{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"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":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"1612.08083","title":"Language Modeling with Gated Convolutional Networks","created":"2016-12-23","cited_by_count":702},{"id":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"id":"2110.13985","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","created":"2021-10-26","cited_by_count":608},{"id":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","created":"2015-11-02","cited_by_count":592},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"2206.11893","title":"On the Parameterization and Initialization of Diagonal State Space Models","created":"2022-06-23","cited_by_count":424},{"id":"2203.14343","title":"Diagonal State Spaces are as Effective as Structured State Spaces","created":"2022-03-27","cited_by_count":350},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347},{"id":"1511.06464","title":"Unitary Evolution Recurrent Neural Networks","created":"2015-11-20","cited_by_count":294},{"id":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179},{"id":"2202.09729","title":"It's Raw! Audio Generation with State-Space Models","created":"2022-02-20","cited_by_count":171},{"id":"2006.04439","title":"Liquid Time-constant Networks","created":"2020-06-08","cited_by_count":161},{"id":"2205.08897","title":"FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting","created":"2022-05-18","cited_by_count":147},{"id":"1803.04831","title":"Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN","created":"2018-03-13","cited_by_count":143},{"id":"2209.12951","title":"Liquid Structural State-Space Models","created":"2022-09-26","cited_by_count":136},{"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":"1504.00941","title":"A Simple Way to Initialize Recurrent Networks of Rectified Linear Units","created":"2015-04-03","cited_by_count":130},{"id":"1709.04057","title":"Parallelizing Linear Recurrent Neural Nets Over Sequence Length","created":"2017-09-12","cited_by_count":127},{"id":"2206.12037","title":"How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis Projections","created":"2022-06-24","cited_by_count":122},{"id":"2204.01692","title":"Long Movie Clip Classification with State-Space Video Models","created":"2022-04-04","cited_by_count":106},{"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":"2210.09298","title":"What Makes Convolutional Models Great on Long Sequence Modeling?","created":"2022-10-17","cited_by_count":87},{"id":"1707.09520","title":"Orthogonal Recurrent Neural Networks with Scaled Cayley Transform","created":"2017-07-29","cited_by_count":83},{"id":"1609.05191","title":"Gradient Descent Learns Linear Dynamical Systems","created":"2016-09-16","cited_by_count":79},{"id":"1703.04680","title":"On Convergence of Extended Dynamic Mode Decomposition to the Koopman Operator","created":"2017-03-14","cited_by_count":73},{"id":"2205.14027","title":"Learning Dynamical Systems via Koopman Operator Regression in Reproducing Kernel Hilbert Spaces","created":"2022-05-27","cited_by_count":67},{"id":"1610.10099","title":"Neural Machine Translation in Linear Time","created":"2016-10-31","cited_by_count":66},{"id":"1612.05231","title":"Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs","created":"2016-12-15","cited_by_count":65},{"id":"1707.01146","title":"Data-driven discovery of Koopman eigenfunctions for control","created":"2017-07-04","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":"1602.07647","title":"Generalizing Koopman Theory to allow for inputs and control","created":"2016-02-24","cited_by_count":53},{"id":"1702.05043","title":"Unbiased Online Recurrent Optimization","created":"2017-02-16","cited_by_count":47},{"id":"1809.03702","title":"Sparse Attentive Backtracking: Temporal CreditAssignment Through Reminding","created":"2018-09-11","cited_by_count":34},{"id":"1810.07411","title":"Continual Learning of Recurrent Neural Networks by Locally Aligning Distributed Representations","created":"2018-10-17","cited_by_count":32},{"id":"2212.00768","title":"Simplifying and Understanding State Space Models with Diagonal Linear RNNs","created":"2022-12-01","cited_by_count":23},{"id":"1607.04903","title":"Learning Unitary Operators with Help From u(n)","created":"2016-07-17","cited_by_count":15},{"id":"1711.11179","title":"State Space LSTM Models with Particle MCMC Inference","created":"2017-11-30","cited_by_count":11},{"id":"1911.03588","title":"MKD: a Multi-Task Knowledge Distillation Approach for Pretrained Language Models","created":"2019-11-09","cited_by_count":8},{"id":"2104.02899","title":"Recognizing and Verifying Mathematical Equations using Multiplicative Differential Neural Units","created":"2021-04-07","cited_by_count":8},{"id":"2006.03651","title":"A provably stable neural network Turing Machine","created":"2020-06-05","cited_by_count":7},{"id":"1711.02326","title":"Sparse Attentive Backtracking: Long-Range Credit Assignment in Recurrent Networks","created":"2017-11-07","cited_by_count":3}],"next_cursor":null}