{"list":"other","total":57,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"2009.09761","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","created":"2020-09-21","cited_by_count":1354},{"id":"2106.10466","title":"TS2Vec: Towards Universal Representation of Time Series","created":"2021-06-19","cited_by_count":471},{"id":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408},{"id":"2312.02696","title":"Analyzing and Improving the Training Dynamics of Diffusion Models","created":"2023-12-05","cited_by_count":402},{"id":"1605.09522","title":"Kernel Mean Embedding of Distributions: A Review and Beyond","created":"2016-05-31","cited_by_count":364},{"id":"1801.10198","title":"Generating Wikipedia by Summarizing Long Sequences","created":"2018-01-30","cited_by_count":335},{"id":"1706.02633","title":"Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs","created":"2017-06-08","cited_by_count":333},{"id":"2412.06264","title":"Flow Matching Guide and Code","created":"2024-12-09","cited_by_count":301},{"id":"2102.12086","title":"Modern Koopman Theory for Dynamical Systems","created":"2021-02-24","cited_by_count":276},{"id":"2403.01742","title":"Diffusion-TS: Interpretable Diffusion for General Time Series Generation","created":"2024-03-04","cited_by_count":184},{"id":"2202.09729","title":"It's Raw! Audio Generation with State-Space Models","created":"2022-02-20","cited_by_count":171},{"id":"2109.08668","title":"Primer: Searching for Efficient Transformers for Language Modeling","created":"2021-09-17","cited_by_count":164},{"id":"2111.08095","title":"TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation","created":"2021-11-15","cited_by_count":142},{"id":"1710.06012","title":"VAMPnets: Deep learning of molecular kinetics","created":"2017-10-16","cited_by_count":136},{"id":"1611.09904","title":"C-RNN-GAN: Continuous recurrent neural networks with adversarial training","created":"2016-11-29","cited_by_count":132},{"id":"1906.04370","title":"Maximum Mean Discrepancy Gradient Flow","created":"2019-06-11","cited_by_count":127},{"id":"2002.03689","title":"A Measure-Theoretic Approach to Kernel Conditional Mean Embeddings","created":"2020-02-10","cited_by_count":86},{"id":"2009.14397","title":"Deep Equals Shallow for ReLU Networks in Kernel Regimes","created":"2020-09-30","cited_by_count":85},{"id":"2006.08571","title":"COT-GAN: Generating Sequential Data via Causal Optimal Transport","created":"2020-06-15","cited_by_count":71},{"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":"2108.00981","title":"PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series","created":"2021-08-02","cited_by_count":58},{"id":"2307.01717","title":"On the Constrained Time-Series Generation Problem","created":"2023-07-04","cited_by_count":54},{"id":"2211.14400","title":"Optimal Approximation Rates for Deep ReLU Neural Networks on Sobolev and Besov Spaces","created":"2022-11-25","cited_by_count":51},{"id":"2310.02619","title":"Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs","created":"2023-10-04","cited_by_count":49},{"id":"1411.2066","title":"Learning Theory for Distribution Regression","created":"2014-11-08","cited_by_count":48},{"id":"1712.01572","title":"Eigendecompositions of Transfer Operators in Reproducing Kernel Hilbert Spaces","created":"2017-12-05","cited_by_count":48},{"id":"2303.16535","title":"Nonlinear Independent Component Analysis for Principled Disentanglement in Unsupervised Deep Learning","created":"2023-03-29","cited_by_count":48},{"id":"2210.02040","title":"GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networks","created":"2022-10-05","cited_by_count":44},{"id":"2410.19538","title":"Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series","created":"2024-10-25","cited_by_count":43},{"id":"1708.08157","title":"Characteristic and Universal Tensor Product Kernels","created":"2017-08-28","cited_by_count":41},{"id":"2212.12749","title":"Deep Latent State Space Models for Time-Series Generation","created":"2022-12-24","cited_by_count":38},{"id":"2305.11463","title":"Generative Sliced MMD Flows with Riesz Kernels","created":"2023-05-19","cited_by_count":37},{"id":"1501.02056","title":"Sequential Kernel Herding: Frank-Wolfe Optimization for Particle Filtering","created":"2015-01-09","cited_by_count":22},{"id":"2305.16215","title":"Koopman Kernel Regression","created":"2023-05-25","cited_by_count":22},{"id":"2402.06031","title":"An operator learning perspective on parameter-to-observable maps","created":"2024-02-08","cited_by_count":22},{"id":"2012.12917","title":"Nonparametric approximation of conditional expectation operators","created":"2020-12-23","cited_by_count":21},{"id":"2405.06780","title":"Deep MMD Gradient Flow without adversarial training","created":"2024-05-10","cited_by_count":19},{"id":"2405.06147","title":"State-Free Inference of State-Space Models: The Transfer Function Approach","created":"2024-05-10","cited_by_count":18},{"id":"2307.09912","title":"Learning invariant representations of time-homogeneous stochastic dynamical systems","created":"2023-07-19","cited_by_count":17},{"id":"1309.6819","title":"Hilbert Space Embeddings of Predictive State Representations","created":"2013-09-26","cited_by_count":16},{"id":"1905.11255","title":"Kernel Conditional Density Operators","created":"2019-05-27","cited_by_count":14},{"id":"2402.03655","title":"Operator SVD with Neural Networks via Nested Low-Rank Approximation","created":"2024-02-06","cited_by_count":13},{"id":"2312.13426","title":"Consistent Long-Term Forecasting of Ergodic Dynamical Systems","created":"2023-12-20","cited_by_count":10},{"id":"1906.06637","title":"A Closer Look at Double Backpropagation","created":"2019-06-16","cited_by_count":7},{"id":"2410.14477","title":"Laplace Transform Based Low-Complexity Learning of Continuous Markov Semigroups","created":"2024-10-18","cited_by_count":7},{"id":"1806.04550","title":"Deep State Space Models for Unconditional Word Generation","created":"2018-06-12","cited_by_count":6},{"id":"2405.05334","title":"Multiplicative Dynamic Mode Decomposition","created":"2024-05-08","cited_by_count":4}],"next_cursor":null}