{"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":"1806.07366","title":"Neural Ordinary Differential Equations","created":"2018-06-19","cited_by_count":3779},{"id":"2010.08895","title":"Fourier Neural Operator for Parametric Partial Differential Equations","created":"2020-10-18","cited_by_count":2908},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2006.09661","title":"Implicit Neural Representations with Periodic Activation Functions","created":"2020-06-17","cited_by_count":2238},{"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":"2012.07436","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","created":"2020-12-14","cited_by_count":2169},{"id":"2211.14730","title":"A Time Series is Worth 64 Words: Long-term Forecasting with Transformers","created":"2022-11-27","cited_by_count":2039},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"2106.13008","title":"Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting","created":"2021-06-24","cited_by_count":1676},{"id":"2205.13504","title":"Are Transformers Effective for Time Series Forecasting?","created":"2022-05-26","cited_by_count":1424},{"id":"1806.08734","title":"On the Spectral Bias of Neural Networks","created":"2018-06-22","cited_by_count":1341},{"id":"2201.12740","title":"FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting","created":"2022-01-30","cited_by_count":1210},{"id":"2210.02186","title":"TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis","created":"2022-10-05","cited_by_count":1058},{"id":"1609.09106","title":"HyperNetworks","created":"2016-09-27","cited_by_count":1027},{"id":"2310.06625","title":"iTransformer: Inverted Transformers Are Effective for Time Series Forecasting","created":"2023-10-10","cited_by_count":931},{"id":"1906.01618","title":"Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations","created":"2019-06-04","cited_by_count":864},{"id":"1804.03209","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","created":"2018-04-09","cited_by_count":752},{"id":"2012.09161","title":"Learning Continuous Image Representation with Local Implicit Image Function","created":"2020-12-16","cited_by_count":552},{"id":"2005.08926","title":"Neural Controlled Differential Equations for Irregular Time Series","created":"2020-05-18","cited_by_count":506},{"id":"2110.02642","title":"Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy","created":"2021-10-06","cited_by_count":394},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347},{"id":"2105.11120","title":"A Fourier-based Framework for Domain Generalization","created":"2021-05-24","cited_by_count":290},{"id":"2107.00645","title":"Global Filter Networks for Image Classification","created":"2021-07-01","cited_by_count":260},{"id":"2206.08496","title":"Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency","created":"2022-06-17","cited_by_count":250},{"id":"2111.13587","title":"Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers","created":"2021-11-24","cited_by_count":248},{"id":"2108.05895","title":"Mobile-Former: Bridging MobileNet and Transformer","created":"2021-08-12","cited_by_count":235},{"id":"1905.12374","title":"GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series","created":"2019-05-29","cited_by_count":231},{"id":"1705.09792","title":"Deep Complex Networks","created":"2017-05-27","cited_by_count":217},{"id":"2012.12821","title":"Focal Frequency Loss for Image Reconstruction and Synthesis","created":"2020-12-23","cited_by_count":206},{"id":"2307.03756","title":"FITS: Modeling Time Series with $10k$ Parameters","created":"2023-07-06","cited_by_count":195},{"id":"2311.06184","title":"Frequency-domain MLPs are More Effective Learners in Time Series Forecasting","created":"2023-11-10","cited_by_count":172},{"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":"2202.01575","title":"CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting","created":"2022-02-03","cited_by_count":144},{"id":"2009.08295","title":"Neural Rough Differential Equations for Long Time Series","created":"2020-09-17","cited_by_count":143},{"id":"2311.06190","title":"FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective","created":"2023-11-10","cited_by_count":127},{"id":"2102.02611","title":"CKConv: Continuous Kernel Convolution For Sequential Data","created":"2021-02-04","cited_by_count":120},{"id":"2112.01917","title":"A Structured Dictionary Perspective on Implicit Neural Representations","created":"2021-12-03","cited_by_count":100},{"id":"2202.04770","title":"Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion","created":"2022-02-08","cited_by_count":96},{"id":"1903.03107","title":"Phase-aware Speech Enhancement with Deep Complex U-Net","created":"2019-03-07","cited_by_count":73},{"id":"2206.07706","title":"Masked Frequency Modeling for Self-Supervised Visual Pre-Training","created":"2022-06-15","cited_by_count":71},{"id":"1901.10548","title":"Latent Normalizing Flows for Discrete Sequences","created":"2019-01-29","cited_by_count":67},{"id":"2301.08871","title":"Ti-MAE: Self-Supervised Masked Time Series Autoencoders","created":"2023-01-21","cited_by_count":63},{"id":"2010.04903","title":"What Do Position Embeddings Learn? An Empirical Study of Pre-Trained Language Model Positional Encoding","created":"2020-10-10","cited_by_count":52},{"id":"2307.14008","title":"Adaptive Frequency Filters As Efficient Global Token Mixers","created":"2023-07-26","cited_by_count":45},{"id":"2203.12198","title":"Deep Frequency Filtering for Domain Generalization","created":"2022-03-23","cited_by_count":43},{"id":"2211.13223","title":"Generalizable Implicit Neural Representations via Instance Pattern Composers","created":"2022-11-23","cited_by_count":39},{"id":"2002.10516","title":"Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows","created":"2020-02-24","cited_by_count":37},{"id":"2303.14865","title":"Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete Tokens","created":"2023-03-27","cited_by_count":35},{"id":"2307.10923","title":"Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time Series","created":"2023-07-20","cited_by_count":16}],"next_cursor":null}