{"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/220","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":220,"pages_in_order":285,"rows_per_page":100,"rows":[21901,22000],"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/219","next":"/method/residual-connection/papers/221","papers":[{"paper":"/paper/graph-transformer-networks-learning-meta-path","slug":"graph-transformer-networks-learning-meta-path","title":"Graph Transformer Networks: Learning Meta-path Graphs to Improve GNNs","date":"2021-06-11","arxiv_id":"2106.06218","n_code_links":1,"syntology":null},{"paper":"/paper/hr-nas-searching-efficient-high-resolution","slug":"hr-nas-searching-efficient-high-resolution","title":"HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers","date":"2021-06-11","arxiv_id":"2106.06560","n_code_links":1,"syntology":{"ran":10,"of":12,"n_ran_checked":8,"n_instrument":2,"unverified":2,"pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["dingmyu/HR-NAS"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/isolated-sign-recognition-from-rgb-video","slug":"isolated-sign-recognition-from-rgb-video","title":"Isolated Sign Recognition from RGB Video using Pose Flow and Self-Attention","date":"2021-06-11","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/mltr-multi-label-classification-with","slug":"mltr-multi-label-classification-with","title":"MlTr: Multi-label Classification with Transformer","date":"2021-06-11","arxiv_id":"2106.06195","n_code_links":1,"syntology":null},{"paper":"/paper/modeling-sequences-as-distributions-with","slug":"modeling-sequences-as-distributions-with","title":"Modeling Sequences as Distributions with Uncertainty for Sequential Recommendation","date":"2021-06-11","arxiv_id":"2106.06165","n_code_links":1,"syntology":null},{"paper":"/paper/n-best-asr-transformer-enhancing-slu","slug":"n-best-asr-transformer-enhancing-slu","title":"N-Best ASR Transformer: Enhancing SLU Performance using Multiple ASR Hypotheses","date":"2021-06-11","arxiv_id":"2106.06519","n_code_links":1,"syntology":null},{"paper":"/paper/neural-symbolic-regression-that-scales","slug":"neural-symbolic-regression-that-scales","title":"Neural Symbolic Regression that Scales","date":"2021-06-11","arxiv_id":"2106.06427","n_code_links":2,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["SymposiumOrganization/NeuralSymbolicRegressionThatScales"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"refbert-compressing-bert-by-referencing-to","title":"RefBERT: Compressing BERT by Referencing to Pre-computed Representations","date":"2021-06-11","arxiv_id":"2106.08898","n_code_links":0,"syntology":null},{"paper":null,"slug":"small-object-detection-for-near-real-time","title":"Small Object Detection for Near Real-Time Egocentric Perception in a Manual Assembly Scenario","date":"2021-06-11","arxiv_id":"2106.06403","n_code_links":0,"syntology":null},{"paper":null,"slug":"vit-inception-gan-for-image-colourising","title":"ViT-Inception-GAN for Image Colourising","date":"2021-06-11","arxiv_id":"2106.06321","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-semi-supervised-multi-task-learning","title":"A Semi-supervised Multi-task Learning Approach to Classify Customer Contact Intents","date":"2021-06-10","arxiv_id":"2106.07381","n_code_links":0,"syntology":null},{"paper":"/paper/amu-euranova-at-case-2021-task-1-assessing","slug":"amu-euranova-at-case-2021-task-1-assessing","title":"AMU-EURANOVA at CASE 2021 Task 1: Assessing the stability of multilingual BERT","date":"2021-06-10","arxiv_id":"2106.14625","n_code_links":1,"syntology":null},{"paper":"/paper/cat-cross-attention-in-vision-transformer","slug":"cat-cross-attention-in-vision-transformer","title":"CAT: Cross Attention in Vision Transformer","date":"2021-06-10","arxiv_id":"2106.05786","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["linhezheng19/CAT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/convolutions-and-self-attention-re","slug":"convolutions-and-self-attention-re","title":"Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models","date":"2021-06-10","arxiv_id":"2106.05505","n_code_links":1,"syntology":null},{"paper":null,"slug":"cross-lingual-emotion-detection","title":"Cross-lingual Emotion Detection","date":"2021-06-10","arxiv_id":"2106.06017","n_code_links":0,"syntology":null},{"paper":null,"slug":"groupbert-enhanced-transformer-architecture","title":"GroupBERT: Enhanced Transformer Architecture with Efficient Grouped Structures","date":"2021-06-10","arxiv_id":"2106.05822","n_code_links":0,"syntology":null},{"paper":"/paper/marginal-utility-diminishes-exploring-the","slug":"marginal-utility-diminishes-exploring-the","title":"Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation","date":"2021-06-10","arxiv_id":"2106.05691","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["llyx97/Marginal-Utility-Diminishes"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"mst-masked-self-supervised-transformer-for","title":"MST: Masked Self-Supervised Transformer for Visual Representation","date":"2021-06-10","arxiv_id":"2106.05656","n_code_links":0,"syntology":null},{"paper":"/paper/programming-puzzles","slug":"programming-puzzles","title":"Programming Puzzles","date":"2021-06-10","arxiv_id":"2106.05784","n_code_links":3,"syntology":null},{"paper":"/paper/scaling-vision-with-sparse-mixture-of-experts","slug":"scaling-vision-with-sparse-mixture-of-experts","title":"Scaling Vision with Sparse Mixture of Experts","date":"2021-06-10","arxiv_id":"2106.05974","n_code_links":1,"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: 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":"semantic-aware-binary-code-representation","title":"Semantic-aware Binary Code Representation with BERT","date":"2021-06-10","arxiv_id":"2106.05478","n_code_links":0,"syntology":null},{"paper":"/paper/space-time-mixing-attention-for-video","slug":"space-time-mixing-attention-for-video","title":"Space-time Mixing Attention for Video Transformer","date":"2021-06-10","arxiv_id":"2106.05968","n_code_links":1,"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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["1adrianb/video-transformers"],"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":"/paper/task-aware-multi-task-learning-for-speech-to","slug":"task-aware-multi-task-learning-for-speech-to","title":"TASK AWARE MULTI-TASK LEARNING FOR SPEECH TO TEXT TASKS","date":"2021-06-10","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-sexism-detection-with-multilingual","title":"Automatic Sexism Detection with Multilingual Transformer Models","date":"2021-06-09","arxiv_id":"2106.04908","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-based-low-dose-synchrotron","title":"Deep learning based low-dose synchrotron radiation CT reconstruction","date":"2021-06-09","arxiv_id":"2106.04792","n_code_links":0,"syntology":null},{"paper":"/paper/do-transformers-really-perform-bad-for-graph","slug":"do-transformers-really-perform-bad-for-graph","title":"Do Transformers Really Perform Bad for Graph Representation?","date":"2021-06-09","arxiv_id":"2106.05234","n_code_links":5,"syntology":null},{"paper":"/paper/grounding-inductive-biases-in-natural-images","slug":"grounding-inductive-biases-in-natural-images","title":"Grounding inductive biases in natural images:invariance stems from variations in data","date":"2021-06-09","arxiv_id":"2106.05121","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":["facebookresearch/grounding-inductive-biases"],"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/instantaneous-grammatical-error-correction","slug":"instantaneous-grammatical-error-correction","title":"Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding","date":"2021-06-09","arxiv_id":"2106.04970","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":0,"n_instrument":3,"unverified":2,"pointer_only":5,"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) · 2 unverified","official":{"repos":["AutoTemp/Shallow-Aggressive-Decoding"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/phraseformer-multimodal-key-phrase-extraction","slug":"phraseformer-multimodal-key-phrase-extraction","title":"Phraseformer: Multimodal Key-phrase Extraction using Transformer and Graph Embedding","date":"2021-06-09","arxiv_id":"2106.04939","n_code_links":0,"syntology":null},{"paper":null,"slug":"realtrans-end-to-end-simultaneous-speech","title":"RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer","date":"2021-06-09","arxiv_id":"2106.04833","n_code_links":0,"syntology":null},{"paper":"/paper/salient-positions-based-attention-network-for","slug":"salient-positions-based-attention-network-for","title":"Salient Positions based Attention Network for Image Classification","date":"2021-06-09","arxiv_id":"2106.04996","n_code_links":1,"syntology":null},{"paper":"/paper/semi-supervised-3d-hand-object-poses","slug":"semi-supervised-3d-hand-object-poses","title":"Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time","date":"2021-06-09","arxiv_id":"2106.05266","n_code_links":1,"syntology":null},{"paper":"/paper/sentence-embeddings-using-supervised","slug":"sentence-embeddings-using-supervised","title":"Sentence Embeddings using Supervised Contrastive Learning","date":"2021-06-09","arxiv_id":"2106.04791","n_code_links":1,"syntology":null},{"paper":"/paper/towards-training-stronger-video-vision","slug":"towards-training-stronger-video-vision","title":"Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognition","date":"2021-06-09","arxiv_id":"2106.05058","n_code_links":1,"syntology":null},{"paper":"/paper/a-survey-of-transformers","slug":"a-survey-of-transformers","title":"A Survey of Transformers","date":"2021-06-08","arxiv_id":"2106.04554","n_code_links":2,"syntology":null},{"paper":"/paper/a-unified-generative-framework-for-aspect","slug":"a-unified-generative-framework-for-aspect","title":"A Unified Generative Framework for Aspect-Based Sentiment Analysis","date":"2021-06-08","arxiv_id":"2106.04300","n_code_links":3,"syntology":null},{"paper":"/paper/cheap-and-good-simple-and-effective-data","slug":"cheap-and-good-simple-and-effective-data","title":"Cheap and Good? Simple and Effective Data Augmentation for Low Resource Machine Reading","date":"2021-06-08","arxiv_id":"2106.04134","n_code_links":1,"syntology":null},{"paper":"/paper/demystifying-local-vision-transformer-sparse","slug":"demystifying-local-vision-transformer-sparse","title":"On the Connection between Local Attention and Dynamic Depth-wise Convolution","date":"2021-06-08","arxiv_id":"2106.04263","n_code_links":1,"syntology":{"ran":11,"of":16,"n_ran_checked":11,"n_instrument":0,"unverified":5,"pointer_only":9,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["atten4vis/demystifylocalvit"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/detreg-unsupervised-pretraining-with-region","slug":"detreg-unsupervised-pretraining-with-region","title":"DETReg: Unsupervised Pretraining with Region Priors for Object Detection","date":"2021-06-08","arxiv_id":"2106.04550","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":2,"n_instrument":3,"unverified":2,"pointer_only":1,"phrase":"5 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; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["amirbar/detreg"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/diverse-part-discovery-occluded-person-re","slug":"diverse-part-discovery-occluded-person-re","title":"Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer","date":"2021-06-08","arxiv_id":"2106.04095","n_code_links":0,"syntology":null},{"paper":null,"slug":"engines-of-power-electricity-ai-and-general","title":"Engines of Power: Electricity, AI, and General-Purpose Military Transformations","date":"2021-06-08","arxiv_id":"2106.04338","n_code_links":0,"syntology":null},{"paper":"/paper/fastseq-make-sequence-generation-faster","slug":"fastseq-make-sequence-generation-faster","title":"FastSeq: Make Sequence Generation Faster","date":"2021-06-08","arxiv_id":"2106.04718","n_code_links":1,"syntology":null},{"paper":"/paper/fully-transformer-networks-for-semantic","slug":"fully-transformer-networks-for-semantic","title":"Fully Transformer Networks for Semantic Image Segmentation","date":"2021-06-08","arxiv_id":"2106.04108","n_code_links":1,"syntology":null},{"paper":null,"slug":"hash-layers-for-large-sparse-models","title":"Hash Layers For Large Sparse Models","date":"2021-06-08","arxiv_id":"2106.04426","n_code_links":0,"syntology":null},{"paper":null,"slug":"mvit-mask-vision-transformer-for-facial","title":"MVT: Mask Vision Transformer for Facial Expression Recognition in the wild","date":"2021-06-08","arxiv_id":"2106.04520","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-lack-of-robust-interpretability-of","title":"On the Lack of Robust Interpretability of Neural Text Classifiers","date":"2021-06-08","arxiv_id":"2106.04631","n_code_links":0,"syntology":null},{"paper":"/paper/reading-stackoverflow-encourages-cheating","slug":"reading-stackoverflow-encourages-cheating","title":"Reading StackOverflow Encourages Cheating: Adding Question Text Improves Extractive Code Generation","date":"2021-06-08","arxiv_id":"2106.04447","n_code_links":1,"syntology":null},{"paper":null,"slug":"recurrent-inference-machines-as-inverse","title":"Recurrent Inference Machines as inverse problem solvers for MR relaxometry","date":"2021-06-08","arxiv_id":"2106.07379","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-vision-transformers","slug":"scaling-vision-transformers","title":"Scaling Vision Transformers","date":"2021-06-08","arxiv_id":"2106.04560","n_code_links":1,"syntology":null},{"paper":null,"slug":"speech-bert-embedding-for-improving-prosody","title":"Speech BERT Embedding For Improving Prosody in Neural TTS","date":"2021-06-08","arxiv_id":"2106.04312","n_code_links":0,"syntology":null},{"paper":"/paper/staircase-attention-for-recurrent-processing","slug":"staircase-attention-for-recurrent-processing","title":"Staircase Attention for Recurrent Processing of Sequences","date":"2021-06-08","arxiv_id":"2106.04279","n_code_links":1,"syntology":null},{"paper":"/paper/timedial-temporal-commonsense-reasoning-in","slug":"timedial-temporal-commonsense-reasoning-in","title":"TIMEDIAL: Temporal Commonsense Reasoning in Dialog","date":"2021-06-08","arxiv_id":"2106.04571","n_code_links":1,"syntology":null},{"paper":"/paper/ultra-fine-entity-typing-with-weak","slug":"ultra-fine-entity-typing-with-weak","title":"Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model","date":"2021-06-08","arxiv_id":"2106.04098","n_code_links":1,"syntology":null},{"paper":null,"slug":"vector-quantized-models-for-planning","title":"Vector Quantized Models for Planning","date":"2021-06-08","arxiv_id":"2106.04615","n_code_links":0,"syntology":null},{"paper":"/paper/attention-temperature-matters-in-abstractive","slug":"attention-temperature-matters-in-abstractive","title":"Attention Temperature Matters in Abstractive Summarization Distillation","date":"2021-06-07","arxiv_id":"2106.03441","n_code_links":1,"syntology":null},{"paper":"/paper/bertgen-multi-task-generation-through-bert","slug":"bertgen-multi-task-generation-through-bert","title":"BERTGEN: Multi-task Generation through BERT","date":"2021-06-07","arxiv_id":"2106.03484","n_code_links":1,"syntology":null},{"paper":null,"slug":"lawdr-language-agnostic-weighted-document","title":"LAWDR: Language-Agnostic Weighted Document Representations from Pre-trained Models","date":"2021-06-07","arxiv_id":"2106.03379","n_code_links":0,"syntology":null},{"paper":null,"slug":"measuring-and-improving-bert-s-mathematical","title":"Measuring and Improving BERT's Mathematical Abilities by Predicting the Order of Reasoning","date":"2021-06-07","arxiv_id":"2106.03921","n_code_links":0,"syntology":null},{"paper":"/paper/neural-abstractive-unsupervised-summarization","slug":"neural-abstractive-unsupervised-summarization","title":"Neural Abstractive Unsupervised Summarization of Online News Discussions","date":"2021-06-07","arxiv_id":"2106.03953","n_code_links":1,"syntology":null},{"paper":null,"slug":"never-guess-what-i-heard-rumor-detection-in","title":"Never guess what I heard... Rumor Detection in Finnish News: a Dataset and a Baseline","date":"2021-06-07","arxiv_id":"2106.03389","n_code_links":0,"syntology":null},{"paper":"/paper/person-re-identification-with-a-locally-aware","slug":"person-re-identification-with-a-locally-aware","title":"Person Re-Identification with a Locally Aware Transformer","date":"2021-06-07","arxiv_id":"2106.03720","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"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) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["SiddhantKapil/LA-Transformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"progressive-open-domain-response-generation","title":"Progressive Open-Domain Response Generation with Multiple Controllable Attributes","date":"2021-06-07","arxiv_id":"2106.14614","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-graph-transformers-with-spectral","slug":"rethinking-graph-transformers-with-spectral","title":"Rethinking Graph Transformers with Spectral Attention","date":"2021-06-07","arxiv_id":"2106.03893","n_code_links":1,"syntology":null},{"paper":null,"slug":"reveal-of-vision-transformers-robustness","title":"Reveal of Vision Transformers Robustness against Adversarial Attacks","date":"2021-06-07","arxiv_id":"2106.03734","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-supervised-depth-estimation-leveraging","title":"Self-supervised Depth Estimation Leveraging Global Perception and Geometric Smoothness Using On-board Videos","date":"2021-06-07","arxiv_id":"2106.03505","n_code_links":0,"syntology":null},{"paper":"/paper/shuffle-transformer-rethinking-spatial","slug":"shuffle-transformer-rethinking-spatial","title":"Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer","date":"2021-06-07","arxiv_id":"2106.03650","n_code_links":4,"syntology":{"ran":10,"of":12,"n_ran_checked":8,"n_instrument":2,"unverified":2,"pointer_only":6,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"the-future-is-log-gaussian-resnets-and-their","title":"The Future is Log-Gaussian: ResNets and Their Infinite-Depth-and-Width Limit at Initialization","date":"2021-06-07","arxiv_id":"2106.04013","n_code_links":0,"syntology":null},{"paper":"/paper/visual-transformer-for-task-aware-active","slug":"visual-transformer-for-task-aware-active","title":"Visual Transformer for Task-aware Active Learning","date":"2021-06-07","arxiv_id":"2106.03801","n_code_links":1,"syntology":null},{"paper":"/paper/vitae-vision-transformer-advanced-by","slug":"vitae-vision-transformer-advanced-by","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","date":"2021-06-07","arxiv_id":"2106.03348","n_code_links":2,"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":["Annbless/ViTAE"],"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/attend-and-select-a-segment-attention-based","slug":"attend-and-select-a-segment-attention-based","title":"Attend and select: A segment selective transformer for microblog hashtag generation","date":"2021-06-06","arxiv_id":"2106.03151","n_code_links":1,"syntology":null},{"paper":"/paper/cape-encoding-relative-positions-with","slug":"cape-encoding-relative-positions-with","title":"CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings","date":"2021-06-06","arxiv_id":"2106.03143","n_code_links":1,"syntology":null},{"paper":"/paper/causal-abstractions-of-neural-networks","slug":"causal-abstractions-of-neural-networks","title":"Causal Abstractions of Neural Networks","date":"2021-06-06","arxiv_id":"2106.02997","n_code_links":1,"syntology":null},{"paper":"/paper/deep-learning-based-type-identification-of","slug":"deep-learning-based-type-identification-of","title":"Deep Learning-based Type Identification of Volumetric MRI Sequences","date":"2021-06-06","arxiv_id":"2106.03208","n_code_links":2,"syntology":null},{"paper":null,"slug":"deep-source-channel-coding-for-sentence","title":"Deep Source-Channel Coding for Sentence Semantic Transmission with HARQ","date":"2021-06-06","arxiv_id":"2106.03009","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-unsupervised-learning-for-joint-antenna","title":"Deep Unsupervised Learning for Joint Antenna Selection and Hybrid Beamforming","date":"2021-06-06","arxiv_id":"2106.03127","n_code_links":0,"syntology":null},{"paper":null,"slug":"oriented-object-detection-with-transformer","title":"Oriented Object Detection with Transformer","date":"2021-06-06","arxiv_id":"2106.03146","n_code_links":0,"syntology":null},{"paper":null,"slug":"regularization-in-resnet-with-stochastic","title":"Regularization in ResNet with Stochastic Depth","date":"2021-06-06","arxiv_id":"2106.03091","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-training-from-scratch-for-object","slug":"rethinking-training-from-scratch-for-object","title":"Rethinking Training from Scratch for Object Detection","date":"2021-06-06","arxiv_id":"2106.03112","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-in-convolutional-neural-networks","slug":"transformer-in-convolutional-neural-networks","title":"Vision Transformers with Hierarchical Attention","date":"2021-06-06","arxiv_id":"2106.03180","n_code_links":3,"syntology":null},{"paper":null,"slug":"transient-chaos-in-bert","title":"Transient Chaos in BERT","date":"2021-06-06","arxiv_id":"2106.03181","n_code_links":0,"syntology":null},{"paper":"/paper/uformer-a-general-u-shaped-transformer-for","slug":"uformer-a-general-u-shaped-transformer-for","title":"Uformer: A General U-Shaped Transformer for Image Restoration","date":"2021-06-06","arxiv_id":"2106.03106","n_code_links":4,"syntology":{"ran":6,"of":6,"n_ran_checked":3,"n_instrument":3,"unverified":0,"pointer_only":2,"phrase":"6 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ZhendongWang6/Uformer"],"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":["listed","official","unlocated"]}}},{"paper":null,"slug":"an-end-to-end-breast-tumour-classification","title":"An End-to-End Breast Tumour Classification Model Using Context-Based Patch Modelling- A BiLSTM Approach for Image Classification","date":"2021-06-05","arxiv_id":"2106.02864","n_code_links":0,"syntology":null},{"paper":"/paper/bertnesia-investigating-the-capture-and-1","slug":"bertnesia-investigating-the-capture-and-1","title":"BERTnesia: Investigating the capture and forgetting of knowledge in BERT","date":"2021-06-05","arxiv_id":"2106.02902","n_code_links":1,"syntology":null},{"paper":"/paper/learnable-fourier-features-for-multi","slug":"learnable-fourier-features-for-multi","title":"Learnable Fourier Features for Multi-Dimensional Spatial Positional Encoding","date":"2021-06-05","arxiv_id":"2106.02795","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"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":null}},{"paper":null,"slug":"t-net-deep-stacked-scale-iteration-network","title":"T-Net: Deep Stacked Scale-Iteration Network for Image Dehazing","date":"2021-06-05","arxiv_id":"2106.02809","n_code_links":0,"syntology":null},{"paper":"/paper/associating-objects-with-transformers-for","slug":"associating-objects-with-transformers-for","title":"Associating Objects with Transformers for Video Object Segmentation","date":"2021-06-04","arxiv_id":"2106.02638","n_code_links":2,"syntology":null},{"paper":"/paper/bert-based-sentiment-analysis-a-software","slug":"bert-based-sentiment-analysis-a-software","title":"BERT-Based Sentiment Analysis: A Software Engineering Perspective","date":"2021-06-04","arxiv_id":"2106.02581","n_code_links":2,"syntology":null},{"paper":"/paper/cross-trajectory-representation-learning-for","slug":"cross-trajectory-representation-learning-for","title":"Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL","date":"2021-06-04","arxiv_id":"2106.02193","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":6,"n_instrument":1,"unverified":4,"pointer_only":11,"phrase":"7 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["bmazoure/ctrl_public"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":2,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"do-syntactic-probes-probe-syntax-experiments","title":"Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing","date":"2021-06-04","arxiv_id":"2106.02559","n_code_links":0,"syntology":null},{"paper":null,"slug":"encoder-decoder-neural-architecture","title":"Encoder-Decoder Neural Architecture Optimization for Keyword Spotting","date":"2021-06-04","arxiv_id":"2106.02738","n_code_links":0,"syntology":null},{"paper":"/paper/ernie-tiny-a-progressive-distillation","slug":"ernie-tiny-a-progressive-distillation","title":"ERNIE-Tiny : A Progressive Distillation Framework for Pretrained Transformer Compression","date":"2021-06-04","arxiv_id":"2106.02241","n_code_links":1,"syntology":null},{"paper":"/paper/few-shot-segmentation-via-cycle-consistent","slug":"few-shot-segmentation-via-cycle-consistent","title":"Few-Shot Segmentation via Cycle-Consistent Transformer","date":"2021-06-04","arxiv_id":"2106.02320","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["GengDavid/CyCTR"],"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/glance-and-gaze-vision-transformer","slug":"glance-and-gaze-vision-transformer","title":"Glance-and-Gaze Vision Transformer","date":"2021-06-04","arxiv_id":"2106.02277","n_code_links":1,"syntology":null},{"paper":null,"slug":"scalable-transformers-for-neural-machine-1","title":"Scalable Transformers for Neural Machine Translation","date":"2021-06-04","arxiv_id":"2106.02242","n_code_links":0,"syntology":null},{"paper":"/paper/self-attention-between-datapoints-going","slug":"self-attention-between-datapoints-going","title":"Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning","date":"2021-06-04","arxiv_id":"2106.02584","n_code_links":3,"syntology":{"ran":22,"of":30,"n_ran_checked":22,"n_instrument":0,"unverified":8,"pointer_only":0,"phrase":"22 ran (of which 4 constructed an object rather than computing a result; 22 with no instrument failure: 2 honoured, 1 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","official":{"repos":["OATML/Non-Parametric-Transformers"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":4,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/the-image-local-autoregressive-transformer","slug":"the-image-local-autoregressive-transformer","title":"The Image Local Autoregressive Transformer","date":"2021-06-04","arxiv_id":"2106.02514","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-equal-gender-representation-in-the","title":"Towards Equal Gender Representation in the Annotations of Toxic Language Detection","date":"2021-06-04","arxiv_id":"2106.02183","n_code_links":0,"syntology":null},{"paper":"/paper/you-only-compress-once-towards-effective-and","slug":"you-only-compress-once-towards-effective-and","title":"You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient","date":"2021-06-04","arxiv_id":"2106.02435","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comparison-for-anti-noise-robustness-of","title":"A Comparison for Anti-noise Robustness of Deep Learning Classification Methods on a Tiny Object Image Dataset: from Convolutional Neural Network to Visual Transformer and Performer","date":"2021-06-03","arxiv_id":"2106.01927","n_code_links":0,"syntology":null},{"paper":"/paper/an-improved-model-for-voicing-silent-speech","slug":"an-improved-model-for-voicing-silent-speech","title":"An Improved Model for Voicing Silent Speech","date":"2021-06-03","arxiv_id":"2106.01933","n_code_links":1,"syntology":null}],"record_sha256":"0c29d4c9302724dbc06a39d983aa22191843e4a6e430ec6d7b880b1f9749e4f9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}