{"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/residual-connection/papers/261","list_of":"/method/residual-connection","method":"Residual Connection","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":261,"pages_in_order":285,"rows_per_page":100,"rows":[26001,26100],"of":28401,"counts":{"archive_papers_tagged":28401,"with_a_code_link":12847,"where_syntology_ran_a_sample":3897,"not_listed_spam_title":0,"listed":28401,"listed_where_code_ran":3897,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3291,"every_run_a_failure_of_syntologys_instrument":606,"listed_with_a_run_with_no_instrument_failure":3291,"listed_every_run_a_failure_of_syntologys_instrument":606,"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/residual-connection","prev":"/method/residual-connection/papers/260","next":"/method/residual-connection/papers/262","papers":[{"paper":null,"slug":"compressing-large-scale-transformer-based","title":"Compressing Large-Scale Transformer-Based Models: A Case Study on BERT","date":"2020-02-27","arxiv_id":"2002.11985","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-and-enhancing-mixed-sample-data","slug":"understanding-and-enhancing-mixed-sample-data","title":"FMix: Enhancing Mixed Sample Data Augmentation","date":"2020-02-27","arxiv_id":"2002.12047","n_code_links":5,"syntology":{"ran":8,"of":8,"n_ran_checked":1,"n_instrument":7,"unverified":0,"pointer_only":3,"phrase":"8 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; 7 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ecs-vlc/FMix"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":null,"slug":"graphcore-c2-card-performance-for-image-based","title":"Graphcore C2 Card performance for image-based deep learning application: A Report","date":"2020-02-26","arxiv_id":"2002.11670","n_code_links":0,"syntology":null},{"paper":"/paper/invariance-vs-robustness-of-neural-networks-1","slug":"invariance-vs-robustness-of-neural-networks-1","title":"Can we have it all? On the Trade-off between Spatial and Adversarial Robustness of Neural Networks","date":"2020-02-26","arxiv_id":"2002.11318","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"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) · 1 unverified","official":{"repos":["ksandeshk/spatial-vs-robustness"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/marathi-to-english-neural-machine-translation","slug":"marathi-to-english-neural-machine-translation","title":"Marathi To English Neural Machine Translation With Near Perfect Corpus And Transformers","date":"2020-02-26","arxiv_id":"2002.11643","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-task-learning-with-multi-head-attention","title":"Multi-task Learning with Multi-head Attention for Multi-choice Reading Comprehension","date":"2020-02-26","arxiv_id":"2003.04992","n_code_links":0,"syntology":null},{"paper":"/paper/sparse-sinkhorn-attention","slug":"sparse-sinkhorn-attention","title":"Sparse Sinkhorn Attention","date":"2020-02-26","arxiv_id":"2002.11296","n_code_links":1,"syntology":null},{"paper":"/paper/train-large-then-compress-rethinking-model","slug":"train-large-then-compress-rethinking-model","title":"Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers","date":"2020-02-26","arxiv_id":"2002.11794","n_code_links":2,"syntology":null},{"paper":"/paper/200210957","slug":"200210957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","date":"2020-02-25","arxiv_id":"2002.10957","n_code_links":1,"syntology":null},{"paper":"/paper/adversarial-perturbations-prevail-in-the-y","slug":"adversarial-perturbations-prevail-in-the-y","title":"Adversarial Perturbations Prevail in the Y-Channel of the YCbCr Color Space","date":"2020-02-25","arxiv_id":"2003.00883","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-can-see-out-of-the-box-on-the-cross","title":"What BERT Sees: Cross-Modal Transfer for Visual Question Generation","date":"2020-02-25","arxiv_id":"2002.10832","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-bert-parameter-efficiency-on-the","title":"Exploring BERT Parameter Efficiency on the Stanford Question Answering Dataset v2.0","date":"2020-02-25","arxiv_id":"2002.10670","n_code_links":0,"syntology":null},{"paper":"/paper/on-feature-normalization-and-data","slug":"on-feature-normalization-and-data","title":"On Feature Normalization and Data Augmentation","date":"2020-02-25","arxiv_id":"2002.11102","n_code_links":1,"syntology":{"ran":6,"of":14,"n_ran_checked":3,"n_instrument":3,"unverified":8,"pointer_only":2,"phrase":"6 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; 3 where Syntology's instrument failed) · 8 unverified","official":{"repos":["Boyiliee/MoEx"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"fixed-encoder-self-attention-patterns-in","title":"Fixed Encoder Self-Attention Patterns in Transformer-Based Machine Translation","date":"2020-02-24","arxiv_id":"2002.10260","n_code_links":0,"syntology":null},{"paper":null,"slug":"gret-global-representation-enhanced","title":"GRET: Global Representation Enhanced Transformer","date":"2020-02-24","arxiv_id":"2002.10101","n_code_links":0,"syntology":null},{"paper":"/paper/improving-bert-fine-tuning-via-self-ensemble","slug":"improving-bert-fine-tuning-via-self-ensemble","title":"Improving BERT Fine-Tuning via Self-Ensemble and Self-Distillation","date":"2020-02-24","arxiv_id":"2002.10345","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/leafgan-an-effective-data-augmentation-method","slug":"leafgan-an-effective-data-augmentation-method","title":"LeafGAN: An Effective Data Augmentation Method for Practical Plant Disease Diagnosis","date":"2020-02-24","arxiv_id":"2002.10100","n_code_links":1,"syntology":null},{"paper":"/paper/predicting-subjective-features-from-questions","slug":"predicting-subjective-features-from-questions","title":"Predicting Subjective Features of Questions of QA Websites using BERT","date":"2020-02-24","arxiv_id":"2002.10107","n_code_links":5,"syntology":null},{"paper":"/paper/sketchformer-transformer-based-representation","slug":"sketchformer-transformer-based-representation","title":"Sketchformer: Transformer-based Representation for Sketched Structure","date":"2020-02-24","arxiv_id":"2002.10381","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":null}},{"paper":null,"slug":"dihard-ii-is-still-hard-experimental-results","title":"DIHARD II is Still Hard: Experimental Results and Discussions from the DKU-LENOVO Team","date":"2020-02-23","arxiv_id":"2002.12761","n_code_links":0,"syntology":null},{"paper":null,"slug":"dotfan-a-domain-transferred-face-augmentation","title":"DotFAN: A Domain-transferred Face Augmentation Network for Pose and Illumination Invariant Face Recognition","date":"2020-02-23","arxiv_id":"2002.09859","n_code_links":0,"syntology":null},{"paper":"/paper/gradual-channel-pruning-while-training-using","slug":"gradual-channel-pruning-while-training-using","title":"Gradual Channel Pruning while Training using Feature Relevance Scores for Convolutional Neural Networks","date":"2020-02-23","arxiv_id":"2002.09958","n_code_links":1,"syntology":null},{"paper":"/paper/practical-and-bilateral-privacy-preserving","slug":"practical-and-bilateral-privacy-preserving","title":"An Accuracy-Lossless Perturbation Method for Defending Privacy Attacks in Federated Learning","date":"2020-02-23","arxiv_id":"2002.09843","n_code_links":1,"syntology":null},{"paper":null,"slug":"training-question-answering-models-from","title":"Training Question Answering Models From Synthetic Data","date":"2020-02-22","arxiv_id":"2002.09599","n_code_links":0,"syntology":null},{"paper":"/paper/accessing-higher-level-representations-in","slug":"accessing-higher-level-representations-in","title":"Addressing Some Limitations of Transformers with Feedback Memory","date":"2020-02-21","arxiv_id":"2002.09402","n_code_links":4,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":2,"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) · 0 unverified","official":{"repos":["facebookresearch/transformer-sequential"],"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":"/paper/learning-dynamic-knowledge-graphs-to","slug":"learning-dynamic-knowledge-graphs-to","title":"Learning Dynamic Belief Graphs to Generalize on Text-Based Games","date":"2020-02-21","arxiv_id":"2002.09127","n_code_links":1,"syntology":null},{"paper":"/paper/tfapprox-towards-a-fast-emulation-of-dnn","slug":"tfapprox-towards-a-fast-emulation-of-dnn","title":"TFApprox: Towards a Fast Emulation of DNN Approximate Hardware Accelerators on GPU","date":"2020-02-21","arxiv_id":"2002.09481","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-hawkes-process","slug":"transformer-hawkes-process","title":"Transformer Hawkes Process","date":"2020-02-21","arxiv_id":"2002.09291","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"5 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["SimiaoZuo/Transformer-Hawkes-Process"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"deep-learning-estimation-of-multi-tissue","title":"Deep Learning Estimation of Multi-Tissue Constrained Spherical Deconvolution with Limited Single Shell DW-MRI","date":"2020-02-20","arxiv_id":"2002.08820","n_code_links":0,"syntology":null},{"paper":"/paper/fast-and-regularized-reconstruction-of","slug":"fast-and-regularized-reconstruction-of","title":"Fast and Regularized Reconstruction of Building Façades from Street-View Images using Binary Integer Programming","date":"2020-02-20","arxiv_id":"2002.08549","n_code_links":1,"syntology":null},{"paper":null,"slug":"federated-pretraining-and-fine-tuning-of-bert","title":"Federated pretraining and fine tuning of BERT using clinical notes from multiple silos","date":"2020-02-20","arxiv_id":"2002.08562","n_code_links":0,"syntology":null},{"paper":"/paper/maxup-a-simple-way-to-improve-generalization","slug":"maxup-a-simple-way-to-improve-generalization","title":"MaxUp: A Simple Way to Improve Generalization of Neural Network Training","date":"2020-02-20","arxiv_id":"2002.09024","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":null}},{"paper":"/paper/compressing-bert-studying-the-effects-of-1","slug":"compressing-bert-studying-the-effects-of-1","title":"Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning","date":"2020-02-19","arxiv_id":"2002.08307","n_code_links":1,"syntology":null},{"paper":"/paper/knapsack-pruning-with-inner-distillation","slug":"knapsack-pruning-with-inner-distillation","title":"Knapsack Pruning with Inner Distillation","date":"2020-02-19","arxiv_id":"2002.08258","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"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":["yoniaflalo/knapsack_pruning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/lambert-layout-aware-language-modeling-using","slug":"lambert-layout-aware-language-modeling-using","title":"LAMBERT: Layout-Aware (Language) Modeling for information extraction","date":"2020-02-19","arxiv_id":"2002.08087","n_code_links":1,"syntology":null},{"paper":"/paper/modelling-response-to-trypophobia-trigger","slug":"modelling-response-to-trypophobia-trigger","title":"Modelling response to trypophobia trigger using intermediate layers of ImageNet networks","date":"2020-02-19","arxiv_id":"2002.08490","n_code_links":1,"syntology":null},{"paper":"/paper/molecule-attention-transformer","slug":"molecule-attention-transformer","title":"Molecule Attention Transformer","date":"2020-02-19","arxiv_id":"2002.08264","n_code_links":7,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["gmum/MAT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":"/paper/nnoculation-broad-spectrum-and-targeted","slug":"nnoculation-broad-spectrum-and-targeted","title":"NNoculation: Catching BadNets in the Wild","date":"2020-02-19","arxiv_id":"2002.08313","n_code_links":1,"syntology":null},{"paper":"/paper/the-microsoft-toolkit-of-multi-task-deep","slug":"the-microsoft-toolkit-of-multi-task-deep","title":"The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding","date":"2020-02-19","arxiv_id":"2002.07972","n_code_links":3,"syntology":null},{"paper":"/paper/toward-making-the-most-of-context-in-neural","slug":"toward-making-the-most-of-context-in-neural","title":"Towards Making the Most of Context in Neural Machine Translation","date":"2020-02-19","arxiv_id":"2002.07982","n_code_links":1,"syntology":null},{"paper":null,"slug":"tree-structured-attention-with-hierarchical-1","title":"Tree-structured Attention with Hierarchical Accumulation","date":"2020-02-19","arxiv_id":"2002.08046","n_code_links":0,"syntology":null},{"paper":null,"slug":"conditional-self-attention-for-query-based","title":"Conditional Self-Attention for Query-based Summarization","date":"2020-02-18","arxiv_id":"2002.07338","n_code_links":0,"syntology":null},{"paper":"/paper/from-english-to-foreign-languages-1","slug":"from-english-to-foreign-languages-1","title":"From English To Foreign Languages: Transferring Pre-trained Language Models","date":"2020-02-18","arxiv_id":"2002.07306","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/gradient-based-adversarial-training-on","slug":"gradient-based-adversarial-training-on","title":"Gradient-Based Adversarial Training on Transformer Networks for Detecting Check-Worthy Factual Claims","date":"2020-02-18","arxiv_id":"2002.07725","n_code_links":1,"syntology":null},{"paper":"/paper/hierarchical-transformer-network-for","slug":"hierarchical-transformer-network-for","title":"Hierarchical Transformer Network for Utterance-level Emotion Recognition","date":"2020-02-18","arxiv_id":"2002.07551","n_code_links":0,"syntology":null},{"paper":"/paper/picking-winning-tickets-before-training-by-1","slug":"picking-winning-tickets-before-training-by-1","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","date":"2020-02-18","arxiv_id":"2002.07376","n_code_links":3,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["alecwangcq/GraSP"],"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":"/paper/sequential-latent-knowledge-selection-for-1","slug":"sequential-latent-knowledge-selection-for-1","title":"Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue","date":"2020-02-18","arxiv_id":"2002.07510","n_code_links":3,"syntology":{"ran":0,"of":5,"n_ran_checked":0,"n_instrument":0,"unverified":5,"pointer_only":5,"phrase":"0 ran · 5 unverified","official":{"repos":["bckim92/sequential-knowledge-transformer"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":"/paper/uncertainty-in-structured-prediction","slug":"uncertainty-in-structured-prediction","title":"Uncertainty Estimation in Autoregressive Structured Prediction","date":"2020-02-18","arxiv_id":"2002.07650","n_code_links":1,"syntology":null},{"paper":"/paper/v4d4d-convolutional-neural-networks-for-video","slug":"v4d4d-convolutional-neural-networks-for-video","title":"V4D:4D Convolutional Neural Networks for Video-level Representation Learning","date":"2020-02-18","arxiv_id":"2002.07442","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-financial-service-chatbot-based-on-deep","title":"A Financial Service Chatbot based on Deep Bidirectional Transformers","date":"2020-02-17","arxiv_id":"2003.04987","n_code_links":0,"syntology":null},{"paper":null,"slug":"controlling-computation-versus-quality-for","title":"Controlling Computation versus Quality for Neural Sequence Models","date":"2020-02-17","arxiv_id":"2002.07106","n_code_links":0,"syntology":null},{"paper":"/paper/incorporating-bert-into-neural-machine-1","slug":"incorporating-bert-into-neural-machine-1","title":"Incorporating BERT into Neural Machine Translation","date":"2020-02-17","arxiv_id":"2002.06823","n_code_links":3,"syntology":null},{"paper":"/paper/learning-architectures-for-binary-networks","slug":"learning-architectures-for-binary-networks","title":"Learning Architectures for Binary Networks","date":"2020-02-17","arxiv_id":"2002.06963","n_code_links":1,"syntology":null},{"paper":null,"slug":"low-rank-bottleneck-in-multi-head-attention","title":"Low-Rank Bottleneck in Multi-head Attention Models","date":"2020-02-17","arxiv_id":"2002.07028","n_code_links":0,"syntology":null},{"paper":"/paper/precision-gating-improving-neural-network-1","slug":"precision-gating-improving-neural-network-1","title":"Precision Gating: Improving Neural Network Efficiency with Dynamic Dual-Precision Activations","date":"2020-02-17","arxiv_id":"2002.07136","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"9 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; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["cornell-zhang/dnn-gating"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":8,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"unsupervised-image-generation-enhanced","title":"Unsupervised Image-generation Enhanced Adaptation for Object Detection in Thermal images","date":"2020-02-17","arxiv_id":"2002.06770","n_code_links":0,"syntology":null},{"paper":"/paper/active-bayesian-assessment-for-black-box","slug":"active-bayesian-assessment-for-black-box","title":"Active Bayesian Assessment for Black-Box Classifiers","date":"2020-02-16","arxiv_id":"2002.06532","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"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":["disiji/bayesian-blackbox"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/multi-layer-representation-fusion-for-neural-2","slug":"multi-layer-representation-fusion-for-neural-2","title":"Multi-layer Representation Fusion for Neural Machine Translation","date":"2020-02-16","arxiv_id":"2002.06714","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":null}},{"paper":null,"slug":"multi-task-siamese-neural-network-for","title":"Multi-Task Siamese Neural Network for Improving Replay Attack Detection","date":"2020-02-16","arxiv_id":"2002.07629","n_code_links":0,"syntology":null},{"paper":"/paper/neural-machine-translation-with-joint","slug":"neural-machine-translation-with-joint","title":"Neural Machine Translation with Joint Representation","date":"2020-02-16","arxiv_id":"2002.06546","n_code_links":1,"syntology":null},{"paper":"/paper/sbert-wk-a-sentence-embedding-method-by","slug":"sbert-wk-a-sentence-embedding-method-by","title":"SBERT-WK: A Sentence Embedding Method by Dissecting BERT-based Word Models","date":"2020-02-16","arxiv_id":"2002.06652","n_code_links":3,"syntology":null},{"paper":null,"slug":"the-utility-of-general-domain-transfer","title":"The Utility of General Domain Transfer Learning for Medical Language Tasks","date":"2020-02-16","arxiv_id":"2002.06670","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-lesion-segmentation-and","title":"Automatic lesion segmentation and Pathological Myopia classification in fundus images","date":"2020-02-15","arxiv_id":"2002.06382","n_code_links":0,"syntology":null},{"paper":"/paper/fine-tuning-pretrained-language-models-weight","slug":"fine-tuning-pretrained-language-models-weight","title":"Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping","date":"2020-02-15","arxiv_id":"2002.06305","n_code_links":4,"syntology":null},{"paper":null,"slug":"many-to-many-voice-conversion-using","title":"Many-to-Many Voice Conversion using Conditional Cycle-Consistent Adversarial Networks","date":"2020-02-15","arxiv_id":"2002.06328","n_code_links":0,"syntology":null},{"paper":null,"slug":"small-energy-masking-for-improved-neural","title":"Small energy masking for improved neural network training for end-to-end speech recognition","date":"2020-02-15","arxiv_id":"2002.06312","n_code_links":0,"syntology":null},{"paper":"/paper/univilm-a-unified-video-and-language-pre","slug":"univilm-a-unified-video-and-language-pre","title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","date":"2020-02-15","arxiv_id":"2002.06353","n_code_links":2,"syntology":{"ran":1,"of":4,"n_ran_checked":0,"n_instrument":1,"unverified":3,"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) · 3 unverified","official":{"repos":["microsoft/UniVL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"paper":null,"slug":"deep-attentive-study-session-dropout","title":"Deep Attentive Study Session Dropout Prediction in Mobile Learning Environment","date":"2020-02-14","arxiv_id":"2002.11624","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-speaker-embeddings-for-far-field-speaker","title":"Deep Speaker Embeddings for Far-Field Speaker Recognition on Short Utterances","date":"2020-02-14","arxiv_id":"2002.06033","n_code_links":0,"syntology":null},{"paper":"/paper/fquad-french-question-answering-dataset","slug":"fquad-french-question-answering-dataset","title":"FQuAD: French Question Answering Dataset","date":"2020-02-14","arxiv_id":"2002.06071","n_code_links":0,"syntology":null},{"paper":"/paper/gsanet-semantic-segmentation-with-global-and","slug":"gsanet-semantic-segmentation-with-global-and","title":"GSANet: Semantic Segmentation with Global and Selective Attention","date":"2020-02-14","arxiv_id":"2003.00830","n_code_links":0,"syntology":null},{"paper":"/paper/skip-connections-matter-on-the","slug":"skip-connections-matter-on-the","title":"Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets","date":"2020-02-14","arxiv_id":"2002.05990","n_code_links":4,"syntology":{"ran":4,"of":9,"n_ran_checked":1,"n_instrument":3,"unverified":5,"pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 5 unverified","official":{"repos":["csdongxian/skip-connections-matter"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"stress-test-evaluation-of-transformer-based","title":"Stress Test Evaluation of Transformer-based Models in Natural Language Understanding Tasks","date":"2020-02-14","arxiv_id":"2002.06261","n_code_links":0,"syntology":null},{"paper":"/paper/towards-an-appropriate-query-key-and-value","slug":"towards-an-appropriate-query-key-and-value","title":"Towards an Appropriate Query, Key, and Value Computation for Knowledge Tracing","date":"2020-02-14","arxiv_id":"2002.07033","n_code_links":5,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/transformer-on-a-diet","slug":"transformer-on-a-diet","title":"Transformer on a Diet","date":"2020-02-14","arxiv_id":"2002.06170","n_code_links":1,"syntology":null},{"paper":"/paper/twinbert-distilling-knowledge-to-twin","slug":"twinbert-distilling-knowledge-to-twin","title":"TwinBERT: Distilling Knowledge to Twin-Structured BERT Models for Efficient Retrieval","date":"2020-02-14","arxiv_id":"2002.06275","n_code_links":2,"syntology":null},{"paper":null,"slug":"understanding-patient-complaint","title":"Understanding patient complaint characteristics using contextual clinical BERT embeddings","date":"2020-02-14","arxiv_id":"2002.05902","n_code_links":0,"syntology":null},{"paper":"/paper/a-simple-framework-for-contrastive-learning","slug":"a-simple-framework-for-contrastive-learning","title":"A Simple Framework for Contrastive Learning of Visual Representations","date":"2020-02-13","arxiv_id":"2002.05709","n_code_links":96,"syntology":{"ran":115,"of":137,"n_ran_checked":90,"n_instrument":25,"unverified":22,"pointer_only":52,"phrase":"115 ran (of which 33 constructed an object rather than computing a result; 90 with no instrument failure: 1 honoured, 1 violated, 88 with no contract checked; 25 where Syntology's instrument failed) · 22 unverified","official":{"repos":["google-research/simclr"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"cbag-conditional-biomedical-abstract","title":"CBAG: Conditional Biomedical Abstract Generation","date":"2020-02-13","arxiv_id":"2002.05637","n_code_links":0,"syntology":null},{"paper":"/paper/cross-iteration-batch-normalization","slug":"cross-iteration-batch-normalization","title":"Cross-Iteration Batch Normalization","date":"2020-02-13","arxiv_id":"2002.05712","n_code_links":2,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["Howal/Cross-iterationBatchNorm"],"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/endol2h-deep-super-resolution-for-capsule","slug":"endol2h-deep-super-resolution-for-capsule","title":"EndoL2H: Deep Super-Resolution for Capsule Endoscopy","date":"2020-02-13","arxiv_id":"2002.05459","n_code_links":3,"syntology":null},{"paper":"/paper/pcsgan-perceptual-cyclic-synthesized","slug":"pcsgan-perceptual-cyclic-synthesized","title":"PCSGAN: Perceptual Cyclic-Synthesized Generative Adversarial Networks for Thermal and NIR to Visible Image Transformation","date":"2020-02-13","arxiv_id":"2002.07082","n_code_links":1,"syntology":null},{"paper":"/paper/physical-accuracy-of-deep-neural-networks-for","slug":"physical-accuracy-of-deep-neural-networks-for","title":"Physical Accuracy of Deep Neural Networks for 2D and 3D Multi-Mineral Segmentation of Rock micro-CT Images","date":"2020-02-13","arxiv_id":"2002.05322","n_code_links":1,"syntology":null},{"paper":"/paper/sparse-and-structured-visual-attention-1","slug":"sparse-and-structured-visual-attention-1","title":"Sparse and Structured Visual Attention","date":"2020-02-13","arxiv_id":"2002.05556","n_code_links":1,"syntology":null},{"paper":"/paper/spotnet-self-attention-multi-task-network-for","slug":"spotnet-self-attention-multi-task-network-for","title":"SpotNet: Self-Attention Multi-Task Network for Object Detection","date":"2020-02-13","arxiv_id":"2002.05540","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-use-of-convolutional-neural-networks-for","title":"The use of Convolutional Neural Networks for signal-background classification in Particle Physics experiments","date":"2020-02-13","arxiv_id":"2002.05761","n_code_links":0,"syntology":null},{"paper":"/paper/training-large-neural-networks-with-constant","slug":"training-large-neural-networks-with-constant","title":"Training Large Neural Networks with Constant Memory using a New Execution Algorithm","date":"2020-02-13","arxiv_id":"2002.05645","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/attentional-speech-recognition-models","slug":"attentional-speech-recognition-models","title":"Attentional Speech Recognition Models Misbehave on Out-of-domain Utterances","date":"2020-02-12","arxiv_id":"2002.05150","n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-face-parsing-via-interlinked","slug":"end-to-end-face-parsing-via-interlinked","title":"End-to-End Face Parsing via Interlinked Convolutional Neural Networks","date":"2020-02-12","arxiv_id":"2002.04831","n_code_links":1,"syntology":null},{"paper":"/paper/glu-variants-improve-transformer","slug":"glu-variants-improve-transformer","title":"GLU Variants Improve Transformer","date":"2020-02-12","arxiv_id":"2002.05202","n_code_links":27,"syntology":{"ran":9,"of":9,"n_ran_checked":7,"n_instrument":2,"unverified":0,"pointer_only":7,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 4 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"learning-to-compare-for-better-training-and","title":"Learning to Compare for Better Training and Evaluation of Open Domain Natural Language Generation Models","date":"2020-02-12","arxiv_id":"2002.05058","n_code_links":0,"syntology":null},{"paper":"/paper/lookahead-a-far-sighted-alternative-of-1","slug":"lookahead-a-far-sighted-alternative-of-1","title":"Lookahead: a Far-Sighted Alternative of Magnitude-based Pruning","date":"2020-02-12","arxiv_id":"2002.04809","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":6,"n_instrument":2,"unverified":2,"pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 6 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["alinlab/lookahead_pruning"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/on-layer-normalization-in-the-transformer-1","slug":"on-layer-normalization-in-the-transformer-1","title":"On Layer Normalization in the Transformer Architecture","date":"2020-02-12","arxiv_id":"2002.04745","n_code_links":9,"syntology":{"ran":10,"of":11,"n_ran_checked":10,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/utilizing-bert-intermediate-layers-for-aspect","slug":"utilizing-bert-intermediate-layers-for-aspect","title":"Utilizing BERT Intermediate Layers for Aspect Based Sentiment Analysis and Natural Language Inference","date":"2020-02-12","arxiv_id":"2002.04815","n_code_links":1,"syntology":null},{"paper":null,"slug":"best-of-both-worlds-automl-codesign-of-a-cnn","title":"Best of Both Worlds: AutoML Codesign of a CNN and its Hardware Accelerator","date":"2020-02-11","arxiv_id":"2002.05022","n_code_links":0,"syntology":null},{"paper":null,"slug":"improved-consistency-regularization-for-gans","title":"Improved Consistency Regularization for GANs","date":"2020-02-11","arxiv_id":"2002.04724","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimal-transfer-learning-model-for-binary","title":"Optimal Transfer Learning Model for Binary Classification of Funduscopic Images through Simple Heuristics","date":"2020-02-11","arxiv_id":"2002.04189","n_code_links":0,"syntology":null},{"paper":null,"slug":"superbloom-bloom-filter-meets-transformer-1","title":"Superbloom: Bloom filter meets Transformer","date":"2020-02-11","arxiv_id":"2002.04723","n_code_links":0,"syntology":null},{"paper":"/paper/the-devil-is-in-the-channels-mutual-channel","slug":"the-devil-is-in-the-channels-mutual-channel","title":"The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification","date":"2020-02-11","arxiv_id":"2002.04264","n_code_links":3,"syntology":{"ran":4,"of":5,"n_ran_checked":3,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"4 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["dongliangchang/Mutual-Channel-Loss"],"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":["listed","official"]}}},{"paper":null,"slug":"training-with-streaming-annotation","title":"Training with Streaming Annotation","date":"2020-02-11","arxiv_id":"2002.04165","n_code_links":0,"syntology":null}],"record_sha256":"d2236547526a8b8058bdb29362106e0c05e99aa3a501fd71ed3057c5b3574839","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}