{"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/298","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":298,"pages_in_order":375,"rows_per_page":100,"rows":[29701,29800],"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/297","next":"/method/softmax/papers/299","papers":[{"paper":null,"slug":"target-model-agnostic-adversarial-attacks","title":"Target Model Agnostic Adversarial Attacks with Query Budgets on Language Understanding Models","date":"2021-06-13","arxiv_id":"2106.07047","n_code_links":0,"syntology":null},{"paper":"/paper/the-deformer-an-order-agnostic-distribution","slug":"the-deformer-an-order-agnostic-distribution","title":"The DEformer: An Order-Agnostic Distribution Estimating Transformer","date":"2021-06-13","arxiv_id":"2106.06989","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":2,"n_instrument":0,"unverified":3,"pointer_only":5,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["airalcorn2/deformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/thinking-like-transformers-1","slug":"thinking-like-transformers-1","title":"Thinking Like Transformers","date":"2021-06-13","arxiv_id":"2106.06981","n_code_links":5,"syntology":{"ran":11,"of":18,"n_ran_checked":7,"n_instrument":4,"unverified":7,"pointer_only":5,"phrase":"11 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","official":{"repos":["tech-srl/RASP"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/a-sentence-level-hierarchical-bert-model-for","slug":"a-sentence-level-hierarchical-bert-model-for","title":"A Sentence-level Hierarchical BERT Model for Document Classification with Limited Labelled Data","date":"2021-06-12","arxiv_id":"2106.06738","n_code_links":1,"syntology":null},{"paper":"/paper/adversarial-robustness-via-fisher-rao","slug":"adversarial-robustness-via-fisher-rao","title":"Adversarial Robustness via Fisher-Rao Regularization","date":"2021-06-12","arxiv_id":"2106.06685","n_code_links":1,"syntology":null},{"paper":null,"slug":"curriculum-pre-training-heterogeneous","title":"Curriculum Pre-Training Heterogeneous Subgraph Transformer for Top-$N$ Recommendation","date":"2021-06-12","arxiv_id":"2106.06722","n_code_links":0,"syntology":null},{"paper":"/paper/ds-transunet-dual-swin-transformer-u-net-for","slug":"ds-transunet-dual-swin-transformer-u-net-for","title":"DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentation","date":"2021-06-12","arxiv_id":"2106.06716","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":1,"n_instrument":4,"unverified":0,"pointer_only":5,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["TianBaoGe/DS-TransUNet"],"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","unlocated"]}}},{"paper":null,"slug":"explaining-the-deep-natural-language","title":"Explaining the Deep Natural Language Processing by Mining Textual Interpretable Features","date":"2021-06-12","arxiv_id":"2106.06697","n_code_links":0,"syntology":null},{"paper":"/paper/neural-combinatory-constituency-parsing","slug":"neural-combinatory-constituency-parsing","title":"Neural Combinatory Constituency Parsing","date":"2021-06-12","arxiv_id":"2106.06689","n_code_links":1,"syntology":null},{"paper":"/paper/video-super-resolution-transformer","slug":"video-super-resolution-transformer","title":"Video Super-Resolution Transformer","date":"2021-06-12","arxiv_id":"2106.06847","n_code_links":1,"syntology":null},{"paper":"/paper/bioelectra-pretrained-biomedical-text-encoder","slug":"bioelectra-pretrained-biomedical-text-encoder","title":"BioELECTRA:Pretrained Biomedical text Encoder using Discriminators","date":"2021-06-11","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/break-it-fix-it-unsupervised-learning-for","slug":"break-it-fix-it-unsupervised-learning-for","title":"Break-It-Fix-It: Unsupervised Learning for Program Repair","date":"2021-06-11","arxiv_id":"2106.06600","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["michiyasunaga/bifi"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"decore-deep-compression-with-reinforcement","title":"DECORE: Deep Compression with Reinforcement Learning","date":"2021-06-11","arxiv_id":"2106.06091","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-language-models-for-continuously","title":"Dynamic Language Models for Continuously Evolving Content","date":"2021-06-11","arxiv_id":"2106.06297","n_code_links":0,"syntology":null},{"paper":"/paper/generate-annotate-and-learn-generative-models","slug":"generate-annotate-and-learn-generative-models","title":"Generate, Annotate, and Learn: NLP with Synthetic Text","date":"2021-06-11","arxiv_id":"2106.06168","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xlhex/gal_syntex"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/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/improving-pretrained-cross-lingual-language","slug":"improving-pretrained-cross-lingual-language","title":"Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment","date":"2021-06-11","arxiv_id":"2106.06381","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["CZWin32768/XLM-Align"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"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/a-template-guided-hybrid-pointer-network-for","slug":"a-template-guided-hybrid-pointer-network-for","title":"A Template-guided Hybrid Pointer Network for Knowledge-basedTask-oriented Dialogue Systems","date":"2021-06-10","arxiv_id":"2106.05830","n_code_links":1,"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":null,"slug":"joint-landmark-and-structure-learning-for","title":"Joint Landmark and Structure Learning for Automatic Evaluation of Developmental Dysplasia of the Hip","date":"2021-06-10","arxiv_id":"2106.05458","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":"/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":null,"slug":"nerf-in-detail-learning-to-sample-for-view","title":"NeRF in detail: Learning to sample for view synthesis","date":"2021-06-09","arxiv_id":"2106.05264","n_code_links":0,"syntology":null},{"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/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":null,"slug":"understanding-softmax-confidence-and","title":"Understanding Softmax Confidence and Uncertainty","date":"2021-06-09","arxiv_id":"2106.04972","n_code_links":0,"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":"linear-convergence-of-entropy-regularized","title":"Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation","date":"2021-06-08","arxiv_id":"2106.04096","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":"/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":"/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":"generative-flows-with-invertible-attentions","title":"Generative Flows with Invertible Attentions","date":"2021-06-07","arxiv_id":"2106.03959","n_code_links":0,"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":null,"slug":"multi-modal-entity-alignment-in-hyperbolic","title":"Multi-modal Entity Alignment in Hyperbolic Space","date":"2021-06-07","arxiv_id":"2106.03619","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":null,"slug":"open-source-disease-analysis-system-of-cactus","title":"Open source disease analysis system of cactus by artificial intelligence and image processing","date":"2021-06-07","arxiv_id":"2106.03669","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/refiner-refining-self-attention-for-vision","slug":"refiner-refining-self-attention-for-vision","title":"Refiner: Refining Self-attention for Vision Transformers","date":"2021-06-07","arxiv_id":"2106.03714","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":3,"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) · 1 unverified","official":{"repos":["zhoudaquan/Refiner_ViT"],"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":["official"]}}},{"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":"supervised-adptive-threshold-network-for","title":"supervised adptive threshold network for instance segmentation","date":"2021-06-07","arxiv_id":"2106.03450","n_code_links":0,"syntology":null},{"paper":"/paper/training-strategies-for-deep-learning","slug":"training-strategies-for-deep-learning","title":"Training Strategies for Deep Learning Gravitational-Wave Searches","date":"2021-06-07","arxiv_id":"2106.03741","n_code_links":1,"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/zero-shot-knowledge-distillation-from-a","slug":"zero-shot-knowledge-distillation-from-a","title":"Zero-Shot Knowledge Distillation from a Decision-Based Black-Box Model","date":"2021-06-07","arxiv_id":"2106.03310","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"pointer_only":4,"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) · 3 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["zwang84/zsdb3kd"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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":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":"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":"/paper/reducing-the-feature-divergence-of-rgb-and","slug":"reducing-the-feature-divergence-of-rgb-and","title":"Reducing the feature divergence of RGB and near-infrared images using Switchable Normalization","date":"2021-06-06","arxiv_id":"2106.03088","n_code_links":1,"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}],"record_sha256":"7145a2bd9931ba1ff09ff673ad5a6a70ffa82614180c3833866a34fd4a3af30f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}