{"list":"other","total":72,"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":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"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":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2106.13008","title":"Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting","created":"2021-06-24","cited_by_count":1676},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"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":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"2205.13504","title":"Are Transformers Effective for Time Series Forecasting?","created":"2022-05-26","cited_by_count":1424},{"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":"1904.06690","title":"BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer","created":"2019-04-14","cited_by_count":964},{"id":"2310.06625","title":"iTransformer: Inverted Transformers Are Effective for Time Series Forecasting","created":"2023-10-10","cited_by_count":931},{"id":"1703.07015","title":"Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks","created":"2017-03-21","cited_by_count":879},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"1912.09363","title":"Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting","created":"2019-12-19","cited_by_count":761},{"id":"1905.10437","title":"N-BEATS: Neural basis expansion analysis for interpretable time series forecasting","created":"2019-05-24","cited_by_count":753},{"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":"1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","created":"2013-03-22","cited_by_count":669},{"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":"1508.01991","title":"Bidirectional LSTM-CRF Models for Sequence Tagging","created":"2015-08-09","cited_by_count":546},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502},{"id":"2202.07125","title":"Transformers in Time Series: A Survey","created":"2022-02-15","cited_by_count":497},{"id":"2106.10466","title":"TS2Vec: Towards Universal Representation of Time Series","created":"2021-06-19","cited_by_count":471},{"id":"2206.11893","title":"On the Parameterization and Initialization of Diagonal State Space Models","created":"2022-06-23","cited_by_count":424},{"id":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401},{"id":"2203.14343","title":"Diagonal State Spaces are as Effective as Structured State Spaces","created":"2022-03-27","cited_by_count":350},{"id":"2304.08424","title":"Long-term Forecasting with TiDE: Time-series Dense Encoder","created":"2023-04-17","cited_by_count":332},{"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":"1701.05923","title":"Gate-Variants of Gated Recurrent Unit (GRU) Neural Networks","created":"2017-01-20","cited_by_count":242},{"id":"2106.00750","title":"Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding","created":"2021-06-01","cited_by_count":224},{"id":"1806.00451","title":"Do CIFAR-10 Classifiers Generalize to CIFAR-10?","created":"2018-06-01","cited_by_count":200},{"id":"1909.00590","title":"Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions","created":"2019-09-02","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":"1504.00941","title":"A Simple Way to Initialize Recurrent Networks of Rectified Linear Units","created":"2015-04-03","cited_by_count":130},{"id":"1804.06028","title":"ListOps: A Diagnostic Dataset for Latent Tree Learning","created":"2018-04-17","cited_by_count":129},{"id":"1709.04057","title":"Parallelizing Linear Recurrent Neural Nets Over Sequence Length","created":"2017-09-12","cited_by_count":127},{"id":"1905.06566","title":"HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization","created":"2019-05-16","cited_by_count":121},{"id":"1706.05764","title":"Dipole: Diagnosis Prediction in Healthcare via Attention-based Bidirectional Recurrent Neural Networks","created":"2017-06-19","cited_by_count":116},{"id":"2403.11144","title":"Is Mamba Effective for Time Series Forecasting?","created":"2024-03-17","cited_by_count":114},{"id":"2311.04823","title":"Hierarchically Gated Recurrent Neural Network for Sequence Modeling","created":"2023-11-08","cited_by_count":102},{"id":"1702.00071","title":"On orthogonality and learning recurrent networks with long term dependencies","created":"2017-01-31","cited_by_count":83},{"id":"2403.15360","title":"SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series","created":"2024-03-22","cited_by_count":82},{"id":"1609.05191","title":"Gradient Descent Learns Linear Dynamical Systems","created":"2016-09-16","cited_by_count":79},{"id":"2404.14197","title":"SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion","created":"2024-04-22","cited_by_count":76},{"id":"2402.19047","title":"Theoretical Foundations of Deep Selective State-Space Models","created":"2024-02-29","cited_by_count":74},{"id":"1909.00968","title":"Image Inpainting with Learnable Bidirectional Attention Maps","created":"2019-09-03","cited_by_count":64},{"id":"2403.09898","title":"TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecasting","created":"2024-03-14","cited_by_count":64},{"id":"1709.02755","title":"Simple Recurrent Units for Highly Parallelizable Recurrence","created":"2017-09-08","cited_by_count":61},{"id":"2308.11200","title":"SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting","created":"2023-08-22","cited_by_count":55},{"id":"2305.00359","title":"A Review of Deep Learning Techniques for Speech Processing","created":"2023-04-30","cited_by_count":52},{"id":"2212.10544","title":"Pretraining Without Attention","created":"2022-12-20","cited_by_count":51},{"id":"2403.01255","title":"Automatic Speech Recognition using Advanced Deep Learning Approaches: A survey","created":"2024-03-02","cited_by_count":50},{"id":"1909.11416","title":"Focus Your Attention: A Bidirectional Focal Attention Network for Image-Text Matching","created":"2019-09-25","cited_by_count":49},{"id":"1810.10161","title":"Deep Learning with Long Short-Term Memory for Time Series Prediction","created":"2018-10-24","cited_by_count":39},{"id":"2410.01201","title":"Were RNNs All We Needed?","created":"2024-10-02","cited_by_count":38},{"id":"1702.07028","title":"On the ability of neural nets to express distributions","created":"2017-02-22","cited_by_count":26},{"id":"2205.01972","title":"Sequencer: Deep LSTM for Image Classification","created":"2022-05-04","cited_by_count":23},{"id":"1506.07452","title":"Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation","created":"2015-06-24","cited_by_count":16},{"id":"1602.02218","title":"Strongly-Typed Recurrent Neural Networks","created":"2016-02-06","cited_by_count":13},{"id":"2406.04419","title":"TSCMamba: Mamba Meets Multi-View Learning for Time Series Classification","created":"2024-06-06","cited_by_count":10},{"id":"1703.07910","title":"Bidirectional-Convolutional LSTM Based Spectral-Spatial Feature Learning for Hyperspectral Image Classification","created":"2017-03-23","cited_by_count":8},{"id":"2410.11278","title":"UmambaTSF: A U-shaped Multi-Scale Long-Term Time Series Forecasting Method Using Mamba","created":"2024-10-15","cited_by_count":3}],"next_cursor":null}