{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2010.08895","title":"Fourier Neural Operator for Parametric Partial Differential Equations","created":"2020-10-18","cited_by_count":2908},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2006.10739","title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","created":"2020-06-18","cited_by_count":2200},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"1708.00055","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","created":"2017-07-31","cited_by_count":1001},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"id":"2008.02217","title":"Hopfield Networks is All You Need","created":"2020-07-16","cited_by_count":475},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347},{"id":"2105.14995","title":"Choose a Transformer: Fourier or Galerkin","created":"2021-05-31","cited_by_count":343},{"id":"2006.10685","title":"Deep Learning Enabled Semantic Communication Systems","created":"2020-06-18","cited_by_count":292},{"id":"2107.00645","title":"Global Filter Networks for Image Classification","created":"2021-07-01","cited_by_count":260},{"id":"2002.05651","title":"Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning","created":"2020-01-31","cited_by_count":249},{"id":"2005.00743","title":"Synthesizer: Rethinking Self-Attention in Transformer Models","created":"2020-05-02","cited_by_count":205},{"id":"2204.05149","title":"The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink","created":"2022-04-11","cited_by_count":184},{"id":"2203.16634","title":"Transformer Language Models without Positional Encodings Still Learn Positional Information","created":"2022-03-30","cited_by_count":150},{"id":"1804.06028","title":"ListOps: A Diagnostic Dataset for Latent Tree Learning","created":"2018-04-17","cited_by_count":129},{"id":"1805.08315","title":"Learning long-range spatial dependencies with horizontal gated-recurrent units","created":"2018-05-21","cited_by_count":98},{"id":"1312.5851","title":"Fast Training of Convolutional Networks through FFTs","created":"2013-12-20","cited_by_count":89},{"id":"1506.03767","title":"Spectral Representations for Convolutional Neural Networks","created":"2015-06-11","cited_by_count":81},{"id":"2111.00035","title":"Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\\\"om Method","created":"2021-10-29","cited_by_count":63},{"id":"2002.10260","title":"Fixed Encoder Self-Attention Patterns in Transformer-Based Machine Translation","created":"2020-02-24","cited_by_count":43},{"id":"2005.00742","title":"Hard-Coded Gaussian Attention for Neural Machine Translation","created":"2020-05-02","cited_by_count":42},{"id":"2011.04823","title":"Language Through a Prism: A Spectral Approach for Multiscale Language Representations","created":"2020-11-09","cited_by_count":39},{"id":"2102.07594","title":"Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT","created":"2021-02-15","cited_by_count":31},{"id":"2108.07597","title":"Light Field Image Super-Resolution with Transformers","created":"2021-08-17","cited_by_count":31},{"id":"1412.7580","title":"Fast Convolutional Nets With fbfft: A GPU Performance Evaluation","created":"2014-12-24","cited_by_count":27},{"id":"2108.02347","title":"FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention","created":"2021-08-05","cited_by_count":26},{"id":"1811.08257","title":"FALCON: A Fourier Transform Based Approach for Fast and Secure Convolutional Neural Network Predictions","created":"2018-11-20","cited_by_count":20},{"id":"2007.00140","title":"RE-MIMO: Recurrent and Permutation Equivariant Neural MIMO Detection","created":"2020-06-30","cited_by_count":20},{"id":"1711.08591","title":"Regularization of Deep Neural Networks with Spectral Dropout","created":"2017-11-23","cited_by_count":14},{"id":"2201.02711","title":"Block Walsh-Hadamard Transform Based Binary Layers in Deep Neural Networks","created":"2022-01-07","cited_by_count":13},{"id":"2203.01178","title":"DCT-Former: Efficient Self-Attention with Discrete Cosine Transform","created":"2022-03-02","cited_by_count":12},{"id":"1803.06585","title":"Learning Long Term Dependencies via Fourier Recurrent Units","created":"2018-03-17","cited_by_count":11},{"id":"1405.2262","title":"Training Deep Fourier Neural Networks To Fit Time-Series Data","created":"2014-05-09","cited_by_count":7},{"id":"1601.06815","title":"Very Efficient Training of Convolutional Neural Networks using Fast Fourier Transform and Overlap-and-Add","created":"2016-01-25","cited_by_count":7},{"id":"2104.01522","title":"TSNAT: Two-Step Non-Autoregressvie Transformer Models for Speech Recognition","created":"2021-04-04","cited_by_count":7},{"id":"2204.08822","title":"A Convolutional-Attentional Neural Framework for Structure-Aware Performance-Score Synchronization","created":"2022-04-19","cited_by_count":5},{"id":"1807.00141","title":"Fractional Wavelet Scattering Network and Applications","created":"2018-06-30","cited_by_count":1}],"next_cursor":null}