{"total":51,"rows":[{"id":"2312.06635","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","created":"2023-12-11","cited_by_count":514,"area":"ssm"},{"id":"2406.06484","title":"Parallelizing Linear Transformers with the Delta Rule over Sequence Length","created":"2024-06-10","cited_by_count":396,"area":null},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328,"area":"ssm"},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"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":"2404.07904","title":"HGRN2: Gated Linear RNNs with State Expansion","created":"2024-04-11","cited_by_count":127,"area":null},{"id":"2408.15237","title":"The Mamba in the Llama: Distilling and Accelerating Hybrid Models","created":"2024-08-27","cited_by_count":122,"area":"ssm"},{"id":"2403.03234","title":"Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling","created":"2024-03-05","cited_by_count":113,"area":null},{"id":"2403.07487","title":"Motion Mamba: Efficient and Long Sequence Motion Generation","created":"2024-03-12","cited_by_count":112,"area":"ssm"},{"id":"2311.04823","title":"Hierarchically Gated Recurrent Neural Network for Sequence Modeling","created":"2023-11-08","cited_by_count":102,"area":null},{"id":"2403.13802","title":"ZigMa: A DiT-style Zigzag Mamba Diffusion Model","created":"2024-03-20","cited_by_count":84,"area":"diffusion"},{"id":"2311.18257","title":"Diffusion Models Without Attention","created":"2023-11-30","cited_by_count":75,"area":"diffusion"},{"id":"2402.19047","title":"Theoretical Foundations of Deep Selective State-Space Models","created":"2024-02-29","cited_by_count":74,"area":"ssm"},{"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":"2407.14207","title":"Longhorn: State Space Models are Amortized Online Learners","created":"2024-07-19","cited_by_count":59,"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":"2403.19888","title":"MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection","created":"2024-03-29","cited_by_count":40,"area":"ssm"},{"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":"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":"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":"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":"2403.07711","title":"SSM Meets Video Diffusion Models: Efficient Long-Term Video Generation with Structured State Spaces","created":"2024-03-12","cited_by_count":13,"area":"diffusion"},{"id":"2405.18425","title":"ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention","created":"2024-05-28","cited_by_count":13,"area":null},{"id":"2305.14952","title":"Focus Your Attention (with Adaptive IIR Filters)","created":"2023-05-24","cited_by_count":12,"area":null},{"id":"2305.19370","title":"Blockwise Parallel Transformer for Large Context Models","created":"2023-05-30","cited_by_count":12,"area":null},{"id":"2405.16504","title":"Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation","created":"2024-05-26","cited_by_count":11,"area":"ssm"},{"id":"2311.16620","title":"On the Long Range Abilities of Transformers","created":"2023-11-28","cited_by_count":10,"area":null},{"id":"2411.02941","title":"A Mamba Foundation Model for Time Series Forecasting","created":"2024-11-05","cited_by_count":9,"area":"ssm"},{"id":"2401.17919","title":"LOCOST: State-Space Models for Long Document Abstractive Summarization","created":"2024-01-31","cited_by_count":8,"area":null},{"id":"2406.04320","title":"Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models","created":"2024-06-06","cited_by_count":8,"area":"ssm"},{"id":"2403.17902","title":"Serpent: Scalable and Efficient Image Restoration via Multi-scale Structured State Space Models","created":"2024-03-26","cited_by_count":7,"area":"ssm"},{"id":"2407.06136","title":"Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning","created":"2024-07-08","cited_by_count":7,"area":"ssm"},{"id":"2502.14892","title":"EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild","created":"2025-02-17","cited_by_count":7,"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":"2404.10880","title":"HumMUSS: Human Motion Understanding using State Space Models","created":"2024-04-16","cited_by_count":6,"area":null},{"id":"2309.13600","title":"Multi-Dimensional Hyena for Spatial Inductive Bias","created":"2023-09-24","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":"2410.10473","title":"The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels","created":"2024-10-14","cited_by_count":3,"area":"ssm"},{"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":"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":"2401.06762","title":"Seeing the roads through the trees: A benchmark for modeling spatial dependencies with aerial imagery","created":"2024-01-12","cited_by_count":1,"area":null},{"id":"2403.10696","title":"On the low-shot transferability of [V]-Mamba","created":"2024-03-15","cited_by_count":1,"area":"ssm"},{"id":"2406.16722","title":"Venturing into Uncharted Waters: The Navigation Compass from Transformer to Mamba","created":"2024-06-24","cited_by_count":1,"area":"ssm"},{"id":"2506.15976","title":"LBMamba: Locally Bi-directional Mamba","created":"2025-06-19","cited_by_count":1,"area":"ssm"},{"id":"2510.09389","title":"Design Principles for Sequence Models via Coefficient Dynamics","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2602.06774","title":"Towards Understanding What State Space Models Learn About Code","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2504.08964","title":"Bidirectional Linear Recurrent Models for Sequence-Level Multisource Fusion","created":"2025-04-11","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}