{"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/softmax/papers/268","list_of":"/method/softmax","method":"Softmax","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":268,"pages_in_order":375,"rows_per_page":100,"rows":[26701,26800],"of":37443,"counts":{"archive_papers_tagged":37443,"with_a_code_link":15869,"where_syntology_ran_a_sample":4578,"not_listed_spam_title":0,"listed":37443,"listed_where_code_ran":4578,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3835,"every_run_a_failure_of_syntologys_instrument":743,"listed_with_a_run_with_no_instrument_failure":3835,"listed_every_run_a_failure_of_syntologys_instrument":743,"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/softmax","prev":"/method/softmax/papers/267","next":"/method/softmax/papers/269","papers":[{"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/on-learning-contrastive-representations-for","slug":"on-learning-contrastive-representations-for","title":"On Learning Contrastive Representations for Learning with Noisy Labels","date":"2022-03-03","arxiv_id":"2203.01785","n_code_links":1,"syntology":null},{"paper":"/paper/polarity-sampling-quality-and-diversity","slug":"polarity-sampling-quality-and-diversity","title":"Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values","date":"2022-03-03","arxiv_id":"2203.01993","n_code_links":1,"syntology":null},{"paper":"/paper/selective-residual-m-net-for-real-image","slug":"selective-residual-m-net-for-real-image","title":"Selective Residual M-Net for Real Image Denoising","date":"2022-03-03","arxiv_id":"2203.01645","n_code_links":1,"syntology":null},{"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/advise-adaptive-feature-relevance-and-visual","slug":"advise-adaptive-feature-relevance-and-visual","title":"ADVISE: ADaptive Feature Relevance and VISual Explanations for Convolutional Neural Networks","date":"2022-03-02","arxiv_id":"2203.01289","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/class-re-activation-maps-for-weakly","slug":"class-re-activation-maps-for-weakly","title":"Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation","date":"2022-03-02","arxiv_id":"2203.00962","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":2,"n_instrument":1,"unverified":2,"pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zhaozhengchen/recam"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"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":null,"slug":"gsc-loss-a-gaussian-score-calibrating-loss","title":"Adaptive Discriminative Regularization for Visual Classification","date":"2022-03-02","arxiv_id":"2203.00833","n_code_links":0,"syntology":null},{"paper":null,"slug":"instance-aware-multi-object-self-supervision","title":"Instance-aware multi-object self-supervision for monocular depth prediction","date":"2022-03-02","arxiv_id":"2203.00809","n_code_links":0,"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":null,"slug":"colon-nuclei-instance-segmentation-using-a","title":"Colon Nuclei Instance Segmentation using a Probabilistic Two-Stage Detector","date":"2022-03-01","arxiv_id":"2203.01321","n_code_links":0,"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":"robots-autonomously-detecting-people-a","title":"Robots Autonomously Detecting People: A Multimodal Deep Contrastive Learning Method Robust to Intraclass Variations","date":"2022-03-01","arxiv_id":"2203.00187","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/spatio-temporal-vision-transformer-for-super","slug":"spatio-temporal-vision-transformer-for-super","title":"Spatio-temporal Vision Transformer for Super-resolution Microscopy","date":"2022-02-28","arxiv_id":"2203.00030","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":"a-computer-vision-assisted-approach-to","title":"A Computer Vision-assisted Approach to Automated Real-Time Road Infrastructure Management","date":"2022-02-27","arxiv_id":"2202.13285","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/transformer-based-knowledge-distillation-for","slug":"transformer-based-knowledge-distillation-for","title":"TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation","date":"2022-02-27","arxiv_id":"2202.13393","n_code_links":2,"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":"analysis-of-visual-reasoning-on-one-stage","title":"Analysis of Visual Reasoning on One-Stage Object Detection","date":"2022-02-26","arxiv_id":"2202.13115","n_code_links":0,"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-image-super-resolution-via-quality-map","title":"Multi-image Super-resolution via Quality Map Associated Attention Network","date":"2022-02-26","arxiv_id":"2202.13124","n_code_links":0,"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-data-driven-column-generation-algorithm-for","title":"A Data-Driven Column Generation Algorithm For Bin Packing Problem in Manufacturing Industry","date":"2022-02-25","arxiv_id":"2202.12466","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/extracting-effective-subnetworks-with-gumebel","slug":"extracting-effective-subnetworks-with-gumebel","title":"Extracting Effective Subnetworks with Gumbel-Softmax","date":"2022-02-25","arxiv_id":"2202.12986","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},{"paper":null,"slug":"finite-sum-compositional-stochastic","title":"Finite-Sum Coupled Compositional Stochastic Optimization: Theory and Applications","date":"2022-02-24","arxiv_id":"2202.12396","n_code_links":0,"syntology":null},{"paper":"/paper/from-natural-language-to-simulations-applying","slug":"from-natural-language-to-simulations-applying","title":"From Natural Language to Simulations: Applying GPT-3 Codex to Automate Simulation Modeling of Logistics Systems","date":"2022-02-24","arxiv_id":"2202.12107","n_code_links":1,"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":"pretraining-without-wordpieces-learning-over","title":"Pretraining without Wordpieces: Learning Over a Vocabulary of Millions of Words","date":"2022-02-24","arxiv_id":"2202.12142","n_code_links":0,"syntology":null},{"paper":"/paper/probing-bert-s-priors-with-serial","slug":"probing-bert-s-priors-with-serial","title":"Probing BERT's priors with serial reproduction chains","date":"2022-02-24","arxiv_id":"2202.12226","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["taka-yamakoshi/telephonegame"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/retriever-learning-content-style-1","slug":"retriever-learning-content-style-1","title":"Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph","date":"2022-02-24","arxiv_id":"2202.12307","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xrenaa/Retriever"],"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/sky-computing-accelerating-geo-distributed","slug":"sky-computing-accelerating-geo-distributed","title":"Sky Computing: Accelerating Geo-distributed Computing in Federated Learning","date":"2022-02-24","arxiv_id":"2202.11836","n_code_links":1,"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":"trimbert-tailoring-bert-for-trade-offs","title":"TrimBERT: Tailoring BERT for Trade-offs","date":"2022-02-24","arxiv_id":"2202.12411","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-calibrator-to-improve-robustness-in","title":"Using calibrator to improve robustness in Machine Reading Comprehension","date":"2022-02-24","arxiv_id":"2202.11865","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-bayesian-deep-learning-approach-to-near","title":"A Bayesian Deep Learning Approach to Near-Term Climate Prediction","date":"2022-02-23","arxiv_id":"2202.11244","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":null,"slug":"consistent-dropout-for-policy-gradient","title":"Consistent Dropout for Policy Gradient Reinforcement Learning","date":"2022-02-23","arxiv_id":"2202.11818","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":"integration-of-neural-network-and-fuzzy-logic","title":"Integration of neural network and fuzzy logic decision making compared with bilayered neural network in the simulation of daily dew point temperature","date":"2022-02-23","arxiv_id":"2202.12256","n_code_links":0,"syntology":null},{"paper":"/paper/isda-position-aware-instance-segmentation","slug":"isda-position-aware-instance-segmentation","title":"ISDA: Position-Aware Instance Segmentation with Deformable Attention","date":"2022-02-23","arxiv_id":"2202.12251","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":null,"slug":"skeleton-sequence-and-rgb-frame-based-multi","title":"Skeleton Sequence and RGB Frame Based Multi-Modality Feature Fusion Network for Action Recognition","date":"2022-02-23","arxiv_id":"2202.11374","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":"/paper/when-do-gans-replicate-on-the-choice-of-1","slug":"when-do-gans-replicate-on-the-choice-of-1","title":"When do GANs replicate? On the choice of dataset size","date":"2022-02-23","arxiv_id":"2202.11765","n_code_links":1,"syntology":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":null,"slug":"exploiting-long-term-temporal-dynamics-for","title":"Exploiting long-term temporal dynamics for video captioning","date":"2022-02-22","arxiv_id":"2202.10828","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/improving-ctc-based-speech-recognition-via","slug":"improving-ctc-based-speech-recognition-via","title":"Improving CTC-based speech recognition via knowledge transferring from pre-trained language models","date":"2022-02-22","arxiv_id":"2203.03582","n_code_links":1,"syntology":null},{"paper":null,"slug":"james-job-title-mapping-with-multi-aspect","title":"JAMES: Normalizing Job Titles with Multi-Aspect Graph Embeddings and Reasoning","date":"2022-02-22","arxiv_id":"2202.10739","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-cluster-patterns-for-abstractive","title":"Learning Cluster Patterns for Abstractive Summarization","date":"2022-02-22","arxiv_id":"2202.10967","n_code_links":0,"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/tracking-perovskite-crystallization-via-deep","slug":"tracking-perovskite-crystallization-via-deep","title":"Tracking perovskite crystallization via deep learning-based feature detection on 2D X-ray scattering data","date":"2022-02-22","arxiv_id":"2202.10983","n_code_links":1,"syntology":null}],"record_sha256":"33fe3d9b2be1e80bc8c2a31cbd336ea751ad3f99596d6d989aad32d5e6bad9c3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}