{"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/label-smoothing/papers/115","list_of":"/method/label-smoothing","method":"Label Smoothing","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":115,"pages_in_order":144,"rows_per_page":100,"rows":[11401,11500],"of":14327,"counts":{"archive_papers_tagged":14327,"with_a_code_link":6651,"where_syntology_ran_a_sample":2259,"not_listed_spam_title":0,"listed":14327,"listed_where_code_ran":2259,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1920,"every_run_a_failure_of_syntologys_instrument":339,"listed_with_a_run_with_no_instrument_failure":1920,"listed_every_run_a_failure_of_syntologys_instrument":339,"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/label-smoothing","prev":"/method/label-smoothing/papers/114","next":"/method/label-smoothing/papers/116","papers":[{"paper":"/paper/dbia-data-free-backdoor-injection-attack","slug":"dbia-data-free-backdoor-injection-attack","title":"DBIA: Data-free Backdoor Injection Attack against Transformer Networks","date":"2021-11-22","arxiv_id":"2111.11870","n_code_links":1,"syntology":null},{"paper":"/paper/metaformer-is-actually-what-you-need-for","slug":"metaformer-is-actually-what-you-need-for","title":"MetaFormer Is Actually What You Need for Vision","date":"2021-11-22","arxiv_id":"2111.11418","n_code_links":18,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rwightman/pytorch-image-models","sail-sg/poolformer"],"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":"patch-vestiges-in-the-adversarial-examples","title":"Patch Vestiges in the Adversarial Examples Against Vision Transformer Can Be Leveraged for Adversarial Detection","date":"2021-11-22","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"replica-enhanced-feature-pyramid-network-by","title":"Lightweight Transformer Backbone for Medical Object Detection","date":"2021-11-22","arxiv_id":"2111.11546","n_code_links":0,"syntology":null},{"paper":"/paper/semi-supervised-vision-transformers","slug":"semi-supervised-vision-transformers","title":"Semi-Supervised Vision Transformers","date":"2021-11-22","arxiv_id":"2111.11067","n_code_links":1,"syntology":null},{"paper":null,"slug":"cpt-convolutional-point-transformer-for-3d","title":"CpT: Convolutional Point Transformer for 3D Point Cloud Processing","date":"2021-11-21","arxiv_id":"2111.10866","n_code_links":0,"syntology":null},{"paper":null,"slug":"dudotrans-dual-domain-transformer-provides","title":"DuDoTrans: Dual-Domain Transformer Provides More Attention for Sinogram Restoration in Sparse-View CT Reconstruction","date":"2021-11-21","arxiv_id":"2111.10790","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-softmax-approximation-for-deep","title":"Efficient Softmax Approximation for Deep Neural Networks with Attention Mechanism","date":"2021-11-21","arxiv_id":"2111.10770","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-vision-transformers-robust-to-patch","title":"Are Vision Transformers Robust to Patch Perturbations?","date":"2021-11-20","arxiv_id":"2111.10659","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-processing-matters-srph-konvergen-ai-s","title":"Data Processing Matters: SRPH-Konvergen AI's Machine Translation System for WMT'21","date":"2021-11-20","arxiv_id":"2111.10513","n_code_links":0,"syntology":null},{"paper":"/paper/discrete-representations-strengthen-vision-1","slug":"discrete-representations-strengthen-vision-1","title":"Discrete Representations Strengthen Vision Transformer Robustness","date":"2021-11-20","arxiv_id":"2111.10493","n_code_links":1,"syntology":null},{"paper":"/paper/advancing-high-resolution-video-language","slug":"advancing-high-resolution-video-language","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","date":"2021-11-19","arxiv_id":"2111.10337","n_code_links":1,"syntology":null},{"paper":null,"slug":"dynamic-graph-representation-learning-via-2","title":"DyFormer: A Scalable Dynamic Graph Transformer with Provable Benefits on Generalization Ability","date":"2021-11-19","arxiv_id":"2111.10447","n_code_links":0,"syntology":null},{"paper":"/paper/generalized-decision-transformer-for-offline","slug":"generalized-decision-transformer-for-offline","title":"Generalized Decision Transformer for Offline Hindsight Information Matching","date":"2021-11-19","arxiv_id":"2111.10364","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":["frt03/generalized_dt"],"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/grounded-situation-recognition-with","slug":"grounded-situation-recognition-with","title":"Grounded Situation Recognition with Transformers","date":"2021-11-19","arxiv_id":"2111.10135","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":3,"n_instrument":2,"unverified":4,"pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["jhcho99/gsrtr"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"lexicon-based-methods-vs-bert-for-text","title":"Lexicon-based Methods vs. BERT for Text Sentiment Analysis","date":"2021-11-19","arxiv_id":"2111.10097","n_code_links":0,"syntology":null},{"paper":null,"slug":"tnt-attacks-universal-naturalistic","title":"TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems","date":"2021-11-19","arxiv_id":"2111.09999","n_code_links":0,"syntology":null},{"paper":"/paper/transmorph-transformer-for-unsupervised","slug":"transmorph-transformer-for-unsupervised","title":"TransMorph: Transformer for unsupervised medical image registration","date":"2021-11-19","arxiv_id":"2111.10480","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["junyuchen245/TransMorph_Transformer_for_Medical_Image_Registration"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"zero-shot-certified-defense-against","title":"PatchCensor: Patch Robustness Certification for Transformers via Exhaustive Testing","date":"2021-11-19","arxiv_id":"2111.10481","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-much-do-language-models-copy-from-their","title":"How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN","date":"2021-11-18","arxiv_id":"2111.09509","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-emotion-recognition-on-ravdess","slug":"multimodal-emotion-recognition-on-ravdess","title":"Multimodal Emotion Recognition on RAVDESS Dataset Using Transfer Learning","date":"2021-11-18","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"reference-based-magnetic-resonance-image","title":"Reference-based Magnetic Resonance Image Reconstruction Using Texture Transformer","date":"2021-11-18","arxiv_id":"2111.09492","n_code_links":0,"syntology":null},{"paper":"/paper/restormer-efficient-transformer-for-high","slug":"restormer-efficient-transformer-for-high","title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","date":"2021-11-18","arxiv_id":"2111.09881","n_code_links":13,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["swz30/restormer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/robertuito-a-pre-trained-language-model-for","slug":"robertuito-a-pre-trained-language-model-for","title":"RoBERTuito: a pre-trained language model for social media text in Spanish","date":"2021-11-18","arxiv_id":"2111.09453","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["pysentimiento/robertuito"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/swin-transformer-v2-scaling-up-capacity-and","slug":"swin-transformer-v2-scaling-up-capacity-and","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","date":"2021-11-18","arxiv_id":"2111.09883","n_code_links":23,"syntology":{"ran":17,"of":30,"n_ran_checked":17,"n_instrument":0,"unverified":13,"pointer_only":4,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 3 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 13 unverified","official":{"repos":["microsoft/Swin-Transformer"],"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/you-only-sample-almost-once-linear-cost-self-1","slug":"you-only-sample-almost-once-linear-cost-self-1","title":"You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling","date":"2021-11-18","arxiv_id":"2111.09714","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":["mlpen/yoso"],"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":null,"slug":"fine-grained-vehicle-classification-in-urban","title":"Fine-Grained Vehicle Classification in Urban Traffic Scenes using Deep Learning","date":"2021-11-17","arxiv_id":"2111.09403","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-deep-generative-xai-framework-for-natural","title":"A Deep Generative XAI Framework for Natural Language Inference Explanations Generation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"all-birds-with-one-stone-multi-task-learning","title":"All Birds with One Stone: Multi-task Learning for Inference with One Forward Pass","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empirical-study-of-document-to-document","title":"An Empirical Study of Document-to-document Neural Machine Translation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/attention-based-multi-hypothesis-fusion-for","slug":"attention-based-multi-hypothesis-fusion-for","title":"Attention-based Multi-hypothesis Fusion for Speech Summarization","date":"2021-11-16","arxiv_id":"2111.08201","n_code_links":2,"syntology":null},{"paper":null,"slug":"boundary-smoothing-for-named-entity","title":"Boundary Smoothing for Named Entity Recognition","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"calbert-code-mixed-adaptive-language","title":"CalBERT - Code-mixed Adaptive Language representations using BERT","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"causal-transformers-improving-the-robustness","title":"Causal Transformers: Improving the Robustness on Spurious Correlations","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"compressing-sentence-representation-via","title":"Compressing Sentence Representation via Homomorphic Projective Distillation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"constructing-phrase-level-semantic-labels-to-1","title":"Constructing Phrase-level Semantic Labels to Form Multi-GrainedSupervision for Image-Text Retrieval","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"data-augmentation-and-learned-layer","title":"Data Augmentation and Learned Layer Aggregation for Improved Multilingual Language Understanding in Dialogue","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-long-sequence-encoding-via","title":"Efficient Long Sequence Encoding via Synchronization","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"empirical-analysis-of-training-strategies-of-1","title":"Empirical Analysis of Training Strategies of Transformer-based Japanese Chit-chat Systems","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-sign-language-translation-via","title":"End-To-End Sign Language Translation via Multitask Learning","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-the-nonlinear-mutual-dependencies","title":"Enhancing the Nonlinear Mutual Dependencies in Transformers with Mutual Information","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ernie-sparse-learning-hierarchical-efficient","title":"ERNIE-SPARSE: Learning Hierarchical Efficient Transformer Through Regularized Self-Attention","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"extreme-multi-label-text-classification-with-1","title":"Extreme Multi-label Text Classification with Multi-layer Experts","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-and-accurate-transformer-based","title":"Fast and Accurate Transformer-based Translation with Character-Level Encoding and Subword-Level Decoding","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fix-bugs-with-transformer-through-a-neural","title":"Fix Bugs with Transformer through a Neural-Symbolic Edit Grammar","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"focus-on-the-targets-vocabulary-masked-label","title":"Focus on the Target’s Vocabulary: Masked Label Smoothing for Machine Translation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-diverse-and-high-quality","title":"Generating Diverse and High-Quality Abstractive Summaries with Variational Transformers","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"input-specific-attention-subnetworks-for","title":"Input-specific Attention Subnetworks for Adversarial Detection","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-guided-transformer-for-joint-theme","title":"Knowledge-guided Transformer for Joint Theme and Emotion Classification of Chinese Classical Poetry","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-methods-for-solving-astronomy-course","title":"Learning Methods for Solving Astronomy Course Problems","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-non-autoregressive-models-from","title":"Learning Non-Autoregressive Models from Search for Unsupervised Sentence Summarization","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"listen-to-both-sides-and-be-enlightened","title":"Listen to Both Sides and be Enlightened! -- Hierarchical Modality Fusion Network for Entity and Relation Extraction","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"making-transformers-solve-compositional-tasks-1","title":"Making Transformers Solve Compositional Tasks","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"marcqap-effective-context-modeling-for","title":"MarCQAp: Effective Context Modeling for Conversational Question Answering","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/modeling-hierarchical-syntax-structure-with","slug":"modeling-hierarchical-syntax-structure-with","title":"Modeling Hierarchical Syntax Structure with Triplet Position for Source Code Summarization","date":"2021-11-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-head-or-single-head-an-empirical-1","title":"Multi-head or Single-head? An Empirical Comparison for Transformer Training","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"n-grammer-augmenting-transformers-with-latent","title":"N-grammer: Augmenting Transformers with latent n-grams","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"on-vision-features-in-multimodal-machine","title":"On Vision Features in Multimodal Machine Translation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"online-advertising-revenue-forecasting-an","title":"Online Advertising Revenue Forecasting: An Interpretable Deep Learning Approach","date":"2021-11-16","arxiv_id":"2111.08840","n_code_links":0,"syntology":null},{"paper":null,"slug":"pesto-a-post-user-fusion-network-for-rumour","title":"PESTO: A Post-User Fusion Network for Rumour Detection on Social Media","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"polise-reinforcing-politeness-using-user","title":"PoliSe: Reinforcing Politeness using User Sentiment for Customer Care Response Generation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-based-layer-wise-adaptive","title":"Retrieval-based Layer-wise Adaptive Transformer for Source Code Summarization","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sequence-to-sequence-amr-parsing-with","title":"Sequence-to-sequence AMR Parsing with Ancestor Information","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sequence-to-sequence-knowledge-graph","title":"Sequence-to-Sequence Knowledge Graph Completion and Question Answering","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"shct-a-successively-hierarchical-conditional","title":"SHCT: A Successively Hierarchical Conditional Transformer for Controllable Paraphrase Generation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"shrinknas-single-path-one-shot-operator","title":"ShrinkNAS : Single-Path One-Shot Operator Exploratory Training for Transformer with Dynamic Space Shrinking","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"solving-probability-and-statistics-problems","title":"Solving Probability and Statistics Problems by Program Synthesis","date":"2021-11-16","arxiv_id":"2111.08267","n_code_links":0,"syntology":null},{"paper":null,"slug":"solving-probability-and-statistics-problems-1","title":"Solving Probability and Statistics Problems by Program Synthesis","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/sparsifying-transformer-models-with-trainable","slug":"sparsifying-transformer-models-with-trainable","title":"Sparsifying Transformer Models with Trainable Representation Pooling","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"speaker-profiling-in-multi-party","title":"Speaker Profiling in Multi-party Conversations","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"structured-pruning-learns-compact-and","title":"Structured Pruning Learns Compact and Accurate Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"supershaper-task-agnostic-super-pre-training-1","title":"SuperShaper: Task-Agnostic Super Pre-training of BERT Models with Variable Hidden Dimensions","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"taco-pre-training-of-deep-transformers-with","title":"TACO: Pre-training of Deep Transformers with Attention Convolution using Disentangled Positional Representation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"teaching-bert-to-wait-balancing-accuracy-and","title":"Teaching BERT to Wait: Balancing Accuracy and Latency for Streaming Disfluency Detection","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"wets-a-benchmark-for-translation-suggestion-1","title":"WeTS: A Benchmark for Translation Suggestion","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"what-works-and-doesn-t-work-a-deep-decoder","title":"What Works and Doesn't Work, A Deep Decoder for Neural Machine Translation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-in-games-techniques-challenges-and","title":"AI in Human-computer Gaming: Techniques, Challenges and Opportunities","date":"2021-11-15","arxiv_id":"2111.07631","n_code_links":0,"syntology":null},{"paper":null,"slug":"faketransformer-exposing-face-forgery-from","title":"FakeTransformer: Exposing Face Forgery From Spatial-Temporal Representation Modeled By Facial Pixel Variations","date":"2021-11-15","arxiv_id":"2111.07601","n_code_links":0,"syntology":null},{"paper":"/paper/mask-guided-spectral-wise-transformer-for","slug":"mask-guided-spectral-wise-transformer-for","title":"Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction","date":"2021-11-15","arxiv_id":"2111.07910","n_code_links":4,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["caiyuanhao1998/MST"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/local-multi-head-channel-self-attention-for","slug":"local-multi-head-channel-self-attention-for","title":"Local Multi-Head Channel Self-Attention for Facial Expression Recognition","date":"2021-11-14","arxiv_id":"2111.07224","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-based-image-compression","title":"Transformer-based Image Compression","date":"2021-11-12","arxiv_id":"2111.06707","n_code_links":0,"syntology":null},{"paper":"/paper/a-survey-of-visual-transformers","slug":"a-survey-of-visual-transformers","title":"A Survey of Visual Transformers","date":"2021-11-11","arxiv_id":"2111.06091","n_code_links":1,"syntology":null},{"paper":null,"slug":"graph-relation-transformer-incorporating","title":"Graph Relation Transformer: Incorporating pairwise object features into the Transformer architecture","date":"2021-11-11","arxiv_id":"2111.06075","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-large-scale-language-models-and","title":"Improving Large-scale Language Models and Resources for Filipino","date":"2021-11-11","arxiv_id":"2111.06053","n_code_links":0,"syntology":null},{"paper":"/paper/attention-approximates-sparse-distributed","slug":"attention-approximates-sparse-distributed","title":"Attention Approximates Sparse Distributed Memory","date":"2021-11-10","arxiv_id":"2111.05498","n_code_links":1,"syntology":{"ran":12,"of":19,"n_ran_checked":11,"n_instrument":1,"unverified":7,"pointer_only":7,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","official":{"repos":["trentbrick/attention-approximates-sdm"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/multimodal-transformer-with-variable-length","slug":"multimodal-transformer-with-variable-length","title":"Multimodal Transformer with Variable-length Memory for Vision-and-Language Navigation","date":"2021-11-10","arxiv_id":"2111.05759","n_code_links":1,"syntology":null},{"paper":"/paper/prune-once-for-all-sparse-pre-trained","slug":"prune-once-for-all-sparse-pre-trained","title":"Prune Once for All: Sparse Pre-Trained Language Models","date":"2021-11-10","arxiv_id":"2111.05754","n_code_links":2,"syntology":null},{"paper":"/paper/soft-sensing-transformer-hundreds-of-sensors","slug":"soft-sensing-transformer-hundreds-of-sensors","title":"Soft Sensing Transformer: Hundreds of Sensors are Worth a Single Word","date":"2021-11-10","arxiv_id":"2111.05973","n_code_links":1,"syntology":null},{"paper":null,"slug":"constrained-instance-and-class-reweighting","title":"Constrained Instance and Class Reweighting for Robust Learning under Label Noise","date":"2021-11-09","arxiv_id":"2111.05428","n_code_links":0,"syntology":null},{"paper":null,"slug":"fpm-a-collection-of-large-scale-foundation","title":"FPM: A Collection of Large-scale Foundation Pre-trained Language Models","date":"2021-11-09","arxiv_id":"2111.04909","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-task-prediction-of-clinical-outcomes-in","title":"Multi-Task Prediction of Clinical Outcomes in the Intensive Care Unit using Flexible Multimodal Transformers","date":"2021-11-09","arxiv_id":"2111.05431","n_code_links":0,"syntology":null},{"paper":"/paper/sliced-recursive-transformer-1","slug":"sliced-recursive-transformer-1","title":"Sliced Recursive Transformer","date":"2021-11-09","arxiv_id":"2111.05297","n_code_links":1,"syntology":null},{"paper":"/paper/guiding-multi-step-rearrangement-tasks-with","slug":"guiding-multi-step-rearrangement-tasks-with","title":"Guiding Multi-Step Rearrangement Tasks with Natural Language Instructions","date":"2021-11-08","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/mixed-transformer-u-net-for-medical-image","slug":"mixed-transformer-u-net-for-medical-image","title":"Mixed Transformer U-Net For Medical Image Segmentation","date":"2021-11-08","arxiv_id":"2111.04734","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 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":{"repos":["dootmaan/mt-unet"],"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"]}}},{"paper":"/paper/are-we-ready-for-a-new-paradigm-shift-a","slug":"are-we-ready-for-a-new-paradigm-shift-a","title":"Are we ready for a new paradigm shift? A Survey on Visual Deep MLP","date":"2021-11-07","arxiv_id":"2111.04060","n_code_links":1,"syntology":null},{"paper":null,"slug":"analyzing-architectures-for-neural-machine","title":"Analyzing Architectures for Neural Machine Translation Using Low Computational Resources","date":"2021-11-06","arxiv_id":"2111.03813","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-data-driven-surrogate-simulators","slug":"benchmarking-data-driven-surrogate-simulators","title":"Benchmarking Data-driven Surrogate Simulators for Artificial Electromagnetic Materials","date":"2021-11-06","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"convolutional-gated-mlp-combining","title":"Convolutional Gated MLP: Combining Convolutions & gMLP","date":"2021-11-06","arxiv_id":"2111.03940","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-visual-quality-of-image-synthesis","title":"Improving Visual Quality of Image Synthesis by A Token-based Generator with Transformers","date":"2021-11-05","arxiv_id":"2111.03481","n_code_links":0,"syntology":null},{"paper":null,"slug":"oracle-teacher-towards-better-knowledge","title":"Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Models","date":"2021-11-05","arxiv_id":"2111.03664","n_code_links":0,"syntology":null}],"record_sha256":"9a97e7ea4b4a129fccc5528279933550aa65c2ee9e23f0f7290eb14a726bfb4f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}