{"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/linear-layer/papers/197","list_of":"/method/linear-layer","method":"Linear Layer","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":197,"pages_in_order":255,"rows_per_page":100,"rows":[19601,19700],"of":25421,"counts":{"archive_papers_tagged":25421,"with_a_code_link":11479,"where_syntology_ran_a_sample":3523,"not_listed_spam_title":0,"listed":25421,"listed_where_code_ran":3523,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2976,"every_run_a_failure_of_syntologys_instrument":547,"listed_with_a_run_with_no_instrument_failure":2976,"listed_every_run_a_failure_of_syntologys_instrument":547,"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/linear-layer","prev":"/method/linear-layer/papers/196","next":"/method/linear-layer/papers/198","papers":[{"paper":"/paper/semantic-prediction-which-one-should-come","slug":"semantic-prediction-which-one-should-come","title":"Semantic Prediction: Which One Should Come First, Recognition or Prediction?","date":"2021-10-06","arxiv_id":"2110.02829","n_code_links":1,"syntology":null},{"paper":null,"slug":"analyzing-the-impact-of-covid-19-on-economy","title":"Analyzing the Impact of COVID-19 on Economy from the Perspective of Users Reviews","date":"2021-10-05","arxiv_id":"2110.02198","n_code_links":0,"syntology":null},{"paper":null,"slug":"asr-rescoring-and-confidence-estimation-with","title":"ASR Rescoring and Confidence Estimation with ELECTRA","date":"2021-10-05","arxiv_id":"2110.01857","n_code_links":0,"syntology":null},{"paper":"/paper/disambiguation-bert-for-n-best-rescoring-in","slug":"disambiguation-bert-for-n-best-rescoring-in","title":"BERT Attends the Conversation: Improving Low-Resource Conversational ASR","date":"2021-10-05","arxiv_id":"2110.02267","n_code_links":1,"syntology":null},{"paper":"/paper/distilhubert-speech-representation-learning","slug":"distilhubert-speech-representation-learning","title":"DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT","date":"2021-10-05","arxiv_id":"2110.01900","n_code_links":1,"syntology":null},{"paper":"/paper/exploiting-twitter-as-source-of-large-corpora","slug":"exploiting-twitter-as-source-of-large-corpora","title":"Exploiting Twitter as Source of Large Corpora of Weakly Similar Pairs for Semantic Sentence Embeddings","date":"2021-10-05","arxiv_id":"2110.02030","n_code_links":1,"syntology":null},{"paper":"/paper/foodchem-a-food-chemical-relation-extraction","slug":"foodchem-a-food-chemical-relation-extraction","title":"FoodChem: A food-chemical relation extraction model","date":"2021-10-05","arxiv_id":"2110.02019","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-sense-specific-static-embeddings","title":"Learning Sense-Specific Static Embeddings using Contextualised Word Embeddings as a Proxy","date":"2021-10-05","arxiv_id":"2110.02204","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-the-inductive-bias-of-large","title":"Leveraging the Inductive Bias of Large Language Models for Abstract Textual Reasoning","date":"2021-10-05","arxiv_id":"2110.02370","n_code_links":0,"syntology":null},{"paper":"/paper/mobilevit-light-weight-general-purpose-and","slug":"mobilevit-light-weight-general-purpose-and","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","date":"2021-10-05","arxiv_id":"2110.02178","n_code_links":31,"syntology":{"ran":53,"of":68,"n_ran_checked":44,"n_instrument":9,"unverified":15,"pointer_only":18,"phrase":"53 ran (of which 31 constructed an object rather than computing a result; 44 with no instrument failure: 1 honoured, 0 violated, 43 with no contract checked; 9 where Syntology's instrument failed) · 15 unverified","official":{"repos":["apple/ml-cvnets"],"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/sicilian-translator-a-recipe-for-low-resource","slug":"sicilian-translator-a-recipe-for-low-resource","title":"Sicilian Translator: A Recipe for Low-Resource NMT","date":"2021-10-05","arxiv_id":"2110.01938","n_code_links":1,"syntology":null},{"paper":"/paper/sound-event-detection-transformer-an-event","slug":"sound-event-detection-transformer-an-event","title":"Sound Event Detection Transformer: An Event-based End-to-End Model for Sound Event Detection","date":"2021-10-05","arxiv_id":"2110.02011","n_code_links":1,"syntology":null},{"paper":"/paper/top-n-equivariant-set-and-graph-generation","slug":"top-n-equivariant-set-and-graph-generation","title":"Top-N: Equivariant set and graph generation without exchangeability","date":"2021-10-05","arxiv_id":"2110.02096","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":2,"n_instrument":2,"unverified":2,"pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["cvignac/top-n"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"ur-iw-hnt-at-germeval-2021-an-ensembling","title":"ur-iw-hnt at GermEval 2021: An Ensembling Strategy with Multiple BERT Models","date":"2021-10-05","arxiv_id":"2110.02042","n_code_links":0,"syntology":null},{"paper":"/paper/word-acquisition-in-neural-language-models","slug":"word-acquisition-in-neural-language-models","title":"Word Acquisition in Neural Language Models","date":"2021-10-05","arxiv_id":"2110.02406","n_code_links":1,"syntology":null},{"paper":"/paper/3d-transformer-molecular-representation-with","slug":"3d-transformer-molecular-representation-with","title":"Molformer: Motif-based Transformer on 3D Heterogeneous Molecular Graphs","date":"2021-10-04","arxiv_id":"2110.01191","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["smiles724/3d-transformer","smiles724/molformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-free-lunch-from-vit-adaptive-attention","slug":"a-free-lunch-from-vit-adaptive-attention","title":"A free lunch from ViT:Adaptive Attention Multi-scale Fusion Transformer for Fine-grained Visual Recognition","date":"2021-10-04","arxiv_id":"2110.01240","n_code_links":0,"syntology":null},{"paper":"/paper/deepa2-a-modular-framework-for-deep-argument","slug":"deepa2-a-modular-framework-for-deep-argument","title":"DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language Models","date":"2021-10-04","arxiv_id":"2110.01509","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploiting-pre-trained-asr-models-for","title":"Exploiting Pre-Trained ASR Models for Alzheimer's Disease Recognition Through Spontaneous Speech","date":"2021-10-04","arxiv_id":"2110.01493","n_code_links":0,"syntology":null},{"paper":"/paper/juribert-a-masked-language-model-adaptation","slug":"juribert-a-masked-language-model-adaptation","title":"JuriBERT: A Masked-Language Model Adaptation for French Legal Text","date":"2021-10-04","arxiv_id":"2110.01485","n_code_links":1,"syntology":null},{"paper":null,"slug":"perhaps-ptlms-should-go-to-school-a-task-to","title":"Perhaps PTLMs Should Go to School -- A Task to Assess Open Book and Closed Book QA","date":"2021-10-04","arxiv_id":"2110.01552","n_code_links":0,"syntology":null},{"paper":"/paper/vtamiq-transformers-for-attention-modulated","slug":"vtamiq-transformers-for-attention-modulated","title":"VTAMIQ: Transformers for Attention Modulated Image Quality Assessment","date":"2021-10-04","arxiv_id":"2110.01655","n_code_links":1,"syntology":null},{"paper":null,"slug":"adversarial-examples-generation-for-reducing","title":"Adversarial Examples Generation for Reducing Implicit Gender Bias in Pre-trained Models","date":"2021-10-03","arxiv_id":"2110.01094","n_code_links":0,"syntology":null},{"paper":null,"slug":"music-playlist-title-generation-a-machine","title":"Music Playlist Title Generation: A Machine-Translation Approach","date":"2021-10-03","arxiv_id":"2110.07354","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-paradigm-for-information","title":"Unsupervised paradigm for information extraction from transcripts using BERT","date":"2021-10-03","arxiv_id":"2110.00949","n_code_links":0,"syntology":null},{"paper":null,"slug":"artificial-intelligence-for-sustainable","title":"Artificial intelligence for Sustainable Energy: A Contextual Topic Modeling and Content Analysis","date":"2021-10-02","arxiv_id":"2110.00828","n_code_links":0,"syntology":null},{"paper":"/paper/implicit-and-explicit-attention-for-zero-shot","slug":"implicit-and-explicit-attention-for-zero-shot","title":"Implicit and Explicit Attention for Zero-Shot Learning","date":"2021-10-02","arxiv_id":"2110.00860","n_code_links":1,"syntology":null},{"paper":"/paper/proto-program-guided-transformer-for-program","slug":"proto-program-guided-transformer-for-program","title":"ProTo: Program-Guided Transformer for Program-Guided Tasks","date":"2021-10-02","arxiv_id":"2110.00804","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["sjtuytc/Neurips21-ProTo-Program-guided-Transformers-for-Program-guided-Tasks"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/swiss-judgment-prediction-a-multilingual","slug":"swiss-judgment-prediction-a-multilingual","title":"Swiss-Judgment-Prediction: A Multilingual Legal Judgment Prediction Benchmark","date":"2021-10-02","arxiv_id":"2110.00806","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert4gcn-using-bert-intermediate-layers-to","title":"BERT4GCN: Using BERT Intermediate Layers to Augment GCN for Aspect-based Sentiment Classification","date":"2021-10-01","arxiv_id":"2110.00171","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-efficient-instance-segmentation-with-a","title":"3rd Place Scheme on Instance Segmentation Track of ICCV 2021 VIPriors Challenges","date":"2021-10-01","arxiv_id":"2110.00242","n_code_links":0,"syntology":null},{"paper":"/paper/geometry-attention-transformer-with-position","slug":"geometry-attention-transformer-with-position","title":"Geometry Attention Transformer with Position-aware LSTMs for Image Captioning","date":"2021-10-01","arxiv_id":"2110.00335","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-punctuation-restoration-for-speech","title":"Improving Punctuation Restoration for Speech Transcripts via External Data","date":"2021-10-01","arxiv_id":"2110.00560","n_code_links":0,"syntology":null},{"paper":null,"slug":"low-frequency-names-exhibit-bias-and","title":"Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models","date":"2021-10-01","arxiv_id":"2110.00672","n_code_links":0,"syntology":null},{"paper":null,"slug":"span-labeling-approach-for-vietnamese-and","title":"Span Labeling Approach for Vietnamese and Chinese Word Segmentation","date":"2021-10-01","arxiv_id":"2110.00156","n_code_links":0,"syntology":null},{"paper":null,"slug":"unpacking-the-interdependent-systems-of","title":"Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lens","date":"2021-10-01","arxiv_id":"2110.00521","n_code_links":0,"syntology":null},{"paper":"/paper/bert-got-a-date-introducing-transformers-to","slug":"bert-got-a-date-introducing-transformers-to","title":"BERT got a Date: Introducing Transformers to Temporal Tagging","date":"2021-09-30","arxiv_id":"2109.14927","n_code_links":1,"syntology":null},{"paper":null,"slug":"bitcoin-transaction-strategy-construction","title":"Bitcoin Transaction Strategy Construction Based on Deep Reinforcement Learning","date":"2021-09-30","arxiv_id":"2109.14789","n_code_links":0,"syntology":null},{"paper":"/paper/covid-19-fake-news-detection-using","slug":"covid-19-fake-news-detection-using","title":"COVID-19 Fake News Detection Using Bidirectional Encoder Representations from Transformers Based Models","date":"2021-09-30","arxiv_id":"2109.14816","n_code_links":1,"syntology":null},{"paper":"/paper/gt-u-net-a-u-net-like-group-transformer","slug":"gt-u-net-a-u-net-like-group-transformer","title":"GT U-Net: A U-Net Like Group Transformer Network for Tooth Root Segmentation","date":"2021-09-30","arxiv_id":"2109.14813","n_code_links":1,"syntology":null},{"paper":"/paper/inducing-transformer-s-compositional","slug":"inducing-transformer-s-compositional","title":"Inducing Transformer's Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks","date":"2021-09-30","arxiv_id":"2109.15256","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-predict-trustworthiness-with","slug":"learning-to-predict-trustworthiness-with","title":"Learning to Predict Trustworthiness with Steep Slope Loss","date":"2021-09-30","arxiv_id":"2110.00054","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["luoyan407/predict_trustworthiness"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mobtcast-leveraging-auxiliary-trajectory","title":"MobTCast: Leveraging Auxiliary Trajectory Forecasting for Human Mobility Prediction","date":"2021-09-30","arxiv_id":"2110.01401","n_code_links":0,"syntology":null},{"paper":"/paper/portaspeech-portable-and-high-quality","slug":"portaspeech-portable-and-high-quality","title":"PortaSpeech: Portable and High-Quality Generative Text-to-Speech","date":"2021-09-30","arxiv_id":"2109.15166","n_code_links":4,"syntology":{"ran":12,"of":12,"n_ran_checked":9,"n_instrument":3,"unverified":0,"pointer_only":6,"phrase":"12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["natspeech/natspeech"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":"/paper/prose2poem-the-blessing-of-transformer-based","slug":"prose2poem-the-blessing-of-transformer-based","title":"Prose2Poem: The Blessing of Transformers in Translating Prose to Persian Poetry","date":"2021-09-30","arxiv_id":"2109.14934","n_code_links":1,"syntology":null},{"paper":"/paper/redesigning-the-transformer-architecture-with","slug":"redesigning-the-transformer-architecture-with","title":"Redesigning the Transformer Architecture with Insights from Multi-particle Dynamical Systems","date":"2021-09-30","arxiv_id":"2109.15142","n_code_links":1,"syntology":null},{"paper":"/paper/scientific-evidence-extraction","slug":"scientific-evidence-extraction","title":"PubTables-1M: Towards comprehensive table extraction from unstructured documents","date":"2021-09-30","arxiv_id":"2110.00061","n_code_links":2,"syntology":{"ran":11,"of":13,"n_ran_checked":9,"n_instrument":2,"unverified":2,"pointer_only":10,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["microsoft/table-transformer"],"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":["listed","official"]}}},{"paper":"/paper/syntactic-persistence-in-language-models","slug":"syntactic-persistence-in-language-models","title":"Structural Persistence in Language Models: Priming as a Window into Abstract Language Representations","date":"2021-09-30","arxiv_id":"2109.14989","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-collaborative-attention-adaptive-network","title":"A Collaborative Attention Adaptive Network for Financial Market Forecasting","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/a-dot-product-attention-free-transformer","slug":"a-dot-product-attention-free-transformer","title":"A Dot Product Attention Free Transformer","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-control-flow-in-transformers","title":"Adaptive Control Flow in Transformers Improves Systematic Generalization","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-wavelet-transformer-network-for-3d","title":"Adaptive Wavelet Transformer Network for 3D Shape Representation Learning","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"an-investigation-on-hardware-aware-vision","title":"An Investigation on Hardware-Aware Vision Transformer Scaling","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"an-object-centric-sensitivity-analysis-of","title":"An object-centric sensitivity analysis of deep learning based instance segmentation","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-the-implicit-position-encoding","title":"Analyzing the Implicit Position Encoding Ability of Transformer Decoder","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"are-bert-families-zero-shot-learners-a-study","title":"Are BERT Families Zero-Shot Learners? A Study on Their Potential and Limitations","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"are-vision-transformers-robust-to-patch-wise","title":"Are Vision Transformers Robust to Patch-wise Perturbations?","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"associated-learning-an-alternative-to-end-to","title":"Associated Learning: an Alternative to End-to-End Backpropagation that Works on CNN, RNN, and Transformer","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-based-interpretability-with-concept","title":"Attention-based Interpretability with Concept Transformers","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"audio-lottery-speech-recognition-made-ultra","title":"Audio Lottery: Speech Recognition Made Ultra-Lightweight, Noise-Robust, and Transferable","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/cctrans-simplifying-and-improving-crowd","slug":"cctrans-simplifying-and-improving-crowd","title":"CCTrans: Simplifying and Improving Crowd Counting with Transformer","date":"2021-09-29","arxiv_id":"2109.14483","n_code_links":2,"syntology":{"ran":5,"of":6,"n_ran_checked":3,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"5 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; 2 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"coarformer-transformer-for-large-graph-via","title":"Coarformer: Transformer for large graph via graph coarsening","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"collaborative-storytelling-with-human-actors","title":"Collaborative Storytelling with Human Actors and AI Narrators","date":"2021-09-29","arxiv_id":"2109.14728","n_code_links":0,"syntology":null},{"paper":null,"slug":"compressing-transformer-based-sequence-to","title":"Compressing Transformer-Based Sequence to Sequence Models With Pre-trained Autoencoders for Text Summarization","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"computing-the-average-inter-sample-time-of","title":"Computing the average inter-sample time of event-triggered control using quantitative automata","date":"2021-09-29","arxiv_id":"2109.14391","n_code_links":0,"syntology":null},{"paper":null,"slug":"contrastive-pre-training-for-zero-shot","title":"Contrastive Pre-training for Zero-Shot Information Retrieval","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-architecture-distillation-using","title":"Cross-Architecture Distillation Using Bidirectional CMOW Embeddings","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"crossformer-transformer-with-alternated-cross","title":"Crossformer: Transformer with Alternated Cross-Layer Guidance","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"d-2-etr-decoder-only-detr-with","title":"D$^2$ETR: Decoder-Only DETR with Computationally Efficient Cross-Scale Attention","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dictionary-learning-under-generative","title":"Dictionary Learning Under Generative Coefficient Priors with Applications to Compression","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"disentangled-mask-attention-in-transformer","title":"Disentangled Mask Attention in Transformer","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"distributional-decision-transformer-for","title":"Distributional Decision Transformer for Hindsight Information Matching","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-packing-towards-2x-nlp-speed-up","title":"Efficient Packing: Towards 2x NLP Speed-Up without Loss of Accuracy for BERT","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-point-transformer-for-large-scale","title":"Efficient Point Transformer for Large-scale 3D Scene Understanding","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"embedding-models-through-the-lens-of-stable","title":"Embedding models through the lens of Stable Coloring","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"equivariant-transformers-for-neural-network","title":"Equivariant Transformers for Neural Network based Molecular Potentials","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ernie-sparse-robust-efficient-transformer","title":"ERNIE-SPARSE: Robust Efficient Transformer Through Hierarchically Unifying Isolated Information","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"fairness-in-representation-for-multilingual","title":"Fairness in Representation for Multilingual NLP: Insights from Controlled Experiments on Conditional Language Modeling","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"gental-generative-denoising-skip-gram","title":"GenTAL: Generative Denoising Skip-gram Transformer for Unsupervised Binary Code Similarity Detection","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"geometry-entangled-visual-semantic","title":"Geometry-Entangled Visual Semantic Transformer for Image Captioning","date":"2021-09-29","arxiv_id":"2109.14137","n_code_links":0,"syntology":null},{"paper":null,"slug":"gradient-broadcast-adaptation-defending","title":"Gradient Broadcast Adaptation: Defending against the backdoor attack in pre-trained models","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"graphix-a-pre-trained-graph-edit-model-for","title":"GRAPHIX: A Pre-trained Graph Edit Model for Automated Program Repair","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"grounding-language-representation-with-visual","title":"Grounding Language Representation with Visual Object Information via Cross Modal Pretraining","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/group-based-interleaved-pipeline-parallelism","slug":"group-based-interleaved-pipeline-parallelism","title":"Group-based Interleaved Pipeline Parallelism for Large-scale DNN Training","date":"2021-09-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"guiding-transformers-to-process-in-steps","title":"Guiding Transformers to Process in Steps","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hfsp-a-hardware-friendly-soft-pruning","title":"HFSP: A Hardware-friendly Soft Pruning Framework for Vision Transformers","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-character-tagger-for-short-text","title":"Hierarchical Character Tagger for Short Text Spelling Error Correction","date":"2021-09-29","arxiv_id":"2109.14259","n_code_links":0,"syntology":null},{"paper":null,"slug":"holoformer-deep-compression-of-pre-trained","title":"HoloFormer: Deep Compression of Pre-Trained Transforms via Unified Optimization of N:M Sparsity and Integer Quantization","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"how-does-bert-address-polysemy-of-korean","title":"How does BERT address polysemy of Korean adverbial postpositions -ey, -eyse, and -(u)lo?","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hydrasum-disentangling-stylistic-features-in","title":"HydraSum - Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"illiterate-dall-cdot-e-learns-to-compose","title":"Illiterate DALL$\\cdot$E Learns to Compose","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-sentiment-classification-using-0","title":"Improving Sentiment Classification Using 0-Shot Generated Labels for Custom Transformer Embeddings","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"in-defense-of-dual-encoders-for-neural","title":"In defense of dual-encoders for neural ranking","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"isotropic-contextual-representations-through","title":"Isotropic Contextual Representations through Variational Regularization","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"language-model-pre-training-improves","title":"Language Model Pre-training Improves Generalization in Policy Learning","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-rate-grafting-transferability-of","title":"Learning Rate Grafting: Transferability of Optimizer Tuning","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-schedule-learning-rate-with-graph","title":"Learning to Schedule Learning rate with Graph Neural Networks","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-visual-linguistic-adequacy-fidelity","title":"Learning Visual-Linguistic Adequacy, Fidelity, and Fluency for Novel Object Captioning","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"lmsa-low-relation-mutil-head-self-attention","title":"LMSA: Low-relation Mutil-head Self-Attention Mechanism in Visual Transformer","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/localizing-objects-with-self-supervised","slug":"localizing-objects-with-self-supervised","title":"Localizing Objects with Self-Supervised Transformers and no Labels","date":"2021-09-29","arxiv_id":"2109.14279","n_code_links":2,"syntology":null}],"record_sha256":"02a51e87928264f16b510d434987346c9fcd420ea39ef8da381a8d02dab371bf","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}