{"total":120,"rows":[{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718,"area":"ssm"},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465,"area":"ssm"},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788,"area":"ssm"},{"id":"2110.13985","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","created":"2021-10-26","cited_by_count":608,"area":null},{"id":"2312.06635","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","created":"2023-12-11","cited_by_count":514,"area":"ssm"},{"id":"2206.11893","title":"On the Parameterization and Initialization of Diagonal State Space Models","created":"2022-06-23","cited_by_count":424,"area":null},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393,"area":null},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2209.15616","title":"Towards Multi-spatiotemporal-scale Generalized PDE Modeling","created":"2022-09-30","cited_by_count":197,"area":null},{"id":"2306.15794","title":"HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution","created":"2023-06-27","cited_by_count":194,"area":null},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179,"area":null},{"id":"2203.06717","title":"Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs","created":"2022-03-13","cited_by_count":155,"area":null},{"id":"2207.03620","title":"More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity","created":"2022-07-07","cited_by_count":142,"area":null},{"id":"2209.12951","title":"Liquid Structural State-Space Models","created":"2022-09-26","cited_by_count":136,"area":null},{"id":"2403.01590","title":"The Hidden Attention of Mamba Models","created":"2024-03-03","cited_by_count":91,"area":"ssm"},{"id":"2210.09298","title":"What Makes Convolutional Models Great on Long Sequence Modeling?","created":"2022-10-17","cited_by_count":87,"area":null},{"id":"2402.15584","title":"State Space Models for Event Cameras","created":"2024-02-23","cited_by_count":75,"area":null},{"id":"2206.10555","title":"LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs","created":"2022-06-21","cited_by_count":72,"area":null},{"id":"2110.08059","title":"FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes","created":"2021-10-15","cited_by_count":66,"area":null},{"id":"2302.06646","title":"Simple Hardware-Efficient Long Convolutions for Sequence Modeling","created":"2023-02-13","cited_by_count":62,"area":null},{"id":"2302.03130","title":"Spatial Functa: Scaling Functa to ImageNet Classification and Generation","created":"2023-02-06","cited_by_count":57,"area":null},{"id":"2205.14623","title":"SKFlow: Learning Optical Flow with Super Kernels","created":"2022-05-29","cited_by_count":56,"area":null},{"id":"2404.15956","title":"A Survey on Visual Mamba","created":"2024-04-24","cited_by_count":50,"area":"ssm"},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2110.10211","title":"Learning Partial Equivariances from Data","created":"2021-10-19","cited_by_count":45,"area":null},{"id":"2407.09941","title":"Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers","created":"2024-07-13","cited_by_count":44,"area":"ssm"},{"id":"2204.07178","title":"Relaxing Equivariance Constraints with Non-stationary Continuous Filters","created":"2022-04-14","cited_by_count":41,"area":null},{"id":"2210.06583","title":"S4ND: Modeling Images and Videos as Multidimensional Signals Using State Spaces","created":"2022-10-12","cited_by_count":41,"area":null},{"id":"2310.02970","title":"Fast, Expressive SE$(n)$ Equivariant Networks through Weight-Sharing in Position-Orientation Space","created":"2023-10-04","cited_by_count":41,"area":null},{"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,"area":null},{"id":"2212.12749","title":"Deep Latent State Space Models for Time-Series Generation","created":"2022-12-24","cited_by_count":38,"area":"ssm"},{"id":"2407.19115","title":"Towards Scalable and Stable Parallelization of Nonlinear RNNs","created":"2024-07-26","cited_by_count":38,"area":null},{"id":"2311.05908","title":"FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores","created":"2023-11-10","cited_by_count":33,"area":null},{"id":"2402.14730","title":"Clifford-Steerable Convolutional Neural Networks","created":"2024-02-22","cited_by_count":25,"area":null},{"id":"2310.18780","title":"Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions","created":"2023-10-28","cited_by_count":24,"area":null},{"id":"2110.13059","title":"Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups","created":"2021-10-25","cited_by_count":22,"area":null},{"id":"2112.03740","title":"Dilated convolution with learnable spacings","created":"2021-12-07","cited_by_count":20,"area":null},{"id":"2310.00655","title":"PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting","created":"2023-10-01","cited_by_count":20,"area":null},{"id":"2305.01638","title":"Sequence Modeling with Multiresolution Convolutional Memory","created":"2023-05-02","cited_by_count":19,"area":null},{"id":"2504.05646","title":"Lattice: Learning to Efficiently Compress the Memory","created":"2025-04-08","cited_by_count":19,"area":null},{"id":"2301.10540","title":"Modelling Long Range Dependencies in $N$D: From Task-Specific to a General Purpose CNN","created":"2023-01-25","cited_by_count":18,"area":null},{"id":"2310.01698","title":"Robustifying State-space Models for Long Sequences via Approximate Diagonalization","created":"2023-10-02","cited_by_count":18,"area":null},{"id":"2405.06147","title":"State-Free Inference of State-Space Models: The Transfer Function Approach","created":"2024-05-10","cited_by_count":18,"area":null},{"id":"2410.02035","title":"Tuning Frequency Bias of State Space Models","created":"2024-10-02","cited_by_count":17,"area":null},{"id":"2206.03398","title":"Towards a General Purpose CNN for Long Range Dependencies in $N$D","created":"2022-06-07","cited_by_count":16,"area":null},{"id":"2405.20799","title":"Rough Transformers: Lightweight and Continuous Time Series Modelling through Signature Patching","created":"2024-05-31","cited_by_count":16,"area":null},{"id":"2404.07645","title":"Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videos","created":"2024-04-11","cited_by_count":13,"area":"ssm"},{"id":"2107.05050","title":"Neural Waveshaping Synthesis","created":"2021-07-11","cited_by_count":12,"area":null},{"id":"2305.14952","title":"Focus Your Attention (with Adaptive IIR Filters)","created":"2023-05-24","cited_by_count":12,"area":null},{"id":"2310.11366","title":"Lie Group Decompositions for Equivariant Neural Networks","created":"2023-10-17","cited_by_count":12,"area":null},{"id":"2503.01868","title":"Systems and Algorithms for Convolutional Multi-Hybrid Language Models at Scale","created":"2025-02-25","cited_by_count":12,"area":null},{"id":"2311.16620","title":"On the Long Range Abilities of Transformers","created":"2023-11-28","cited_by_count":10,"area":null},{"id":"2212.06096","title":"Implicit Convolutional Kernels for Steerable CNNs","created":"2022-12-12","cited_by_count":9,"area":null},{"id":"2204.00740","title":"Path Development Network with Finite-dimensional Lie Group Representation","created":"2022-04-02","cited_by_count":8,"area":null},{"id":"2210.06965","title":"CUF: Continuous Upsampling Filters","created":"2022-10-13","cited_by_count":8,"area":null},{"id":"2307.10001","title":"As large as it gets: Learning infinitely large Filters via Neural Implicit Functions in the Fourier Domain","created":"2023-07-19","cited_by_count":8,"area":null},{"id":"2401.03246","title":"SeqNAS: Neural Architecture Search for Event Sequence Classification","created":"2024-01-06","cited_by_count":8,"area":null},{"id":"2407.08972","title":"Revealing the Dark Secrets of Extremely Large Kernel ConvNets on Robustness","created":"2024-07-12","cited_by_count":8,"area":null},{"id":"2505.09022","title":"Block-Biased Mamba for Long-Range Sequence Processing","created":"2025-05-13","cited_by_count":8,"area":"ssm"},{"id":"2106.08928","title":"RNNs of RNNs: Recursive Construction of Stable Assemblies of Recurrent Neural Networks","created":"2021-06-16","cited_by_count":7,"area":null},{"id":"2411.17800","title":"STAR: Synthesis of Tailored Architectures","created":"2024-11-26","cited_by_count":7,"area":null},{"id":"2205.15254","title":"Pooling Revisited: Your Receptive Field is Suboptimal","created":"2022-05-30","cited_by_count":6,"area":null},{"id":"2211.05151","title":"QuadConv: Quadrature-Based Convolutions with Applications to Non-Uniform PDE Data Compression","created":"2022-11-09","cited_by_count":6,"area":null},{"id":"2304.02330","title":"SMPConv: Self-moving Point Representations for Continuous Convolution","created":"2023-04-05","cited_by_count":6,"area":null},{"id":"2306.14072","title":"Intensity-free Convolutional Temporal Point Process: Incorporating Local and Global Event Contexts","created":"2023-06-24","cited_by_count":6,"area":null},{"id":"2311.11587","title":"LDConv: Linear deformable convolution for improving convolutional neural networks","created":"2023-11-20","cited_by_count":6,"area":null},{"id":"2402.18508","title":"Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling","created":"2024-02-28","cited_by_count":6,"area":null},{"id":"2407.01049","title":"SE(3)-Hyena Operator for Scalable Equivariant Learning","created":"2024-07-01","cited_by_count":6,"area":null},{"id":"2508.02124","title":"Trainable Dynamic Mask Sparse Attention","created":"2025-08-04","cited_by_count":6,"area":null},{"id":"2305.06741","title":"IVP-VAE: Modeling EHR Time Series with Initial Value Problem Solvers","created":"2023-05-11","cited_by_count":5,"area":null},{"id":"2308.03210","title":"Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series","created":"2023-08-06","cited_by_count":5,"area":null},{"id":"2309.13600","title":"Multi-Dimensional Hyena for Spatial Inductive Bias","created":"2023-09-24","cited_by_count":5,"area":null},{"id":"2404.13604","title":"CKGConv: General Graph Convolution with Continuous Kernels","created":"2024-04-21","cited_by_count":5,"area":null},{"id":"2512.23852","title":"Trellis: Learning to Compress Key-Value Memory in Attention Models","created":"2025-12-29","cited_by_count":5,"area":null},{"id":"2302.05400","title":"DNArch: Learning Convolutional Neural Architectures by Backpropagation","created":"2023-02-10","cited_by_count":4,"area":null},{"id":"2306.00817","title":"Dilated Convolution with Learnable Spacings: beyond bilinear interpolation","created":"2023-06-01","cited_by_count":4,"area":null},{"id":"2306.16524","title":"Hyena Neural Operator for Partial Differential Equations","created":"2023-06-28","cited_by_count":4,"area":null},{"id":"2307.14680","title":"TimeGNN: Temporal Dynamic Graph Learning for Time Series Forecasting","created":"2023-07-27","cited_by_count":4,"area":null},{"id":"2404.13182","title":"Spectral Convolutional Conditional Neural Processes","created":"2024-04-19","cited_by_count":4,"area":null},{"id":"2405.12179","title":"PLEIADES: Building Temporal Kernels with Orthogonal Polynomials","created":"2024-05-20","cited_by_count":4,"area":null},{"id":"2406.12059","title":"A Scalable and Effective Alternative to Graph Transformers","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2502.18394","title":"SPECTRE: An FFT-Based Efficient Drop-In Replacement to Self-Attention for Long Contexts","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2505.22560","title":"Geometric Hyena Networks for Large-scale Equivariant Learning","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2307.00868","title":"MADS: Modulated Auto-Decoding SIREN for time series imputation","created":"2023-07-03","cited_by_count":3,"area":null},{"id":"2309.15812","title":"Convolutional Networks with Oriented 1D Kernels","created":"2023-09-27","cited_by_count":3,"area":null},{"id":"2410.04703","title":"Neural Fourier Modelling: A Highly Compact Approach to Time-Series Analysis","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2410.12982","title":"Flash Inference: Near Linear Time Inference for Long Convolution Sequence Models and Beyond","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2411.10649","title":"Deep Loss Convexification for Learning Iterative Models","created":"2024-11-16","cited_by_count":3,"area":null},{"id":"2508.20441","title":"Uncovering the Spectral Bias in Diagonal State Space Models","created":"2025-08-28","cited_by_count":3,"area":null},{"id":"2402.19305","title":"HyenaPixel: Global Image Context with Convolutions","created":"2024-02-29","cited_by_count":2,"area":null},{"id":"2408.09453","title":"Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling","created":"2024-08-18","cited_by_count":2,"area":null},{"id":"2509.20503","title":"Myosotis: structured computation for attention like layer","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2512.23824","title":"MS-SSM: A Multi-Scale State Space Model for Efficient Sequence Modeling","created":"2025-12-29","cited_by_count":2,"area":null},{"id":"2206.01178","title":"Discretization Invariant Networks for Learning Maps between Neural Fields","created":"2022-06-02","cited_by_count":1,"area":null},{"id":"2305.15385","title":"Behavior quantification as the missing link between fields: Tools for digital psychiatry and their role in the future of neurobiology","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2307.11462","title":"Improve Long-term Memory Learning Through Rescaling the Error Temporally","created":"2023-07-21","cited_by_count":1,"area":null},{"id":"2407.04271","title":"Variational Partial Group Convolutions for Input-Aware Partial Equivariance of Rotations and Color-Shifts","created":"2024-07-05","cited_by_count":1,"area":null},{"id":"2409.09875","title":"Scaling Continuous Kernels with Sparse Fourier Domain Learning","created":"2024-09-15","cited_by_count":1,"area":null},{"id":"2506.11305","title":"Don't Pay Attention","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2511.01704","title":"Learnable Fractional Reaction-Diffusion Dynamics for Under-Display ToF Imaging and Beyond","created":"2025-11-03","cited_by_count":1,"area":null}],"next_cursor":"100"}