{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1803.01271","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","created":"2018-03-04","cited_by_count":1476},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"id":"1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","created":"2013-03-22","cited_by_count":669},{"id":"1909.01377","title":"Deep Equilibrium Models","created":"2019-09-03","cited_by_count":615},{"id":"1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","created":"2015-11-02","cited_by_count":592},{"id":"1609.07061","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","created":"2016-09-22","cited_by_count":426},{"id":"1909.05840","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","created":"2019-09-12","cited_by_count":359},{"id":"1511.06464","title":"Unitary Evolution Recurrent Neural Networks","created":"2015-11-20","cited_by_count":294},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269},{"id":"2402.01032","title":"Repeat After Me: Transformers are Better than State Space Models at Copying","created":"2024-02-01","cited_by_count":216},{"id":"1811.05381","title":"Sorting out Lipschitz function approximation","created":"2018-11-13","cited_by_count":213},{"id":"1803.04831","title":"Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN","created":"2018-03-13","cited_by_count":143},{"id":"1901.08428","title":"Cheap Orthogonal Constraints in Neural Networks: A Simple Parametrization of the Orthogonal and Unitary Group","created":"2019-01-24","cited_by_count":134},{"id":"1902.09689","title":"AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks","created":"2019-02-26","cited_by_count":112},{"id":"1611.00035","title":"Full-Capacity Unitary Recurrent Neural Networks","created":"2016-10-31","cited_by_count":94},{"id":"2006.12070","title":"Lipschitz Recurrent Neural Networks","created":"2020-06-22","cited_by_count":89},{"id":"1702.00071","title":"On orthogonality and learning recurrent networks with long term dependencies","created":"2017-01-31","cited_by_count":83},{"id":"1707.09520","title":"Orthogonal Recurrent Neural Networks with Scaled Cayley Transform","created":"2017-07-29","cited_by_count":83},{"id":"1710.02224","title":"Dilated Recurrent Neural Networks","created":"2017-10-05","cited_by_count":83},{"id":"2006.04418","title":"Learning Long-Term Dependencies in Irregularly-Sampled Time Series","created":"2020-06-08","cited_by_count":83},{"id":"2010.00951","title":"Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies","created":"2020-10-02","cited_by_count":82},{"id":"1612.05231","title":"Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs","created":"2016-12-15","cited_by_count":65},{"id":"2008.05221","title":"Compression of Deep Learning Models for Text: A Survey","created":"2020-08-12","cited_by_count":64},{"id":"1612.00188","title":"Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections","created":"2016-12-01","cited_by_count":57},{"id":"1611.01600","title":"Loss-aware Binarization of Deep Networks","created":"2016-11-05","cited_by_count":56},{"id":"2103.05487","title":"UnICORNN: A recurrent model for learning very long time dependencies","created":"2021-03-09","cited_by_count":56},{"id":"1804.11188","title":"Can recurrent neural networks warp time?","created":"2018-03-23","cited_by_count":55},{"id":"2110.06804","title":"A comprehensive review of Binary Neural Network","created":"2021-10-11","cited_by_count":45},{"id":"1602.06662","title":"Recurrent Orthogonal Networks and Long-Memory Tasks","created":"2016-02-22","cited_by_count":38},{"id":"1901.02358","title":"FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network","created":"2019-01-08","cited_by_count":38},{"id":"1910.10485","title":"Fully Quantized Transformer for Machine Translation","created":"2019-10-17","cited_by_count":36},{"id":"1803.09327","title":"Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization","created":"2018-03-25","cited_by_count":35},{"id":"1810.07411","title":"Continual Learning of Recurrent Neural Networks by Locally Aligning Distributed Representations","created":"2018-10-17","cited_by_count":32},{"id":"1802.00150","title":"Alternating Multi-bit Quantization for Recurrent Neural Networks","created":"2018-02-01","cited_by_count":31},{"id":"1905.12080","title":"Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics","created":"2019-05-28","cited_by_count":29},{"id":"2203.05483","title":"projUNN: efficient method for training deep networks with unitary matrices","created":"2022-03-10","cited_by_count":27},{"id":"1706.07145","title":"Balanced Quantization: An Effective and Efficient Approach to Quantized Neural Networks","created":"2017-06-22","cited_by_count":21},{"id":"2108.02297","title":"Spartus: A 9.4 TOp/s FPGA-based LSTM Accelerator Exploiting Spatio-Temporal Sparsity","created":"2021-08-04","cited_by_count":20},{"id":"2009.07453","title":"Extremely Low Bit Transformer Quantization for On-Device Neural Machine Translation","created":"2020-09-16","cited_by_count":14},{"id":"1705.10142","title":"Kronecker Recurrent Units","created":"2017-05-29","cited_by_count":13},{"id":"1608.06902","title":"Recurrent Neural Networks With Limited Numerical Precision","created":"2016-08-24","cited_by_count":12},{"id":"1802.02615","title":"Effective Quantization Approaches for Recurrent Neural Networks","created":"2018-02-07","cited_by_count":10},{"id":"1809.11086","title":"Learning Recurrent Binary/Ternary Weights","created":"2018-09-28","cited_by_count":9},{"id":"2212.11791","title":"Training Integer-Only Deep Recurrent Neural Networks","created":"2022-12-22","cited_by_count":5}],"next_cursor":null}