for Weather Forecasting Using Spatiotemporal Context Aggregation Network","date":"2022-12-06","arxiv_id":"2212.02952","n_code_links":1,"syntology":{"ran":5,"of":10,"n_ran_checked":5,"n_instrument":0,"unverified":5,"pointer_only":10,"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) · 5 unverified","official":{"repos":["seominseok0429/w4c22-simple-baseline-for-weather-forecasting-using-spatiotemporal-context-aggregation-network"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/unigeo-unifying-geometry-logical-reasoning","slug":"unigeo-unifying-geometry-logical-reasoning","title":"UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression","date":"2022-12-06","arxiv_id":"2212.02746","n_code_links":2,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":4,"phrase":"2 ran (of which 2 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) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["chen-judge/unigeo"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"video-object-of-interest-segmentation","title":"Video Object of Interest Segmentation","date":"2022-12-06","arxiv_id":"2212.02871","n_code_links":0,"syntology":null},{"paper":null,"slug":"3d-latentmapper-view-agnostic-single-view","title":"3D-LatentMapper: View Agnostic Single-View Reconstruction of 3D Shapes","date":"2022-12-05","arxiv_id":"2212.02184","n_code_links":0,"syntology":null},{"paper":null,"slug":"inspired-by-norbert-wiener-feedback-loop","title":"FBLNet: FeedBack Loop Network for Driver Attention Prediction","date":"2022-12-05","arxiv_id":"2212.02096","n_code_links":0,"syntology":null},{"paper":null,"slug":"map-music2vec-a-simple-and-effective-baseline","title":"MAP-Music2Vec: A Simple and Effective Baseline for Self-Supervised Music Audio Representation Learning","date":"2022-12-05","arxiv_id":"2212.02508","n_code_links":0,"syntology":null},{"paper":"/paper/mask-matching-transformer-for-few-shot","slug":"mask-matching-transformer-for-few-shot","title":"Mask Matching Transformer for Few-Shot Segmentation","date":"2022-12-05","arxiv_id":"2301.01208","n_code_links":1,"syntology":null},{"paper":"/paper/retrieval-as-attention-end-to-end-learning-of","slug":"retrieval-as-attention-end-to-end-learning-of","title":"Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer","date":"2022-12-05","arxiv_id":"2212.02027","n_code_links":1,"syntology":null},{"paper":"/paper/unifying-vision-text-and-layout-for-universal","slug":"unifying-vision-text-and-layout-for-universal","title":"Unifying Vision, Text, and Layout for Universal Document Processing","date":"2022-12-05","arxiv_id":"2212.02623","n_code_links":5,"syntology":{"ran":15,"of":17,"n_ran_checked":14,"n_instrument":1,"unverified":2,"pointer_only":4,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 2 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["microsoft/i-code","microsoft/udop"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":null,"slug":"joint-self-supervised-image-volume","title":"Joint Self-Supervised Image-Volume Representation Learning with Intra-Inter Contrastive Clustering","date":"2022-12-04","arxiv_id":"2212.01893","n_code_links":0,"syntology":null},{"paper":"/paper/melody-transcription-via-generative-pre","slug":"melody-transcription-via-generative-pre","title":"Melody transcription via generative pre-training","date":"2022-12-04","arxiv_id":"2212.01884","n_code_links":1,"syntology":null},{"paper":null,"slug":"recognition-and-prediction-of-surgical","title":"Recognition and Prediction of Surgical Gestures and Trajectories Using Transformer Models in Robot-Assisted Surgery","date":"2022-12-03","arxiv_id":"2212.01683","n_code_links":0,"syntology":null},{"paper":"/paper/fecam-frequency-enhanced-channel-attention","slug":"fecam-frequency-enhanced-channel-attention","title":"FECAM: Frequency Enhanced Channel Attention Mechanism for Time Series Forecasting","date":"2022-12-02","arxiv_id":"2212.01209","n_code_links":1,"syntology":null},{"paper":"/paper/relation-aware-language-graph-transformer-for","slug":"relation-aware-language-graph-transformer-for","title":"Relation-Aware Language-Graph Transformer for Question Answering","date":"2022-12-02","arxiv_id":"2212.00975","n_code_links":1,"syntology":null},{"paper":"/paper/slmt-net-a-self-supervised-learning-based","slug":"slmt-net-a-self-supervised-learning-based","title":"Multi-scale Transformer Network with Edge-aware Pre-training for Cross-Modality MR Image Synthesis","date":"2022-12-02","arxiv_id":"2212.01108","n_code_links":2,"syntology":null},{"paper":"/paper/tackling-low-resourced-sign-language","slug":"tackling-low-resourced-sign-language","title":"Tackling Low-Resourced Sign Language Translation: UPC at WMT-SLT 22","date":"2022-12-02","arxiv_id":"2212.01140","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-diverse-relevant-and-coherent-open","title":"Towards Diverse, Relevant and Coherent Open-Domain Dialogue Generation via Hybrid Latent Variables","date":"2022-12-02","arxiv_id":"2212.01145","n_code_links":0,"syntology":null},{"paper":null,"slug":"chapter-exploiting-convolutional-neural","title":"CHAPTER: Exploiting Convolutional Neural Network Adapters for Self-supervised Speech Models","date":"2022-12-01","arxiv_id":"2212.01282","n_code_links":0,"syntology":null},{"paper":null,"slug":"concealed-object-detection-for-passive","title":"Concealed Object Detection for Passive Millimeter-Wave Security Imaging Based on Task-Aligned Detection Transformer","date":"2022-12-01","arxiv_id":"2212.00313","n_code_links":0,"syntology":null},{"paper":null,"slug":"cuni-non-autoregressive-system-for-the-wmt-22","title":"CUNI Non-Autoregressive System for the WMT 22 Efficient Translation Shared Task","date":"2022-12-01","arxiv_id":"2212.00477","n_code_links":0,"syntology":null},{"paper":"/paper/explainable-artificial-intelligence-for-8","slug":"explainable-artificial-intelligence-for-8","title":"Explainable Artificial Intelligence for Improved Modeling of Processes","date":"2022-12-01","arxiv_id":"2212.00695","n_code_links":1,"syntology":null},{"paper":"/paper/ghost-free-high-dynamic-range-imaging-via","slug":"ghost-free-high-dynamic-range-imaging-via","title":"Ghost-free High Dynamic Range Imaging via Hybrid CNN-Transformer and Structure Tensor","date":"2022-12-01","arxiv_id":"2212.00595","n_code_links":1,"syntology":null},{"paper":"/paper/learning-progressive-modality-shared","slug":"learning-progressive-modality-shared","title":"Learning Progressive Modality-shared Transformers for Effective Visible-Infrared Person Re-identification","date":"2022-12-01","arxiv_id":"2212.00226","n_code_links":1,"syntology":null},{"paper":null,"slug":"dsnet-a-simple-yet-efficient-network-with","title":"DSNet: a simple yet efficient network with dual-stream attention for lesion segmentation","date":"2022-11-30","arxiv_id":"2211.16950","n_code_links":0,"syntology":null},{"paper":"/paper/part-based-face-recognition-with-vision","slug":"part-based-face-recognition-with-vision","title":"Part-based Face Recognition with Vision Transformers","date":"2022-11-30","arxiv_id":"2212.00057","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":["szlbiubiubiu/Part_fViT"],"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/pattern-attention-transformer-with-doughnut","slug":"pattern-attention-transformer-with-doughnut","title":"Pattern Attention Transformer with Doughnut Kernel","date":"2022-11-30","arxiv_id":"2211.16961","n_code_links":0,"syntology":null},{"paper":null,"slug":"rephrasing-the-reference-for-non","title":"Rephrasing the Reference for Non-Autoregressive Machine Translation","date":"2022-11-30","arxiv_id":"2211.16863","n_code_links":0,"syntology":null},{"paper":"/paper/t2g-former-organizing-tabular-features-into","slug":"t2g-former-organizing-tabular-features-into","title":"T2G-Former: Organizing Tabular Features into Relation Graphs Promotes Heterogeneous Feature Interaction","date":"2022-11-30","arxiv_id":"2211.16887","n_code_links":1,"syntology":{"ran":13,"of":13,"n_ran_checked":10,"n_instrument":3,"unverified":0,"pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jyansir/t2g-former"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"task-specific-embeddings-for-ante-hoc","title":"Task-Specific Embeddings for Ante-Hoc Explainable Text Classification","date":"2022-11-30","arxiv_id":"2212.00086","n_code_links":0,"syntology":null},{"paper":null,"slug":"topological-data-analysis-for-speech","title":"Topological Data Analysis for Speech Processing","date":"2022-11-30","arxiv_id":"2211.17223","n_code_links":0,"syntology":null},{"paper":"/paper/airformer-predicting-nationwide-air-quality","slug":"airformer-predicting-nationwide-air-quality","title":"AirFormer: Predicting Nationwide Air Quality in China with Transformers","date":"2022-11-29","arxiv_id":"2211.15979","n_code_links":1,"syntology":null},{"paper":"/paper/attribute-de-biased-vision-transformer-ad-vit","slug":"attribute-de-biased-vision-transformer-ad-vit","title":"Attribute De-biased Vision Transformer (AD-ViT) for Long-Term Person Re-identification","date":"2022-11-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/hierarchical-transformer-for-survival","slug":"hierarchical-transformer-for-survival","title":"Hierarchical Transformer for Survival Prediction Using Multimodality Whole Slide Images and Genomics","date":"2022-11-29","arxiv_id":"2211.16632","n_code_links":1,"syntology":null},{"paper":"/paper/noisyquant-noisy-bias-enhanced-post-training","slug":"noisyquant-noisy-bias-enhanced-post-training","title":"NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers","date":"2022-11-29","arxiv_id":"2211.16056","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kriskrisliu/NoisyQuant"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/phrasetransformer-an-incorporation-of-local","slug":"phrasetransformer-an-incorporation-of-local","title":"PhraseTransformer: An Incorporation of Local Context Information into Sequence-to-sequence Semantic Parsing","date":"2022-11-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/spartan-sparse-hierarchical-memory-for","slug":"spartan-sparse-hierarchical-memory-for","title":"SPARTAN: Sparse Hierarchical Memory for Parameter-Efficient Transformers","date":"2022-11-29","arxiv_id":"2211.16634","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-light-touch-approach-to-teaching","title":"A Light Touch Approach to Teaching Transformers Multi-view Geometry","date":"2022-11-28","arxiv_id":"2211.15107","n_code_links":0,"syntology":null},{"paper":null,"slug":"bjtu-wechat-s-systems-for-the-wmt22-chat","title":"BJTU-WeChat's Systems for the WMT22 Chat Translation Task","date":"2022-11-28","arxiv_id":"2211.15009","n_code_links":0,"syntology":null},{"paper":"/paper/connecting-the-dots-floorplan-reconstruction","slug":"connecting-the-dots-floorplan-reconstruction","title":"Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries","date":"2022-11-28","arxiv_id":"2211.15658","n_code_links":1,"syntology":null},{"paper":"/paper/dq-detr-dual-query-detection-transformer-for","slug":"dq-detr-dual-query-detection-transformer-for","title":"DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Grounding","date":"2022-11-28","arxiv_id":"2211.15516","n_code_links":1,"syntology":null},{"paper":null,"slug":"summer-wechat-neural-machine-translation","title":"Summer: WeChat Neural Machine Translation Systems for the WMT22 Biomedical Translation Task","date":"2022-11-28","arxiv_id":"2211.15022","n_code_links":0,"syntology":null},{"paper":"/paper/superpoint-transformer-for-3d-scene-instance","slug":"superpoint-transformer-for-3d-scene-instance","title":"Superpoint Transformer for 3D Scene Instance Segmentation","date":"2022-11-28","arxiv_id":"2211.15766","n_code_links":1,"syntology":null},{"paper":"/paper/3d-point-positional-encoding-for-multi-camera","slug":"3d-point-positional-encoding-for-multi-camera","title":"3DPPE: 3D Point Positional Encoding for Multi-Camera 3D Object Detection Transformers","date":"2022-11-27","arxiv_id":"2211.14710","n_code_links":1,"syntology":null},{"paper":"/paper/a-time-series-is-worth-64-words-long-term","slug":"a-time-series-is-worth-64-words-long-term","title":"A Time Series is Worth 64 Words: Long-term Forecasting with Transformers","date":"2022-11-27","arxiv_id":"2211.14730","n_code_links":8,"syntology":{"ran":17,"of":30,"n_ran_checked":16,"n_instrument":1,"unverified":13,"pointer_only":0,"phrase":"17 ran (of which 2 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 1 where Syntology's instrument failed) · 13 unverified","official":{"repos":["yuqinie98/patchtst"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/prototype-as-query-for-few-shot-semantic","slug":"prototype-as-query-for-few-shot-semantic","title":"Prototype as Query for Few Shot Semantic Segmentation","date":"2022-11-27","arxiv_id":"2211.14764","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":["leileicao/protoformer"],"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":["unlocated"]}}},{"paper":"/paper/semantic-aware-local-global-vision","slug":"semantic-aware-local-global-vision","title":"Semantic-Aware Local-Global Vision Transformer","date":"2022-11-27","arxiv_id":"2211.14705","n_code_links":0,"syntology":null},{"paper":"/paper/cddfuse-correlation-driven-dual-branch","slug":"cddfuse-correlation-driven-dual-branch","title":"CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion","date":"2022-11-26","arxiv_id":"2211.14461","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zhaozixiang1228/mmif-cddfuse"],"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","unlocated"]}}},{"paper":"/paper/cross-field-transformer-for-diabetic","slug":"cross-field-transformer-for-diabetic","title":"Cross-Field Transformer for Diabetic Retinopathy Grading on Two-field Fundus Images","date":"2022-11-26","arxiv_id":"2211.14552","n_code_links":1,"syntology":null},{"paper":"/paper/how-crucial-is-transformer-in-decision","slug":"how-crucial-is-transformer-in-decision","title":"How Crucial is Transformer in Decision Transformer?","date":"2022-11-26","arxiv_id":"2211.14655","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":1,"n_instrument":1,"unverified":3,"pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["max7born/decision-lstm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/patchgt-transformer-over-non-trainable","slug":"patchgt-transformer-over-non-trainable","title":"PatchGT: Transformer over Non-trainable Clusters for Learning Graph Representations","date":"2022-11-26","arxiv_id":"2211.14425","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-based-model-for-word-level","title":"Transformer-based Model for Word Level Language Identification in Code-mixed Kannada-English Texts","date":"2022-11-26","arxiv_id":"2211.14459","n_code_links":0,"syntology":null},{"paper":"/paper/a-system-for-morphology-task-generalization","slug":"a-system-for-morphology-task-generalization","title":"A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation","date":"2022-11-25","arxiv_id":"2211.14296","n_code_links":1,"syntology":null},{"paper":null,"slug":"aggregated-text-transformer-for-scene-text","title":"Aggregated Text Transformer for Scene Text Detection","date":"2022-11-25","arxiv_id":"2211.13984","n_code_links":0,"syntology":null},{"paper":null,"slug":"asynchronous-event-triggered-control-for-non","title":"Asynchronous Event-Triggered Control for Non-Linear Systems","date":"2022-11-25","arxiv_id":"2211.13846","n_code_links":0,"syntology":null},{"paper":"/paper/batmannet-bi-branch-masked-graph-transformer","slug":"batmannet-bi-branch-masked-graph-transformer","title":"BatmanNet: Bi-branch Masked Graph Transformer Autoencoder for Molecular Representation","date":"2022-11-25","arxiv_id":"2211.13979","n_code_links":1,"syntology":null},{"paper":null,"slug":"degenerate-swin-to-win-plain-window-based","title":"Degenerate Swin to Win: Plain Window-based Transformer without Sophisticated Operations","date":"2022-11-25","arxiv_id":"2211.14255","n_code_links":0,"syntology":null},{"paper":"/paper/galvatron-efficient-transformer-training-over","slug":"galvatron-efficient-transformer-training-over","title":"Galvatron: Efficient Transformer Training over Multiple GPUs Using Automatic Parallelism","date":"2022-11-25","arxiv_id":"2211.13878","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["pku-dair/hetu"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/interaction-visual-transformer-for-egocentric","slug":"interaction-visual-transformer-for-egocentric","title":"Interaction Region Visual Transformer for Egocentric Action Anticipation","date":"2022-11-25","arxiv_id":"2211.14154","n_code_links":1,"syntology":null},{"paper":null,"slug":"molecular-joint-representation-learning-via","title":"Molecular Joint Representation Learning via Multi-modal Information","date":"2022-11-25","arxiv_id":"2211.14042","n_code_links":0,"syntology":null},{"paper":null,"slug":"rust-latent-neural-scene-representations-from","title":"RUST: Latent Neural Scene Representations from Unposed Imagery","date":"2022-11-25","arxiv_id":"2211.14306","n_code_links":0,"syntology":null},{"paper":"/paper/spatial-spectral-transformer-for","slug":"spatial-spectral-transformer-for","title":"Spatial-Spectral Transformer for Hyperspectral Image Denoising","date":"2022-11-25","arxiv_id":"2211.14090","n_code_links":3,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["myuli/sst"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":null,"slug":"taotf-a-two-stage-approximately-orthogonal","title":"TAOTF: A Two-stage Approximately Orthogonal Training Framework in Deep Neural Networks","date":"2022-11-25","arxiv_id":"2211.13902","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-naughtyformer-a-transformer-understands","title":"The Naughtyformer: A Transformer Understands Offensive Humor","date":"2022-11-25","arxiv_id":"2211.14369","n_code_links":0,"syntology":null},{"paper":"/paper/uperformer-a-multi-scale-transformer-based","slug":"uperformer-a-multi-scale-transformer-based","title":"MUSTER: A Multi-scale Transformer-based Decoder for Semantic Segmentation","date":"2022-11-25","arxiv_id":"2211.13928","n_code_links":2,"syntology":null},{"paper":"/paper/a-self-attention-ansatz-for-ab-initio-quantum","slug":"a-self-attention-ansatz-for-ab-initio-quantum","title":"A Self-Attention Ansatz for Ab-initio Quantum Chemistry","date":"2022-11-24","arxiv_id":"2211.13672","n_code_links":3,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["deepmind/ferminet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"record_sha256":"308e151d0208276229630078cb958f60c2b6c439d13fdb07c41635410685084f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}