{"total":136,"rows":[{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969,"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":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408,"area":null},{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328,"area":"lr"},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2404.08819","title":"The Illusion of State in State-Space Models","created":"2024-04-12","cited_by_count":187,"area":null},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2311.04823","title":"Hierarchically Gated Recurrent Neural Network for Sequence Modeling","created":"2023-11-08","cited_by_count":102,"area":null},{"id":"2404.02668","title":"RS-Mamba for Large Remote Sensing Image Dense Prediction","created":"2024-04-03","cited_by_count":81,"area":"ssm"},{"id":"2403.06467","title":"Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategy","created":"2024-03-11","cited_by_count":73,"area":"ssm"},{"id":"2512.24695","title":"Nested Learning: The Illusion of Deep Learning Architectures","created":"2025-12-31","cited_by_count":72,"area":null},{"id":"2505.23735","title":"ATLAS: Learning to Optimally Memorize the Context at Test Time","created":"2025-05-29","cited_by_count":66,"area":null},{"id":"2404.16112","title":"Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challenges","created":"2024-04-24","cited_by_count":64,"area":"ssm"},{"id":"2504.13173","title":"It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization","created":"2025-04-17","cited_by_count":64,"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":"2412.10319","title":"SCBench: A KV Cache-Centric Analysis of Long-Context Methods","created":"2024-12-13","cited_by_count":60,"area":"inference"},{"id":"2405.03349","title":"Retinexmamba: Retinex-based Mamba for Low-light Image Enhancement","created":"2024-05-06","cited_by_count":59,"area":"ssm"},{"id":"2302.06755","title":"Dataset Distillation with Convexified Implicit Gradients","created":"2023-02-13","cited_by_count":46,"area":null},{"id":"2403.09471","title":"MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models","created":"2024-03-14","cited_by_count":46,"area":"ssm"},{"id":"2309.12252","title":"Parallelizing non-linear sequential models over the sequence length","created":"2023-09-21","cited_by_count":45,"area":null},{"id":"2402.05608","title":"Scalable Diffusion Models with State Space Backbone","created":"2024-02-08","cited_by_count":45,"area":"diffusion"},{"id":"2410.03943","title":"Oscillatory State-Space Models","created":"2024-10-04","cited_by_count":39,"area":null},{"id":"2410.01201","title":"Were RNNs All We Needed?","created":"2024-10-02","cited_by_count":38,"area":null},{"id":"2410.20399","title":"ThunderKittens: Simple, Fast, and Adorable AI Kernels","created":"2024-10-27","cited_by_count":36,"area":null},{"id":"2403.16536","title":"VMRNN: Integrating Vision Mamba and LSTM for Efficient and Accurate Spatiotemporal Forecasting","created":"2024-03-25","cited_by_count":35,"area":"ssm"},{"id":"2311.05908","title":"FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores","created":"2023-11-10","cited_by_count":33,"area":null},{"id":"2407.06324","title":"B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory","created":"2024-07-08","cited_by_count":26,"area":null},{"id":"2402.07440","title":"Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT","created":"2024-02-12","cited_by_count":21,"area":null},{"id":"2411.10741","title":"MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map","created":"2024-11-16","cited_by_count":21,"area":null},{"id":"2306.11197","title":"Sparse Modular Activation for Efficient Sequence Modeling","created":"2023-06-19","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":"2401.00955","title":"Learning Long Sequences in Spiking Neural Networks","created":"2023-12-14","cited_by_count":19,"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":"2504.02542","title":"Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation","created":"2025-04-03","cited_by_count":17,"area":"diffusion"},{"id":"2404.11375","title":"Text-controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motion","created":"2024-04-17","cited_by_count":16,"area":"ssm"},{"id":"2509.22284","title":"Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models","created":"2025-09-26","cited_by_count":16,"area":null},{"id":"2406.18950","title":"MMR-Mamba: Multi-Modal MRI Reconstruction with Mamba and Spatial-Frequency Information Fusion","created":"2024-06-27","cited_by_count":15,"area":"ssm"},{"id":"2407.13772","title":"GroupMamba: Efficient Group-Based Visual State Space Model","created":"2024-07-18","cited_by_count":15,"area":"ssm"},{"id":"2411.17473","title":"TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba","created":"2024-11-26","cited_by_count":15,"area":"ssm"},{"id":"2503.24065","title":"COSMO: Combination of Selective Memorization for Low-cost Vision-and-Language Navigation","created":"2025-03-31","cited_by_count":15,"area":"ssm"},{"id":"2309.07412","title":"Advancing Regular Language Reasoning in Linear Recurrent Neural Networks","created":"2023-09-14","cited_by_count":13,"area":null},{"id":"2406.02395","title":"GrootVL: Tree Topology is All You Need in State Space Model","created":"2024-06-04","cited_by_count":13,"area":null},{"id":"2406.05815","title":"What Can We Learn from State Space Models for Machine Learning on Graphs?","created":"2024-06-09","cited_by_count":13,"area":null},{"id":"2405.13975","title":"HOPE for a Robust Parameterization of Long-memory State Space Models","created":"2024-05-22","cited_by_count":12,"area":null},{"id":"2210.04763","title":"On the Forward Invariance of Neural ODEs","created":"2022-10-10","cited_by_count":11,"area":null},{"id":"2305.16543","title":"Revisiting Structured Variational Autoencoders","created":"2023-05-25","cited_by_count":11,"area":null},{"id":"2312.01538","title":"Recurrent Distance Filtering for Graph Representation Learning","created":"2023-12-03","cited_by_count":11,"area":null},{"id":"2406.08234","title":"MaIL: Improving Imitation Learning with Mamba","created":"2024-06-12","cited_by_count":11,"area":"ssm"},{"id":"2508.04022","title":"Prototype-Driven Structure Synergy Network for Remote Sensing Images Segmentation","created":"2025-08-06","cited_by_count":11,"area":null},{"id":"2311.16620","title":"On the Long Range Abilities of Transformers","created":"2023-11-28","cited_by_count":10,"area":null},{"id":"2503.04953","title":"Spectral Informed Mamba for Robust Point Cloud Processing","created":"2025-03-06","cited_by_count":10,"area":"ssm"},{"id":"2505.21717","title":"Parallelization of Non-linear State-Space Models: Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence Modeling","created":"2025-05-27","cited_by_count":10,"area":"ssm"},{"id":"2305.01429","title":"Unsupervised Feature Based Algorithms for Time Series Extrinsic Regression","created":"2023-05-02","cited_by_count":9,"area":null},{"id":"2406.15131","title":"KalMamba: Towards Efficient Probabilistic State Space Models for RL under Uncertainty","created":"2024-06-21","cited_by_count":9,"area":"deeprl"},{"id":"2503.18970","title":"Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State-Space Architectures from S4 to Mamba","created":"2025-03-22","cited_by_count":9,"area":"ssm"},{"id":"2505.12171","title":"Learning to Dissipate Energy in Oscillatory State-Space Models","created":"2025-05-17","cited_by_count":9,"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":"2511.07343","title":"TNT: Improving Chunkwise Training for Test-Time Memorization","created":"2025-11-10","cited_by_count":8,"area":null},{"id":"2406.09833","title":"SHMamba: Structured Hyperbolic State Space Model for Audio-Visual Question Answering","created":"2024-06-14","cited_by_count":7,"area":null},{"id":"2604.21100","title":"Preconditioned DeltaNet: Curvature-aware Sequence Modeling for Linear Recurrences","created":"2026-04-22","cited_by_count":7,"area":null},{"id":"2407.05591","title":"On the Power of Convolution Augmented Transformer","created":"2024-07-08","cited_by_count":6,"area":null},{"id":"2407.07239","title":"RotRNN: Modelling Long Sequences with Rotations","created":"2024-07-09","cited_by_count":6,"area":null},{"id":"2409.15022","title":"A Diagonal Structured State Space Model on Loihi 2 for Efficient Streaming Sequence Processing","created":"2024-09-23","cited_by_count":6,"area":"ssm"},{"id":"2505.08299","title":"Efficient Unstructured Pruning of Mamba State-Space Models for Resource-Constrained Environments","created":"2025-05-13","cited_by_count":6,"area":"ssm"},{"id":"2210.04303","title":"Are All Vision Models Created Equal? A Study of the Open-Loop to Closed-Loop Causality Gap","created":"2022-10-09","cited_by_count":5,"area":null},{"id":"2212.00228","title":"Gated Recurrent Neural Networks with Weighted Time-Delay Feedback","created":"2022-12-01","cited_by_count":5,"area":null},{"id":"2311.04449","title":"Recursion in Recursion: Two-Level Nested Recursion for Length Generalization with Scalability","created":"2023-11-08","cited_by_count":5,"area":null},{"id":"2406.08128","title":"Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences","created":"2024-06-12","cited_by_count":5,"area":null},{"id":"2407.07279","title":"Towards a theory of learning dynamics in deep state space models","created":"2024-07-10","cited_by_count":5,"area":null},{"id":"2506.07919","title":"Uncovering the Computational Roles of Nonlinearity in Sequence Modeling Using Almost-Linear RNNs","created":"2025-06-09","cited_by_count":5,"area":null},{"id":"2404.11163","title":"LongVQ: Long Sequence Modeling with Vector Quantization on Structured Memory","created":"2024-04-17","cited_by_count":4,"area":null},{"id":"2510.02823","title":"The Curious Case of In-Training Compression of State Space Models","created":"2025-10-03","cited_by_count":4,"area":null},{"id":"2409.02684","title":"Neural timescales from a computational perspective","created":"2024-09-04","cited_by_count":3,"area":null},{"id":"2501.14980","title":"A Deep State Space Model for Rainfall-Runoff Simulations","created":"2025-01-24","cited_by_count":3,"area":null},{"id":"2502.00466","title":"EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling","created":"2025-02-01","cited_by_count":3,"area":"wm"},{"id":"2505.08977","title":"SaFARi: State-Space Models for Frame-Agnostic Representation","created":"2025-05-13","cited_by_count":3,"area":null},{"id":"2506.21330","title":"Holistic Surgical Phase Recognition with Hierarchical Input Dependent State Space Models","created":"2025-06-26","cited_by_count":3,"area":null},{"id":"2507.01384","title":"MUG: Pseudo Labeling Augmented Audio-Visual Mamba Network for Audio-Visual Video Parsing","created":"2025-07-02","cited_by_count":3,"area":"ssm"},{"id":"2508.20441","title":"Uncovering the Spectral Bias in Diagonal State Space Models","created":"2025-08-28","cited_by_count":3,"area":null},{"id":"2510.07578","title":"Accuracy, Memory Efficiency and Generalization: A Comparative Study on Liquid Neural Networks and Recurrent Neural Networks","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2601.18064","title":"Resonant Sparse Geometry Networks","created":"2026-01-26","cited_by_count":3,"area":null},{"id":"2407.09553","title":"DPEC: Dual-Path Error Compensation Method for Enhanced Low-Light Image Clarity","created":"2024-06-28","cited_by_count":2,"area":null},{"id":"2408.08567","title":"S$^3$Attention: Improving Long Sequence Attention with Smoothed Skeleton Sketching","created":"2024-08-16","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":"2501.13230","title":"Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions","created":"2025-01-22","cited_by_count":2,"area":null},{"id":"2503.11224","title":"Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2504.10669","title":"Perturbed State Space Feature Encoders for Optical Flow with Event Cameras","created":"2025-04-14","cited_by_count":2,"area":null},{"id":"2506.03084","title":"InterMamba: Efficient Human-Human Interaction Generation with Adaptive Spatio-Temporal Mamba","created":"2025-06-03","cited_by_count":2,"area":"ssm"},{"id":"2509.20503","title":"Myosotis: structured computation for attention like layer","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2510.14027","title":"Context-Selective State Space Models: Feedback is All You Need","created":"2025-10-15","cited_by_count":2,"area":"ssm"},{"id":"2510.22951","title":"Hankel Singular Value Regularization for Highly Compressible State Space Models","created":"2025-10-27","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":"2601.19467","title":"On the Expressiveness of State Space Models via Temporal Logics","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2606.22801","title":"Learning Adaptive Dynamical Features via Multi-$\\tau$ Liquid-Mamba for All-in-one Image Restoration","created":"2026-06-22","cited_by_count":2,"area":"ssm"},{"id":"2606.23670","title":"Tapered Language Models","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2210.06650","title":"Interpreting Neural Policies with Disentangled Tree Representations","created":"2022-10-13","cited_by_count":1,"area":null},{"id":"2404.05210","title":"Bidirectional Long-Range Parser for Sequential Data Understanding","created":"2024-04-08","cited_by_count":1,"area":null},{"id":"2411.19544","title":"SkelMamba: A State Space Model for Efficient Skeleton Action Recognition of Neurological Disorders","created":"2024-11-29","cited_by_count":1,"area":null}],"next_cursor":"100"}