{"total":95,"rows":[{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673,"area":null},{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687,"area":null},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499,"area":null},{"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":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408,"area":null},{"id":"2402.19427","title":"Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models","created":"2024-02-29","cited_by_count":242,"area":null},{"id":"2208.09399","title":"Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models","created":"2022-08-19","cited_by_count":198,"area":null},{"id":"2204.01692","title":"Long Movie Clip Classification with State-Space Video Models","created":"2022-04-04","cited_by_count":106,"area":null},{"id":"2312.03701","title":"Return of Unconditional Generation: A Self-supervised Representation Generation Method","created":"2023-12-06","cited_by_count":98,"area":null},{"id":"2306.10574","title":"Score-based Data Assimilation","created":"2023-06-18","cited_by_count":96,"area":null},{"id":"2402.15584","title":"State Space Models for Event Cameras","created":"2024-02-23","cited_by_count":75,"area":null},{"id":"2507.07955","title":"Dynamic Chunking for End-to-End Hierarchical Sequence Modeling","created":"2025-07-10","cited_by_count":72,"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":"2404.09516","title":"State Space Model for New-Generation Network Alternative to Transformers: A Survey","created":"2024-04-15","cited_by_count":59,"area":null},{"id":"2301.12662","title":"SingSong: Generating musical accompaniments from singing","created":"2023-01-30","cited_by_count":55,"area":null},{"id":"2303.09489","title":"Effectively Modeling Time Series with Simple Discrete State Spaces","created":"2023-03-16","cited_by_count":54,"area":null},{"id":"2305.12403","title":"Spatio-temporal Diffusion Point Processes","created":"2023-05-21","cited_by_count":52,"area":null},{"id":"2212.10544","title":"Pretraining Without Attention","created":"2022-12-20","cited_by_count":51,"area":null},{"id":"2212.14427","title":"Efficient Movie Scene Detection using State-Space Transformers","created":"2022-12-29","cited_by_count":51,"area":null},{"id":"2306.03509","title":"Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias","created":"2023-06-06","cited_by_count":51,"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":"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":"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,"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":"2507.11783","title":"EEG Foundation Models: A Critical Review of Current Progress and Future Directions","created":"2025-07-15","cited_by_count":32,"area":null},{"id":"2404.18508","title":"Scalable Event-by-event Processing of Neuromorphic Sensory Signals With Deep State-Space Models","created":"2024-04-29","cited_by_count":31,"area":null},{"id":"2405.15731","title":"Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks","created":"2024-05-24","cited_by_count":26,"area":null},{"id":"2409.07437","title":"Salmon: A Suite for Acoustic Language Model Evaluation","created":"2024-09-11","cited_by_count":24,"area":null},{"id":"2212.00768","title":"Simplifying and Understanding State Space Models with Diagonal Linear RNNs","created":"2022-12-01","cited_by_count":23,"area":null},{"id":"2302.08105","title":"A Neural PDE Solver with Temporal Stencil Modeling","created":"2023-02-16","cited_by_count":22,"area":null},{"id":"2312.06837","title":"Spectral State Space Models","created":"2023-12-11","cited_by_count":21,"area":null},{"id":"2403.16899","title":"State Space Models as Foundation Models: A Control Theoretic Overview","created":"2024-03-25","cited_by_count":19,"area":null},{"id":"2405.16674","title":"Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theory","created":"2024-05-26","cited_by_count":19,"area":null},{"id":"2412.18603","title":"Long-Form Speech Generation with Spoken Language Models","created":"2024-12-24","cited_by_count":19,"area":null},{"id":"2306.06635","title":"2-D SSM: A General Spatial Layer for Visual Transformers","created":"2023-06-11","cited_by_count":18,"area":null},{"id":"2204.05133","title":"On the link between conscious function and general intelligence in humans and machines","created":"2022-03-24","cited_by_count":16,"area":null},{"id":"2207.05543","title":"Markovian Gaussian Process Variational Autoencoders","created":"2022-07-12","cited_by_count":16,"area":null},{"id":"2305.12498","title":"Multi-Head State Space Model for Speech Recognition","created":"2023-05-21","cited_by_count":14,"area":null},{"id":"2305.19534","title":"Recasting Self-Attention with Holographic Reduced Representations","created":"2023-05-31","cited_by_count":14,"area":null},{"id":"2305.14952","title":"Focus Your Attention (with Adaptive IIR Filters)","created":"2023-05-24","cited_by_count":12,"area":null},{"id":"2310.01853","title":"Score-based Data Assimilation for a Two-Layer Quasi-Geostrophic Model","created":"2023-10-03","cited_by_count":12,"area":null},{"id":"2312.01538","title":"Recurrent Distance Filtering for Graph Representation Learning","created":"2023-12-03","cited_by_count":11,"area":null},{"id":"2405.02670","title":"From Generalization Analysis to Optimization Designs for State Space Models","created":"2024-05-04","cited_by_count":11,"area":null},{"id":"2412.19634","title":"Deep Continuous-Time State-Space Models for Marked Event Sequences","created":"2024-12-27","cited_by_count":11,"area":null},{"id":"2209.14458","title":"The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling","created":"2022-09-28","cited_by_count":10,"area":null},{"id":"2411.02824","title":"Layer-Adaptive State Pruning for Deep State Space Models","created":"2024-11-05","cited_by_count":10,"area":null},{"id":"2505.12171","title":"Learning to Dissipate Energy in Oscillatory State-Space Models","created":"2025-05-17","cited_by_count":9,"area":null},{"id":"2508.19029","title":"Revisiting associative recall in modern recurrent models","created":"2025-08-26","cited_by_count":8,"area":null},{"id":"2508.16817","title":"Predictability Enables Parallelization of Nonlinear State Space Models","created":"2025-08-22","cited_by_count":7,"area":null},{"id":"2305.16932","title":"A Neural State-Space Model Approach to Efficient Speech Separation","created":"2023-05-26","cited_by_count":6,"area":null},{"id":"2405.19036","title":"State Space Models are Provably Comparable to Transformers in Dynamic Token Selection","created":"2024-05-29","cited_by_count":6,"area":null},{"id":"2311.15890","title":"Stability-Informed Initialization of Neural Ordinary Differential Equations","created":"2023-11-27","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":"2307.01673","title":"Disentanglement in a GAN for Unconditional Speech Synthesis","created":"2023-07-04","cited_by_count":4,"area":null},{"id":"2406.05532","title":"Exploring Adversarial Robustness of Deep State Space Models","created":"2024-06-08","cited_by_count":4,"area":null},{"id":"2504.00719","title":"Scaling Up Resonate-and-Fire Networks for Fast Deep Learning","created":"2025-04-01","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":"2206.03331","title":"Improving the Diagnosis of Psychiatric Disorders with Self-Supervised Graph State Space Models","created":"2022-06-07","cited_by_count":3,"area":null},{"id":"2206.06811","title":"Adversarial Audio Synthesis with Complex-valued Polynomial Networks","created":"2022-06-14","cited_by_count":3,"area":null},{"id":"2210.13944","title":"A Survey on Artificial Intelligence for Music Generation: Agents, Domains and Perspectives","created":"2022-10-25","cited_by_count":3,"area":null},{"id":"2306.09780","title":"Understanding Deep Generative Models with Generalized Empirical Likelihoods","created":"2023-06-16","cited_by_count":3,"area":null},{"id":"2312.05550","title":"D3A-TS: Denoising-Driven Data Augmentation in Time Series","created":"2023-12-09","cited_by_count":3,"area":null},{"id":"2406.04342","title":"Learning 1D Causal Visual Representation with De-focus Attention Networks","created":"2024-06-06","cited_by_count":3,"area":null},{"id":"2409.11299","title":"TTT-Unet: Enhancing U-Net with Test-Time Training Layers for Biomedical Image Segmentation","created":"2024-09-17","cited_by_count":3,"area":null},{"id":"2502.01330","title":"Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity","created":"2025-02-03","cited_by_count":3,"area":null},{"id":"2303.06475","title":"Transcription free filler word detection with Neural semi-CRFs","created":"2023-03-11","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":"2509.20503","title":"Myosotis: structured computation for attention like layer","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2510.15366","title":"Sequence Modeling with Spectral Mean Flows","created":"2025-10-17","cited_by_count":2,"area":null},{"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":"2512.11411","title":"Sliced ReLU attention: Quasi-linear contextual expressivity via sorting","created":"2025-12-12","cited_by_count":2,"area":null},{"id":"2205.11989","title":"Realization Theory Of Recurrent Neural ODEs Using Polynomial System Embeddings","created":"2022-05-24","cited_by_count":1,"area":null},{"id":"2307.00461","title":"Conformer LLMs -- Convolution Augmented Large Language Models","created":"2023-07-02","cited_by_count":1,"area":null},{"id":"2405.19653","title":"SysCaps: Language Interfaces for Simulation Surrogates of Complex Systems","created":"2024-05-30","cited_by_count":1,"area":null},{"id":"2409.12924","title":"Wavelet GPT: Wavelet Inspired Large Language Models","created":"2024-09-04","cited_by_count":1,"area":null},{"id":"2409.18705","title":"Speech Boosting: Low-Latency Live Speech Enhancement for TWS Earbuds","created":"2024-09-27","cited_by_count":1,"area":null},{"id":"2412.08595","title":"Numerical Analysis of HiPPO-LegS ODE for Deep State Space Models","created":"2024-12-11","cited_by_count":1,"area":null},{"id":"2503.02714","title":"S4D-Bio Audio Monitoring of Bone Cement Disintegration in Pulsating Fluid Jet Surgery under Laboratory Conditions","created":"2025-03-04","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":"2506.19296","title":"The Effect of Depth on the Expressivity of Deep Linear State-Space Models","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2602.21340","title":"HiPPO Zoo: Explicit Memory Mechanisms for Interpretable State Space Models","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2603.02874","title":"Retrievit: In-context Retrieval Capabilities of Transformers, State Space Models, and Hybrid Architectures","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2404.11576","title":"State-space Decomposition Model for Video Prediction Considering Long-term Motion Trend","created":"2024-04-17","cited_by_count":0,"area":null},{"id":"2407.19201","title":"Long Range Switching Time Series Prediction via State Space Model","created":"2024-07-27","cited_by_count":0,"area":null},{"id":"2409.03377","title":"aTENNuate: Optimized Real-time Speech Enhancement with Deep SSMs on Raw Audio","created":"2024-09-05","cited_by_count":0,"area":null},{"id":"2503.18462","title":"PALATE: Peculiar Application of the Law of Total Expectation to Enhance the Evaluation of Deep Generative Models","created":"2025-03-24","cited_by_count":0,"area":null},{"id":"2505.14206","title":"Challenges and Limitations of Generative AI in Synthesizing Wearable Sensor Data","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2510.02206","title":"Poolformer: Recurrent Networks with Pooling for Long-Sequence Modeling","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2510.02401","title":"Linear RNNs for autoregressive generation of long music samples","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2510.15371","title":"Cortical-SSM: A Deep State Space Model for Motor Imagery Decoding from EEG Signals","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2511.01868","title":"Condition-Invariant fMRI Decoding of Speech Intelligibility with Deep State Space Model","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2603.08683","title":"Benchmarking Language Modeling for Lossless Compression of Full-Fidelity Audio","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.19198","title":"Extending SSMs with the Exponentially Weighted Signature","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2609.16710","title":"Continuous-Time Machine Learning: A Unified Mathematical Perspective","created":"2026-09-15","cited_by_count":0,"area":null}],"next_cursor":null}