{"list":"other","total":51,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2012.07436","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","created":"2020-12-14","cited_by_count":2169},{"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":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"1611.08024","title":"EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces","created":"2016-11-23","cited_by_count":628},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613},{"id":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"2412.06464","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","created":"2024-12-09","cited_by_count":532},{"id":"2005.08926","title":"Neural Controlled Differential Equations for Irregular Time Series","created":"2020-05-18","cited_by_count":506},{"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":"2406.06484","title":"Parallelizing Linear Transformers with the Delta Rule over Sequence Length","created":"2024-06-10","cited_by_count":396},{"id":"1811.00075","title":"The UEA multivariate time series classification archive, 2018","created":"2018-10-31","cited_by_count":338},{"id":"2405.04517","title":"xLSTM: Extended Long Short-Term Memory","created":"2024-05-07","cited_by_count":327},{"id":"2405.18765","title":"Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI","created":"2024-05-29","cited_by_count":327},{"id":"2202.02435","title":"On Neural Differential Equations","created":"2022-02-04","cited_by_count":268},{"id":"2207.02098","title":"Neural Networks and the Chomsky Hierarchy","created":"2022-07-05","cited_by_count":217},{"id":"2412.07236","title":"CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding","created":"2024-12-10","cited_by_count":199},{"id":"2404.08819","title":"The Illusion of State in State-Space Models","created":"2024-04-12","cited_by_count":187},{"id":"2202.09729","title":"It's Raw! Audio Generation with State-Space Models","created":"2022-02-20","cited_by_count":171},{"id":"2111.00254","title":"Equinox: neural networks in JAX via callable PyTrees and filtered transformations","created":"2021-10-30","cited_by_count":148},{"id":"2009.08295","title":"Neural Rough Differential Equations for Long Time Series","created":"2020-09-17","cited_by_count":143},{"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":"2411.12537","title":"Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues","created":"2024-11-19","cited_by_count":101},{"id":"2106.11170","title":"Transformer-based Spatial-Temporal Feature Learning for EEG Decoding","created":"2021-06-11","cited_by_count":97},{"id":"2603.15569","title":"Mamba-3: Improved Sequence Modeling using State Space Principles","created":"2026-03-16","cited_by_count":89},{"id":"1601.08169","title":"Kernels for sequentially ordered data","created":"2016-01-29","cited_by_count":84},{"id":"1905.08494","title":"Deep Signature Transforms","created":"2019-05-21","cited_by_count":75},{"id":"2502.10297","title":"DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products","created":"2025-02-14","cited_by_count":75},{"id":"2402.19047","title":"Theoretical Foundations of Deep Selective State-Space Models","created":"2024-02-29","cited_by_count":74},{"id":"2006.14794","title":"The Signature Kernel is the solution of a Goursat PDE","created":"2020-06-26","cited_by_count":58},{"id":"2309.13414","title":"State-space Models with Layer-wise Nonlinearity are Universal Approximators with Exponential Decaying Memory","created":"2023-09-23","cited_by_count":39},{"id":"2410.03943","title":"Oscillatory State-Space Models","created":"2024-10-04","cited_by_count":39},{"id":"2307.11888","title":"Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues","created":"2023-07-21","cited_by_count":36},{"id":"2402.18512","title":"Log Neural Controlled Differential Equations: The Lie Brackets Make a Difference","created":"2024-02-28","cited_by_count":35},{"id":"2206.14674","title":"Signature Methods in Machine Learning","created":"2022-06-29","cited_by_count":34},{"id":"2405.21064","title":"Recurrent neural networks: vanishing and exploding gradients are not the end of the story","created":"2024-05-31","cited_by_count":25},{"id":"1308.0371","title":"Sparse arrays of signatures for online character recognition","created":"2013-08-01","cited_by_count":18},{"id":"2505.17761","title":"Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models","created":"2025-05-23","cited_by_count":18},{"id":"2509.22284","title":"Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models","created":"2025-09-26","cited_by_count":16},{"id":"2505.12171","title":"Learning to Dissipate Energy in Oscillatory State-Space Models","created":"2025-05-17","cited_by_count":9},{"id":"2305.10256","title":"Nowcasting using regression on signatures","created":"2023-05-17","cited_by_count":5},{"id":"2603.04525","title":"The Volterra signature","created":"2026-03-04","cited_by_count":5},{"id":"2502.13729","title":"Emergence of the Primacy Effect in Structured State-Space Models","created":"2025-02-19","cited_by_count":4},{"id":"2510.12337","title":"Sliding-Window Signatures for Time Series: Application to Electricity Demand Forecasting","created":"2025-10-14","cited_by_count":1},{"id":"2603.05573","title":"Why Depth Matters in Parallelizable Sequence Models: A Lie Algebraic View","created":"2026-03-05","cited_by_count":1}],"next_cursor":null}