{"total":171,"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":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788,"area":"ssm"},{"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":"2401.04722","title":"U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation","created":"2024-01-09","cited_by_count":419,"area":"ssm"},{"id":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408,"area":null},{"id":"2203.14343","title":"Diagonal State Spaces are as Effective as Structured State Spaces","created":"2022-03-27","cited_by_count":350,"area":"ssm"},{"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":"2303.03982","title":"Structured State Space Models for In-Context Reinforcement Learning","created":"2023-03-07","cited_by_count":111,"area":"ssm"},{"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":"2403.14520","title":"Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference","created":"2024-03-21","cited_by_count":97,"area":"mllm"},{"id":"2306.10574","title":"Score-based Data Assimilation","created":"2023-06-18","cited_by_count":96,"area":null},{"id":"2403.01590","title":"The Hidden Attention of Mamba Models","created":"2024-03-03","cited_by_count":91,"area":"ssm"},{"id":"2311.18257","title":"Diffusion Models Without Attention","created":"2023-11-30","cited_by_count":75,"area":"diffusion"},{"id":"2402.15584","title":"State Space Models for Event Cameras","created":"2024-02-23","cited_by_count":75,"area":null},{"id":"2402.19047","title":"Theoretical Foundations of Deep Selective State-Space Models","created":"2024-02-29","cited_by_count":74,"area":"ssm"},{"id":"2305.00624","title":"Diffusion Models for Time Series Applications: A Survey","created":"2023-05-01","cited_by_count":72,"area":"diffusion"},{"id":"2507.07955","title":"Dynamic Chunking for End-to-End Hierarchical Sequence Modeling","created":"2025-07-10","cited_by_count":72,"area":null},{"id":"2305.17209","title":"Functional Flow Matching","created":"2023-05-26","cited_by_count":67,"area":"diffusion"},{"id":"2404.18886","title":"A Survey on Diffusion Models for Time Series and Spatio-Temporal Data","created":"2024-04-29","cited_by_count":67,"area":"diffusion"},{"id":"2302.09746","title":"PriSTI: A Conditional Diffusion Framework for Spatiotemporal Imputation","created":"2023-02-20","cited_by_count":66,"area":"diffusion"},{"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":"2210.15228","title":"Solving Audio Inverse Problems with a Diffusion Model","created":"2022-10-27","cited_by_count":62,"area":"diffusion"},{"id":"2302.06646","title":"Simple Hardware-Efficient Long Convolutions for Sequence Modeling","created":"2023-02-13","cited_by_count":62,"area":null},{"id":"2401.13660","title":"MambaByte: Token-free Selective State Space Model","created":"2024-01-24","cited_by_count":59,"area":"ssm"},{"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":"2402.03170","title":"Is Mamba Capable of In-Context Learning?","created":"2024-02-05","cited_by_count":45,"area":"ssm"},{"id":"2407.09941","title":"Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers","created":"2024-07-13","cited_by_count":44,"area":"ssm"},{"id":"2501.04944","title":"MambaHSI: Spatial-Spectral Mamba for Hyperspectral Image Classification","created":"2025-01-09","cited_by_count":44,"area":"ssm"},{"id":"2410.19538","title":"Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series","created":"2024-10-25","cited_by_count":43,"area":"diffusion"},{"id":"2206.05408","title":"Multi-instrument Music Synthesis with Spectrogram Diffusion","created":"2022-06-11","cited_by_count":42,"area":"diffusion"},{"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":"2404.04478","title":"Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion Models","created":"2024-04-06","cited_by_count":41,"area":"diffusion"},{"id":"2402.04139","title":"U-shaped Vision Mamba for Single Image Dehazing","created":"2024-02-06","cited_by_count":40,"area":"ssm"},{"id":"2410.03943","title":"Oscillatory State-Space Models","created":"2024-10-04","cited_by_count":39,"area":null},{"id":"2412.16178","title":"Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHRs","created":"2024-12-09","cited_by_count":39,"area":"ssm"},{"id":"2212.12749","title":"Deep Latent State Space Models for Time-Series Generation","created":"2022-12-24","cited_by_count":38,"area":"ssm"},{"id":"2410.01201","title":"Were RNNs All We Needed?","created":"2024-10-02","cited_by_count":38,"area":null},{"id":"2203.16749","title":"SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping","created":"2022-03-31","cited_by_count":37,"area":"diffusion"},{"id":"2404.03646","title":"Locating and Editing Factual Associations in Mamba","created":"2024-04-04","cited_by_count":37,"area":"ssm"},{"id":"2406.03344","title":"Audio Mamba: Bidirectional State Space Model for Audio Representation Learning","created":"2024-06-05","cited_by_count":37,"area":"ssm"},{"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":"2410.09945","title":"Variational Diffusion Posterior Sampling with Midpoint Guidance","created":"2024-10-13","cited_by_count":32,"area":"diffusion"},{"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":"2307.02064","title":"Facing Off World Model Backbones: RNNs, Transformers, and S4","created":"2023-07-05","cited_by_count":31,"area":"wm"},{"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":"2211.11176","title":"Modeling Multivariate Biosignals With Graph Neural Networks and Structured State Space Models","created":"2022-11-21","cited_by_count":29,"area":"ssm"},{"id":"2410.13229","title":"Quamba: A Post-Training Quantization Recipe for Selective State Space Models","created":"2024-10-17","cited_by_count":28,"area":"ssm"},{"id":"2306.05167","title":"Decision S4: Efficient Sequence-Based RL via State Spaces Layers","created":"2023-06-08","cited_by_count":26,"area":"offlinerl"},{"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":"2401.03006","title":"The Rise of Diffusion Models in Time-Series Forecasting","created":"2024-01-05","cited_by_count":25,"area":"diffusion"},{"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":"2210.01029","title":"WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iteration","created":"2022-10-03","cited_by_count":20,"area":"diffusion"},{"id":"2406.16808","title":"Exploring the Capability of Mamba in Speech Applications","created":"2024-06-24","cited_by_count":20,"area":"ssm"},{"id":"2407.08132","title":"DMM: Disparity-guided Multispectral Mamba for Oriented Object Detection in Remote Sensing","created":"2024-07-11","cited_by_count":20,"area":"ssm"},{"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":"2501.00658","title":"Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing","created":"2024-12-31","cited_by_count":18,"area":"ssm"},{"id":"2406.12272","title":"Slot State Space Models","created":"2024-06-18","cited_by_count":17,"area":"ssm"},{"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":"2503.01113","title":"SCSegamba: Lightweight Structure-Aware Vision Mamba for Crack Segmentation in Structures","created":"2025-03-03","cited_by_count":16,"area":"ssm"},{"id":"2503.22879","title":"Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models","created":"2025-03-28","cited_by_count":16,"area":"ssm"},{"id":"2311.08667","title":"EDMSound: Spectrogram Based Diffusion Models for Efficient and High-Quality Audio Synthesis","created":"2023-11-15","cited_by_count":15,"area":"diffusion"},{"id":"2402.10211","title":"Hierarchical State Space Models for Continuous Sequence-to-Sequence Modeling","created":"2024-02-15","cited_by_count":15,"area":"ssm"},{"id":"2405.05007","title":"HC-Mamba: Vision MAMBA with Hybrid Convolutional Techniques for Medical Image Segmentation","created":"2024-05-08","cited_by_count":15,"area":"ssm"},{"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":"2311.12850","title":"PrivImage: Differentially Private Synthetic Image Generation using Diffusion Models with Semantic-Aware Pretraining","created":"2023-10-19","cited_by_count":13,"area":"diffusion"},{"id":"2402.06378","title":"FD-Vision Mamba for Endoscopic Exposure Correction","created":"2024-02-09","cited_by_count":13,"area":"ssm"},{"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":"2407.08751","title":"Latent Diffusion for Neural Spiking Data","created":"2024-06-27","cited_by_count":12,"area":"diffusion"},{"id":"2210.17098","title":"Structured State Space Decoder for Speech Recognition and Synthesis","created":"2022-10-31","cited_by_count":11,"area":"ssm"},{"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":"2304.12776","title":"State Spaces Aren't Enough: Machine Translation Needs Attention","created":"2023-04-25","cited_by_count":9,"area":"ssm"},{"id":"2306.00331","title":"A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Models","created":"2023-06-01","cited_by_count":9,"area":"ssm"},{"id":"2409.09337","title":"Wave-U-Mamba: An End-To-End Framework For High-Quality And Efficient Speech Super Resolution","created":"2024-09-14","cited_by_count":9,"area":"ssm"},{"id":"2411.02941","title":"A Mamba Foundation Model for Time Series Forecasting","created":"2024-11-05","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":"2508.19029","title":"Revisiting associative recall in modern recurrent models","created":"2025-08-26","cited_by_count":8,"area":null}],"next_cursor":"100"}