{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"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":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"1910.03193","title":"DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators","created":"2019-10-08","cited_by_count":2018},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1607.08022","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","created":"2016-07-27","cited_by_count":1198},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"2003.03485","title":"Neural Operator: Graph Kernel Network for Partial Differential Equations","created":"2020-03-07","cited_by_count":734},{"id":"1807.03819","title":"Universal Transformers","created":"2018-07-10","cited_by_count":647},{"id":"1907.04502","title":"DeepXDE: A deep learning library for solving differential equations","created":"2019-07-10","cited_by_count":619},{"id":"2006.10503","title":"SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks","created":"2020-06-18","cited_by_count":607},{"id":"2103.10974","title":"Learning the solution operator of parametric partial differential equations with physics-informed DeepOnets","created":"2021-03-19","cited_by_count":540},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"1912.10077","title":"Are Transformers universal approximators of sequence-to-sequence functions?","created":"2019-12-20","cited_by_count":406},{"id":"1812.01243","title":"Efficient Attention: Attention with Linear Complexities","created":"2018-12-04","cited_by_count":368},{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354},{"id":"2006.09535","title":"Multipole Graph Neural Operator for Parametric Partial Differential Equations","created":"2020-06-16","cited_by_count":349},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347},{"id":"2005.03180","title":"Model Reduction and Neural Networks for Parametric PDEs","created":"2020-05-07","cited_by_count":258},{"id":"1709.03815","title":"OpenNMT: Open-source Toolkit for Neural Machine Translation","created":"2017-09-12","cited_by_count":251},{"id":"1908.11775","title":"Transformer Dissection: A Unified Understanding of Transformer's Attention via the Lens of Kernel","created":"2019-08-30","cited_by_count":213},{"id":"1801.06879","title":"Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification","created":"2018-01-21","cited_by_count":199},{"id":"2103.05247","title":"Pretrained Transformers as Universal Computation Engines","created":"2021-03-09","cited_by_count":162},{"id":"1910.05895","title":"Transformers without Tears: Improving the Normalization of Self-Attention","created":"2019-10-14","cited_by_count":153},{"id":"1704.04058","title":"Solving ill-posed inverse problems using iterative deep neural networks","created":"2017-04-13","cited_by_count":145},{"id":"1905.13166","title":"Prediction of Aerodynamic Flow Fields Using Convolutional Neural Networks","created":"2019-05-30","cited_by_count":145},{"id":"1808.04444","title":"Character-Level Language Modeling with Deeper Self-Attention","created":"2018-08-09","cited_by_count":138},{"id":"2001.04536","title":"Understanding and mitigating gradient pathologies in physics-informed neural networks","created":"2020-01-13","cited_by_count":135},{"id":"2012.10885","title":"LieTransformer: Equivariant self-attention for Lie Groups","created":"2020-12-20","cited_by_count":100},{"id":"2005.10224","title":"The Random Feature Model for Input-Output Maps between Banach Spaces","created":"2020-05-20","cited_by_count":90},{"id":"1806.10909","title":"ResNet with one-neuron hidden layers is a Universal Approximator","created":"2018-06-28","cited_by_count":79},{"id":"1904.09019","title":"Graph Element Networks: adaptive, structured computation and memory","created":"2019-04-18","cited_by_count":41},{"id":"1712.00527","title":"Adaptive Sampled Softmax with Kernel Based Sampling","created":"2017-12-02","cited_by_count":38},{"id":"1901.11399","title":"Equivariant Transformer Networks","created":"2019-01-25","cited_by_count":35},{"id":"1907.10747","title":"Sampled Softmax with Random Fourier Features","created":"2019-07-24","cited_by_count":33},{"id":"1904.01514","title":"Data driven approximation of parametrized PDEs by Reduced Basis and Neural Networks","created":"2019-04-02","cited_by_count":22},{"id":"2103.15798","title":"Rethinking Neural Operations for Diverse Tasks","created":"2021-03-29","cited_by_count":18},{"id":"2006.06147","title":"Implicit Kernel Attention","created":"2020-06-11","cited_by_count":13},{"id":"1802.04630","title":"A probabilistic framework for multi-view feature learning with many-to-many associations via neural networks","created":"2018-02-13","cited_by_count":5},{"id":"1609.05866","title":"A Cheap Linear Attention Mechanism with Fast Lookups and Fixed-Size Representations","created":"2016-09-19","cited_by_count":3},{"id":"1907.00806","title":"A data-driven approach for multiscale elliptic PDEs with random coefficients based on intrinsic dimension reduction","created":"2019-07-01","cited_by_count":2}],"next_cursor":null}