{"list":"other","total":52,"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":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"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":"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":"2205.13504","title":"Are Transformers Effective for Time Series Forecasting?","created":"2022-05-26","cited_by_count":1424},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"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":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"1703.07015","title":"Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks","created":"2017-03-21","cited_by_count":879},{"id":"2402.02592","title":"Unified Training of Universal Time Series Forecasting Transformers","created":"2024-02-04","cited_by_count":614},{"id":"1907.00235","title":"Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting","created":"2019-06-29","cited_by_count":607},{"id":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"2106.10466","title":"TS2Vec: Towards Universal Representation of Time Series","created":"2021-06-19","cited_by_count":471},{"id":"1802.04431","title":"Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding","created":"2018-02-13","cited_by_count":410},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401},{"id":"2405.14616","title":"TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting","created":"2024-05-23","cited_by_count":346},{"id":"1811.00075","title":"The UEA multivariate time series classification archive, 2018","created":"2018-10-31","cited_by_count":338},{"id":"2106.09305","title":"SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction","created":"2021-06-17","cited_by_count":338},{"id":"2402.02368","title":"Timer: Generative Pre-trained Transformers Are Large Time Series Models","created":"2024-02-04","cited_by_count":208},{"id":"2407.13278","title":"Deep Time Series Models: A Comprehensive Survey and Benchmark","created":"2024-07-18","cited_by_count":197},{"id":"2002.04236","title":"A review on outlier/anomaly detection in time series data","created":"2020-02-11","cited_by_count":189},{"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":"2311.06184","title":"Frequency-domain MLPs are More Effective Learners in Time Series Forecasting","created":"2023-11-10","cited_by_count":172},{"id":"2308.00442","title":"FLatten Transformer: Vision Transformer using Focused Linear Attention","created":"2023-08-01","cited_by_count":171},{"id":"2310.09751","title":"UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting","created":"2023-10-15","cited_by_count":144},{"id":"2306.09364","title":"TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting","created":"2023-06-14","cited_by_count":139},{"id":"2301.07945","title":"PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction","created":"2023-01-19","cited_by_count":137},{"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":"2305.18803","title":"Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors","created":"2023-05-30","cited_by_count":113},{"id":"2403.03234","title":"Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling","created":"2024-03-05","cited_by_count":113},{"id":"2405.16605","title":"Demystify Mamba in Vision: A Linear Attention Perspective","created":"2024-05-26","cited_by_count":102},{"id":"2304.05206","title":"The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecasting","created":"2023-04-11","cited_by_count":101},{"id":"2308.11200","title":"SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting","created":"2023-08-22","cited_by_count":55},{"id":"2403.19888","title":"MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection","created":"2024-03-29","cited_by_count":40},{"id":"2408.01129","title":"A Survey of Mamba","created":"2024-08-02","cited_by_count":39},{"id":"2406.10450","title":"TokenRec: Learning to Tokenize ID for LLM-based Generative Recommendation","created":"2024-06-15","cited_by_count":35},{"id":"2011.11347","title":"Time Series Data Imputation: A Survey on Deep Learning Approaches","created":"2020-11-23","cited_by_count":34},{"id":"2401.17548","title":"Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators","created":"2024-01-31","cited_by_count":32},{"id":"2402.01231","title":"Unveiling Delay Effects in Traffic Forecasting: A Perspective from Spatial-Temporal Delay Differential Equations","created":"2024-02-02","cited_by_count":11},{"id":"2502.12448","title":"From Principles to Applications: A Comprehensive Survey of Discrete Tokenizers in Generation, Comprehension, Recommendation, and Information Retrieval","created":"2025-02-18","cited_by_count":11},{"id":"2503.10198","title":"Deep Learning for Time Series Forecasting: A Survey","created":"2025-03-13","cited_by_count":10},{"id":"2310.05668","title":"LARA: A Light and Anti-overfitting Retraining Approach for Unsupervised Time Series Anomaly Detection","created":"2023-10-09","cited_by_count":9},{"id":"2409.01192","title":"SSD4Rec: A Structured State Space Duality Model for Efficient Sequential Recommendation","created":"2024-09-02","cited_by_count":9},{"id":"2504.12007","title":"Diffusion Generative Recommendation with Continuous Tokens","created":"2025-04-16","cited_by_count":9},{"id":"2512.15133","title":"HD-Prot: A Protein Language Model for Joint Sequence-Structure Modeling with Continuous Structure Tokens","created":"2025-12-17","cited_by_count":4},{"id":"2504.16432","title":"iTFKAN: Interpretable Time Series Forecasting with Kolmogorov-Arnold Network","created":"2025-04-23","cited_by_count":2},{"id":"2506.18939","title":"Damba-ST: Domain-Adaptive Mamba for Efficient Urban Spatio-Temporal Prediction","created":"2025-06-22","cited_by_count":2}],"next_cursor":null}