{"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/layer-normalization/papers/199","list_of":"/method/layer-normalization","method":"Layer Normalization","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":199,"pages_in_order":250,"rows_per_page":100,"rows":[19801,19900],"of":24980,"counts":{"archive_papers_tagged":24980,"with_a_code_link":11273,"where_syntology_ran_a_sample":3471,"not_listed_spam_title":0,"listed":24980,"listed_where_code_ran":3471,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2923,"every_run_a_failure_of_syntologys_instrument":548,"listed_with_a_run_with_no_instrument_failure":2923,"listed_every_run_a_failure_of_syntologys_instrument":548,"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/layer-normalization","prev":"/method/layer-normalization/papers/198","next":"/method/layer-normalization/papers/200","papers":[{"paper":"/paper/rethinking-why-intermediate-task-fine-tuning","slug":"rethinking-why-intermediate-task-fine-tuning","title":"Rethinking Why Intermediate-Task Fine-Tuning Works","date":"2021-08-26","arxiv_id":"2108.11696","n_code_links":1,"syntology":null},{"paper":null,"slug":"shifted-chunk-transformer-for-spatio-temporal","title":"Shifted Chunk Transformer for Spatio-Temporal Representational Learning","date":"2021-08-26","arxiv_id":"2108.11575","n_code_links":0,"syntology":null},{"paper":"/paper/slim-explicit-slot-intent-mapping-with-bert","slug":"slim-explicit-slot-intent-mapping-with-bert","title":"SLIM: Explicit Slot-Intent Mapping with BERT for Joint Multi-Intent Detection and Slot Filling","date":"2021-08-26","arxiv_id":"2108.11711","n_code_links":1,"syntology":null},{"paper":"/paper/the-devil-is-in-the-detail-simple-tricks","slug":"the-devil-is-in-the-detail-simple-tricks","title":"The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers","date":"2021-08-26","arxiv_id":"2108.12284","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["robertcsordas/transformer_generalization"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/tph-yolov5-improved-yolov5-based-on","slug":"tph-yolov5-improved-yolov5-based-on","title":"TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios","date":"2021-08-26","arxiv_id":"2108.11539","n_code_links":3,"syntology":null},{"paper":"/paper/understanding-attention-in-machine-reading","slug":"understanding-attention-in-machine-reading","title":"Multilingual Multi-Aspect Explainability Analyses on Machine Reading Comprehension Models","date":"2021-08-26","arxiv_id":"2108.11574","n_code_links":1,"syntology":null},{"paper":null,"slug":"cancerbert-a-bert-model-for-extracting-breast","title":"CancerBERT: a BERT model for Extracting Breast Cancer Phenotypes from Electronic Health Records","date":"2021-08-25","arxiv_id":"2108.11303","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-transformer-for-single-image-super","slug":"efficient-transformer-for-single-image-super","title":"Transformer for Single Image Super-Resolution","date":"2021-08-25","arxiv_id":"2108.11084","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":7,"n_instrument":3,"unverified":0,"pointer_only":4,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["luissen/esrt"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/models-in-a-spelling-bee-language-models","slug":"models-in-a-spelling-bee-language-models","title":"Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens","date":"2021-08-25","arxiv_id":"2108.11193","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["itay1itzhak/spellingbee"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/on-approximate-nearest-neighbour-selection","slug":"on-approximate-nearest-neighbour-selection","title":"On Approximate Nearest Neighbour Selection for Multi-Stage Dense Retrieval","date":"2021-08-25","arxiv_id":"2108.11480","n_code_links":1,"syntology":null},{"paper":null,"slug":"ontology-enhanced-slot-filling","title":"Ontology-Enhanced Slot Filling","date":"2021-08-25","arxiv_id":"2108.11275","n_code_links":0,"syntology":null},{"paper":"/paper/what-do-pre-trained-code-models-know-about","slug":"what-do-pre-trained-code-models-know-about","title":"What do pre-trained code models know about code?","date":"2021-08-25","arxiv_id":"2108.11308","n_code_links":1,"syntology":null},{"paper":null,"slug":"auto-parsing-network-for-image-captioning-and","title":"Auto-Parsing Network for Image Captioning and Visual Question Answering","date":"2021-08-24","arxiv_id":"2108.10568","n_code_links":0,"syntology":null},{"paper":null,"slug":"greenformers-improving-computation-and-memory","title":"Greenformers: Improving Computation and Memory Efficiency in Transformer Models via Low-Rank Approximation","date":"2021-08-24","arxiv_id":"2108.10808","n_code_links":0,"syntology":null},{"paper":"/paper/sigmoidf1-a-smooth-f1-score-surrogate-loss","slug":"sigmoidf1-a-smooth-f1-score-surrogate-loss","title":"sigmoidF1: A Smooth F1 Score Surrogate Loss for Multilabel Classification","date":"2021-08-24","arxiv_id":"2108.10566","n_code_links":1,"syntology":null},{"paper":"/paper/sn-computer-science-towards-offensive","slug":"sn-computer-science-towards-offensive","title":"Towards Offensive Language Identification for Tamil Code-Mixed YouTube Comments and Posts","date":"2021-08-24","arxiv_id":"2108.10939","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-bert-encoding-and-sentence-level","title":"Using BERT Encoding and Sentence-Level Language Model for Sentence Ordering","date":"2021-08-24","arxiv_id":"2108.10986","n_code_links":0,"syntology":null},{"paper":null,"slug":"weakly-supervised-cross-platform-teenager","title":"Weakly Supervised Cross-platform Teenager Detection with Adversarial BERT","date":"2021-08-24","arxiv_id":"2108.10619","n_code_links":0,"syntology":null},{"paper":null,"slug":"cgems-a-metric-model-for-automatic-code","title":"CGEMs: A Metric Model for Automatic Code Generation using GPT-3","date":"2021-08-23","arxiv_id":"2108.10168","n_code_links":0,"syntology":null},{"paper":null,"slug":"deploying-a-bert-based-query-title-relevance","title":"Deploying a BERT-based Query-Title Relevance Classifier in a Production System: a View from the Trenches","date":"2021-08-23","arxiv_id":"2108.10197","n_code_links":0,"syntology":null},{"paper":"/paper/improving-3d-object-detection-with-channel","slug":"improving-3d-object-detection-with-channel","title":"Improving 3D Object Detection with Channel-wise Transformer","date":"2021-08-23","arxiv_id":"2108.10723","n_code_links":1,"syntology":{"ran":6,"of":12,"n_ran_checked":5,"n_instrument":1,"unverified":6,"pointer_only":0,"phrase":"6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["hlsheng1/ct3d"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/one-tts-alignment-to-rule-them-all","slug":"one-tts-alignment-to-rule-them-all","title":"One TTS Alignment To Rule Them All","date":"2021-08-23","arxiv_id":"2108.10447","n_code_links":3,"syntology":null},{"paper":"/paper/query-embedding-pruning-for-dense-retrieval","slug":"query-embedding-pruning-for-dense-retrieval","title":"Query Embedding Pruning for Dense Retrieval","date":"2021-08-23","arxiv_id":"2108.10341","n_code_links":1,"syntology":null},{"paper":null,"slug":"recurrent-multiple-shared-layers-in-depth-for","title":"Recurrent multiple shared layers in Depth for Neural Machine Translation","date":"2021-08-23","arxiv_id":"2108.10417","n_code_links":0,"syntology":null},{"paper":"/paper/regularizing-transformers-with-deep","slug":"regularizing-transformers-with-deep","title":"Regularizing Transformers With Deep Probabilistic Layers","date":"2021-08-23","arxiv_id":"2108.10764","n_code_links":0,"syntology":null},{"paper":"/paper/sarcasm-detection-in-twitter-performance","slug":"sarcasm-detection-in-twitter-performance","title":"Sarcasm Detection in Twitter -- Performance Impact while using Data Augmentation: Word Embeddings","date":"2021-08-23","arxiv_id":"2108.09924","n_code_links":1,"syntology":null},{"paper":"/paper/swinir-image-restoration-using-swin","slug":"swinir-image-restoration-using-swin","title":"SwinIR: Image Restoration Using Swin Transformer","date":"2021-08-23","arxiv_id":"2108.10257","n_code_links":9,"syntology":{"ran":30,"of":45,"n_ran_checked":16,"n_instrument":14,"unverified":15,"pointer_only":5,"phrase":"30 ran (of which 14 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 14 where Syntology's instrument failed) · 15 unverified","official":{"repos":["jingyunliang/swinir"],"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":["listed","official"]}}},{"paper":null,"slug":"zs-slr-zero-shot-sign-language-recognition","title":"ZS-SLR: Zero-Shot Sign Language Recognition from RGB-D Videos","date":"2021-08-23","arxiv_id":"2108.10059","n_code_links":0,"syntology":null},{"paper":null,"slug":"guiding-query-position-and-performing-similar","title":"Guiding Query Position and Performing Similar Attention for Transformer-Based Detection Heads","date":"2021-08-22","arxiv_id":"2108.09691","n_code_links":0,"syntology":null},{"paper":null,"slug":"spatial-transformer-networks-for-curriculum","title":"Spatial Transformer Networks for Curriculum Learning","date":"2021-08-22","arxiv_id":"2108.09696","n_code_links":0,"syntology":null},{"paper":null,"slug":"starvqa-space-time-attention-for-video","title":"StarVQA: Space-Time Attention for Video Quality Assessment","date":"2021-08-22","arxiv_id":"2108.09635","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-large-pre-trained-models-with-cross","title":"Using Large Pre-Trained Models with Cross-Modal Attention for Multi-Modal Emotion Recognition","date":"2021-08-22","arxiv_id":"2108.09669","n_code_links":0,"syntology":null},{"paper":null,"slug":"uzbert-pretraining-a-bert-model-for-uzbek","title":"UzBERT: pretraining a BERT model for Uzbek","date":"2021-08-22","arxiv_id":"2108.09814","n_code_links":0,"syntology":null},{"paper":null,"slug":"construction-material-classification-on","title":"Construction material classification on imbalanced datasets using Vision Transformer (ViT) architecture","date":"2021-08-21","arxiv_id":"2108.09527","n_code_links":0,"syntology":null},{"paper":"/paper/approximate-bayesian-neural-doppler-imaging","slug":"approximate-bayesian-neural-doppler-imaging","title":"Approximate Bayesian Neural Doppler Imaging","date":"2021-08-20","arxiv_id":"2108.09266","n_code_links":1,"syntology":null},{"paper":null,"slug":"convolutional-neural-network-cnn-vs-visual","title":"Convolutional Neural Network (CNN) vs Vision Transformer (ViT) for Digital Holography","date":"2021-08-20","arxiv_id":"2108.09147","n_code_links":0,"syntology":null},{"paper":null,"slug":"extracting-radiological-findings-with","title":"Extracting Radiological Findings With Normalized Anatomical Information Using a Span-Based BERT Relation Extraction Model","date":"2021-08-20","arxiv_id":"2108.09211","n_code_links":0,"syntology":null},{"paper":"/paper/fastformer-additive-attention-is-all-you-need","slug":"fastformer-additive-attention-is-all-you-need","title":"Fastformer: Additive Attention Can Be All You Need","date":"2021-08-20","arxiv_id":"2108.09084","n_code_links":13,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wuch15/Fastformer"],"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/frozen-pretrained-transformers-for-neural","slug":"frozen-pretrained-transformers-for-neural","title":"Frozen Pretrained Transformers for Neural Sign Language Translation","date":"2021-08-20","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"mm-vit-multi-modal-video-transformer-for","title":"MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition","date":"2021-08-20","arxiv_id":"2108.09322","n_code_links":0,"syntology":null},{"paper":"/paper/one-chatbot-per-person-creating-personalized","slug":"one-chatbot-per-person-creating-personalized","title":"One Chatbot Per Person: Creating Personalized Chatbots based on Implicit User Profiles","date":"2021-08-20","arxiv_id":"2108.09355","n_code_links":1,"syntology":null},{"paper":"/paper/pre-training-for-ad-hoc-retrieval-hyperlink","slug":"pre-training-for-ad-hoc-retrieval-hyperlink","title":"Pre-training for Ad-hoc Retrieval: Hyperlink is Also You Need","date":"2021-08-20","arxiv_id":"2108.09346","n_code_links":1,"syntology":null},{"paper":null,"slug":"semantic-communication-with-adaptive","title":"Semantic Communication with Adaptive Universal Transformer","date":"2021-08-20","arxiv_id":"2108.09119","n_code_links":0,"syntology":null},{"paper":null,"slug":"smart-bird-learnable-sparse-attention-for","title":"Smart Bird: Learnable Sparse Attention for Efficient and Effective Transformer","date":"2021-08-20","arxiv_id":"2108.09193","n_code_links":0,"syntology":null},{"paper":"/paper/trans4trans-efficient-transformer-for-1","slug":"trans4trans-efficient-transformer-for-1","title":"Trans4Trans: Efficient Transformer for Transparent Object and Semantic Scene Segmentation in Real-World Navigation Assistance","date":"2021-08-20","arxiv_id":"2108.09174","n_code_links":1,"syntology":null},{"paper":null,"slug":"uncertainties-and-output-feedback-in-rollout","title":"Uncertainties and output feedback in rollout event-triggered control","date":"2021-08-20","arxiv_id":"2108.09125","n_code_links":0,"syntology":null},{"paper":"/paper/a-framework-for-neural-topic-modeling-of-text","slug":"a-framework-for-neural-topic-modeling-of-text","title":"A Framework for Neural Topic Modeling of Text Corpora","date":"2021-08-19","arxiv_id":"2108.08946","n_code_links":1,"syntology":null},{"paper":"/paper/causal-attention-for-unbiased-visual","slug":"causal-attention-for-unbiased-visual","title":"Causal Attention for Unbiased Visual Recognition","date":"2021-08-19","arxiv_id":"2108.08782","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"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":["wangt-cn/caam"],"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":"/paper/contrastive-language-image-pre-training-for","slug":"contrastive-language-image-pre-training-for","title":"Contrastive Language-Image Pre-training for the Italian Language","date":"2021-08-19","arxiv_id":"2108.08688","n_code_links":1,"syntology":null},{"paper":null,"slug":"detection-of-illicit-drug-trafficking-events","title":"Detection of Illicit Drug Trafficking Events on Instagram: A Deep Multimodal Multilabel Learning Approach","date":"2021-08-19","arxiv_id":"2108.08920","n_code_links":0,"syntology":null},{"paper":"/paper/do-vision-transformers-see-like-convolutional","slug":"do-vision-transformers-see-like-convolutional","title":"Do Vision Transformers See Like Convolutional Neural Networks?","date":"2021-08-19","arxiv_id":"2108.08810","n_code_links":4,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":null}},{"paper":"/paper/fast-passage-re-ranking-with-contextualized","slug":"fast-passage-re-ranking-with-contextualized","title":"Fast Passage Re-ranking with Contextualized Exact Term Matching and Efficient Passage Expansion","date":"2021-08-19","arxiv_id":"2108.08513","n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-grained-element-identification-in","title":"Fine-Grained Element Identification in Complaint Text of Internet Fraud","date":"2021-08-19","arxiv_id":"2108.08676","n_code_links":0,"syntology":null},{"paper":"/paper/how-hateful-are-movies-a-study-and-prediction","slug":"how-hateful-are-movies-a-study-and-prediction","title":"How Hateful are Movies? A Study and Prediction on Movie Subtitles","date":"2021-08-19","arxiv_id":"2108.10724","n_code_links":1,"syntology":null},{"paper":null,"slug":"mvsr-nat-multi-view-subset-regularization-for","title":"MvSR-NAT: Multi-view Subset Regularization for Non-Autoregressive Machine Translation","date":"2021-08-19","arxiv_id":"2108.08447","n_code_links":0,"syntology":null},{"paper":"/paper/sentence-t5-scalable-sentence-encoders-from","slug":"sentence-t5-scalable-sentence-encoders-from","title":"Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models","date":"2021-08-19","arxiv_id":"2108.08877","n_code_links":2,"syntology":null},{"paper":"/paper/uniqorn-unified-question-answering-over-rdf","slug":"uniqorn-unified-question-answering-over-rdf","title":"UNIQORN: Unified Question Answering over RDF Knowledge Graphs and Natural Language Text","date":"2021-08-19","arxiv_id":"2108.08614","n_code_links":1,"syntology":null},{"paper":"/paper/video-relation-detection-via-tracklet-based","slug":"video-relation-detection-via-tracklet-based","title":"Video Relation Detection via Tracklet based Visual Transformer","date":"2021-08-19","arxiv_id":"2108.08669","n_code_links":1,"syntology":null},{"paper":null,"slug":"contributions-of-transformer-attention-heads","title":"Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks","date":"2021-08-18","arxiv_id":"2108.08375","n_code_links":0,"syntology":null},{"paper":null,"slug":"integrating-dialog-history-into-end-to-end","title":"Integrating Dialog History into End-to-End Spoken Language Understanding Systems","date":"2021-08-18","arxiv_id":"2108.08405","n_code_links":0,"syntology":null},{"paper":null,"slug":"shaq-single-headed-attention-with-quasi","title":"SHAQ: Single Headed Attention with Quasi-Recurrence","date":"2021-08-18","arxiv_id":"2108.08207","n_code_links":0,"syntology":null},{"paper":null,"slug":"sifn-a-sentiment-aware-interactive-fusion","title":"SIFN: A Sentiment-aware Interactive Fusion Network for Review-based Item Recommendation","date":"2021-08-18","arxiv_id":"2108.08022","n_code_links":0,"syntology":null},{"paper":"/paper/table-caption-generation-in-scholarly","slug":"table-caption-generation-in-scholarly","title":"Table Caption Generation in Scholarly Documents Leveraging Pre-trained Language Models","date":"2021-08-18","arxiv_id":"2108.08111","n_code_links":1,"syntology":null},{"paper":"/paper/transformers-predicting-the-future-applying","slug":"transformers-predicting-the-future-applying","title":"Transformers predicting the future. Applying attention in next-frame and time series forecasting","date":"2021-08-18","arxiv_id":"2108.08224","n_code_links":1,"syntology":null},{"paper":null,"slug":"tsi-an-ad-text-strength-indicator-using-text","title":"TSI: an Ad Text Strength Indicator using Text-to-CTR and Semantic-Ad-Similarity","date":"2021-08-18","arxiv_id":"2108.08226","n_code_links":0,"syntology":null},{"paper":null,"slug":"two-streams-and-two-resolution-spectrograms","title":"A Multi-level Acoustic Feature Extraction Framework for Transformer Based End-to-End Speech Recognition","date":"2021-08-18","arxiv_id":"2108.07980","n_code_links":0,"syntology":null},{"paper":"/paper/boosting-salient-object-detection-with","slug":"boosting-salient-object-detection-with","title":"Boosting Salient Object Detection with Transformer-based Asymmetric Bilateral U-Net","date":"2021-08-17","arxiv_id":"2108.07851","n_code_links":1,"syntology":null},{"paper":null,"slug":"enct5-fine-tuning-t5-encoder-for","title":"EncT5: Fine-tuning T5 Encoder for Discriminative Tasks","date":"2021-08-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/learning-c-to-x86-translation-an-experiment","slug":"learning-c-to-x86-translation-an-experiment","title":"Learning C to x86 Translation: An Experiment in Neural Compilation","date":"2021-08-17","arxiv_id":"2108.07639","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jordiae/neural-compilers"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/light-field-image-super-resolution-with","slug":"light-field-image-super-resolution-with","title":"Light Field Image Super-Resolution with Transformers","date":"2021-08-17","arxiv_id":"2108.07597","n_code_links":1,"syntology":null},{"paper":null,"slug":"modulating-language-models-with-emotions","title":"Modulating Language Models with Emotions","date":"2021-08-17","arxiv_id":"2108.07886","n_code_links":0,"syntology":null},{"paper":null,"slug":"moi-mixer-improving-mlp-mixer-with-multi","title":"MOI-Mixer: Improving MLP-Mixer with Multi Order Interactions in Sequential Recommendation","date":"2021-08-17","arxiv_id":"2108.07505","n_code_links":0,"syntology":null},{"paper":"/paper/response-ranking-with-multi-types-of-deep","slug":"response-ranking-with-multi-types-of-deep","title":"Response Ranking with Multi-types of Deep Interactive Representations in Retrieval-based Dialogues","date":"2021-08-17","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"semantics-aware-attention-improves-neural-1","title":"Semantics-aware Attention Improves Neural Machine Translation","date":"2021-08-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/semi-parametric-bayesian-additive-regression","slug":"semi-parametric-bayesian-additive-regression","title":"Accounting for shared covariates in semi-parametric Bayesian additive regression trees","date":"2021-08-17","arxiv_id":"2108.07636","n_code_links":2,"syntology":null},{"paper":null,"slug":"an-effective-non-autoregressive-model-for","title":"An Effective Non-Autoregressive Model for Spoken Language Understanding","date":"2021-08-16","arxiv_id":"2108.07005","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-natural-language-processing-for-linkedin-1","title":"Deep Natural Language Processing for LinkedIn Search","date":"2021-08-16","arxiv_id":"2108.13300","n_code_links":0,"syntology":null},{"paper":"/paper/misleading-the-covid-19-vaccination-discourse","slug":"misleading-the-covid-19-vaccination-discourse","title":"Misleading the Covid-19 vaccination discourse on Twitter: An exploratory study of infodemic around the pandemic","date":"2021-08-16","arxiv_id":"2108.10735","n_code_links":1,"syntology":null},{"paper":"/paper/no-reference-image-quality-assessment-via-1","slug":"no-reference-image-quality-assessment-via-1","title":"No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency","date":"2021-08-16","arxiv_id":"2108.06858","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-opportunities-and-risks-of-foundation","slug":"on-the-opportunities-and-risks-of-foundation","title":"On the Opportunities and Risks of Foundation Models","date":"2021-08-16","arxiv_id":"2108.07258","n_code_links":2,"syntology":null},{"paper":"/paper/scene-designer-a-unified-model-for-scene","slug":"scene-designer-a-unified-model-for-scene","title":"Scene Designer: a Unified Model for Scene Search and Synthesis from Sketch","date":"2021-08-16","arxiv_id":"2108.07353","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-generalization-ability-of","title":"Exploring Generalization Ability of Pretrained Language Models on Arithmetic and Logical Reasoning","date":"2021-08-15","arxiv_id":"2108.06743","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-temporal-coherence-for-more-general","slug":"exploring-temporal-coherence-for-more-general","title":"Exploring Temporal Coherence for More General Video Face Forgery Detection","date":"2021-08-15","arxiv_id":"2108.06693","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":6,"phrase":"6 ran (of which 4 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":null}},{"paper":null,"slug":"maps-search-misspelling-detection-leveraging","title":"Maps Search Misspelling Detection Leveraging Domain-Augmented Contextual Representations","date":"2021-08-15","arxiv_id":"2108.06842","n_code_links":0,"syntology":null},{"paper":null,"slug":"sapphire-approaches-for-enhanced-concept-to","title":"SAPPHIRE: Approaches for Enhanced Concept-to-Text Generation","date":"2021-08-15","arxiv_id":"2108.06643","n_code_links":0,"syntology":null},{"paper":"/paper/sotr-segmenting-objects-with-transformers","slug":"sotr-segmenting-objects-with-transformers","title":"SOTR: Segmenting Objects with Transformers","date":"2021-08-15","arxiv_id":"2108.06747","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":6,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"8 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["easton-cau/SOTR"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/heterogeneous-temporal-graph-transformer-an","slug":"heterogeneous-temporal-graph-transformer-an","title":"heterogeneous temporal graph transformer: an intelligent system for evolving android malware detection","date":"2021-08-14","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/conditional-detr-for-fast-training","slug":"conditional-detr-for-fast-training","title":"Conditional DETR for Fast Training Convergence","date":"2021-08-13","arxiv_id":"2108.06152","n_code_links":4,"syntology":{"ran":6,"of":9,"n_ran_checked":4,"n_instrument":2,"unverified":3,"pointer_only":4,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["atten4vis/conditionaldetr"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/curriculum-learning-a-regularization-method","slug":"curriculum-learning-a-regularization-method","title":"The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models","date":"2021-08-13","arxiv_id":"2108.06084","n_code_links":1,"syntology":null},{"paper":"/paper/point-voxel-transformer-an-efficient-approach","slug":"point-voxel-transformer-an-efficient-approach","title":"PVT: Point-Voxel Transformer for Point Cloud Learning","date":"2021-08-13","arxiv_id":"2108.06076","n_code_links":2,"syntology":null},{"paper":null,"slug":"towards-structured-dynamic-sparse-pre","title":"Towards Structured Dynamic Sparse Pre-Training of BERT","date":"2021-08-13","arxiv_id":"2108.06277","n_code_links":0,"syntology":null},{"paper":"/paper/ammus-a-survey-of-transformer-based","slug":"ammus-a-survey-of-transformer-based","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","date":"2021-08-12","arxiv_id":"2108.05542","n_code_links":1,"syntology":null},{"paper":"/paper/how-optimal-is-greedy-decoding-for-extractive","slug":"how-optimal-is-greedy-decoding-for-extractive","title":"How Optimal is Greedy Decoding for Extractive Question Answering?","date":"2021-08-12","arxiv_id":"2108.05857","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["ocastel/exact-extract"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/mobile-former-bridging-mobilenet-and","slug":"mobile-former-bridging-mobilenet-and","title":"Mobile-Former: Bridging MobileNet and Transformer","date":"2021-08-12","arxiv_id":"2108.05895","n_code_links":4,"syntology":null},{"paper":null,"slug":"modeling-relevance-ranking-under-the-pre","title":"Modeling Relevance Ranking under the Pre-training and Fine-tuning Paradigm","date":"2021-08-12","arxiv_id":"2108.05652","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-analysis-of-the-predictability-of","title":"Multimodal analysis of the predictability of hand-gesture properties","date":"2021-08-12","arxiv_id":"2108.05762","n_code_links":0,"syntology":null},{"paper":"/paper/musiq-multi-scale-image-quality-transformer","slug":"musiq-multi-scale-image-quality-transformer","title":"MUSIQ: Multi-scale Image Quality Transformer","date":"2021-08-12","arxiv_id":"2108.05997","n_code_links":2,"syntology":{"ran":5,"of":6,"n_ran_checked":4,"n_instrument":1,"unverified":1,"pointer_only":6,"phrase":"5 ran (of which 1 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) · 1 unverified","official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"overview-of-the-hasoc-track-at-fire-2020-hate","title":"Overview of the HASOC track at FIRE 2020: Hate Speech and Offensive Content Identification in Indo-European Languages","date":"2021-08-12","arxiv_id":"2108.05927","n_code_links":0,"syntology":null},{"paper":"/paper/patrickstar-parallel-training-of-pre-trained","slug":"patrickstar-parallel-training-of-pre-trained","title":"PatrickStar: Parallel Training of Pre-trained Models via Chunk-based Memory Management","date":"2021-08-12","arxiv_id":"2108.05818","n_code_links":1,"syntology":null},{"paper":"/paper/tvt-transferable-vision-transformer-for","slug":"tvt-transferable-vision-transformer-for","title":"TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation","date":"2021-08-12","arxiv_id":"2108.05988","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 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["uta-smile/TVT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"f871cde0bfc72de8065b5cb681c35ba15022a42b1087b7f0b39affb3e4c9bc45","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}