{"total":47,"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":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336,"area":"ssm"},{"id":"2312.06635","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","created":"2023-12-11","cited_by_count":514,"area":"ssm"},{"id":"2403.17695","title":"PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition","created":"2024-03-26","cited_by_count":141,"area":"ssm"},{"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":"2403.09626","title":"Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding","created":"2024-03-14","cited_by_count":108,"area":"ssm"},{"id":"2402.04248","title":"Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks","created":"2024-02-06","cited_by_count":105,"area":"ssm"},{"id":"2408.10189","title":"Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models","created":"2024-08-19","cited_by_count":67,"area":"ssm"},{"id":"2407.14207","title":"Longhorn: State Space Models are Amortized Online Learners","created":"2024-07-19","cited_by_count":59,"area":"ssm"},{"id":"2402.03170","title":"Is Mamba Capable of In-Context Learning?","created":"2024-02-05","cited_by_count":45,"area":"ssm"},{"id":"2404.18861","title":"Visual Mamba: A Survey and New Outlooks","created":"2024-04-29","cited_by_count":41,"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":"2408.12245","title":"Scalable Autoregressive Image Generation with Mamba","created":"2024-08-22","cited_by_count":26,"area":"ssm"},{"id":"2410.02362","title":"A Comprehensive Survey of Mamba Architectures for Medical Image Analysis: Classification, Segmentation, Restoration and Beyond","created":"2024-10-03","cited_by_count":16,"area":"ssm"},{"id":"2403.18276","title":"RankMamba: Benchmarking Mamba's Document Ranking Performance in the Era of Transformers","created":"2024-03-27","cited_by_count":15,"area":"ssm"},{"id":"2411.11843","title":"Bi-Mamba: Towards Accurate 1-Bit State Space Models","created":"2024-11-18","cited_by_count":12,"area":"ssm"},{"id":"2502.15260","title":"LightMamba: Efficient Mamba Acceleration on FPGA with Quantization and Hardware Co-design","created":"2025-02-21","cited_by_count":11,"area":"ssm"},{"id":"2412.20386","title":"PTQ4VM: Post-Training Quantization for Visual Mamba","created":"2024-12-29","cited_by_count":10,"area":"ssm"},{"id":"2410.07599","title":"Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency","created":"2024-10-10","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":"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":"2409.19937","title":"MaskMamba: A Hybrid Mamba-Transformer Model for Masked Image Generation","created":"2024-09-30","cited_by_count":8,"area":"ssm"},{"id":"2503.24067","title":"TransMamba: A Sequence-Level Hybrid Transformer-Mamba Language Model","created":"2025-03-31","cited_by_count":7,"area":"ssm"},{"id":"2407.05489","title":"How Effective are State Space Models for Machine Translation?","created":"2024-07-07","cited_by_count":6,"area":"ssm"},{"id":"2506.09613","title":"SparseSSM: Efficient Selective Structured State Space Models Can Be Pruned in One-Shot","created":"2025-06-11","cited_by_count":5,"area":"ssm"},{"id":"2410.18572","title":"Taipan: Efficient and Expressive State Space Language Models with Selective Attention","created":"2024-10-24","cited_by_count":4,"area":"ssm"},{"id":"2411.15224","title":"Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation","created":"2024-11-21","cited_by_count":4,"area":"ssm"},{"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":"2410.15678","title":"Revealing and Mitigating the Local Pattern Shortcuts of Mamba","created":"2024-10-21","cited_by_count":3,"area":"ssm"},{"id":"2504.20922","title":"DYNAMAX: Dynamic computing for Transformers and Mamba based architectures","created":"2025-04-29","cited_by_count":3,"area":"ssm"},{"id":"2509.17514","title":"Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data","created":"2025-09-22","cited_by_count":3,"area":"ssm"},{"id":"2510.04595","title":"SpikingMamba: Towards Energy-Efficient Large Language Models via Knowledge Distillation from Mamba","created":"2025-10-06","cited_by_count":3,"area":"ssm"},{"id":"2602.12499","title":"A Theoretical Analysis of Mamba's Training Dynamics: Filtering Relevant Features for Generalization in State Space Models","created":"2026-02-13","cited_by_count":3,"area":"ssm"},{"id":"2408.00244","title":"Enhanced Structured State Space Models via Grouped FIR Filtering and Attention Sink Mechanisms","created":"2024-08-01","cited_by_count":2,"area":"ssm"},{"id":"2608.02032","title":"DART: Decoded Attention over Recurrent States for Efficient Long-Context Sequence Modeling","created":"2026-08-03","cited_by_count":2,"area":"ssm"},{"id":"2608.21952","title":"SSDi8: Accurate and Efficient 8-bit Quantization for State Space Duality","created":"2026-08-22","cited_by_count":2,"area":"ssm"},{"id":"2405.20917","title":"Learning to Estimate System Specifications in Linear Temporal Logic using Transformers and Mamba","created":"2024-05-31","cited_by_count":1,"area":"ssm"},{"id":"2406.02013","title":"Mamba as Decision Maker: Exploring Multi-scale Sequence Modeling in Offline Reinforcement Learning","created":"2024-06-04","cited_by_count":1,"area":"ssm"},{"id":"2408.03865","title":"PackMamba: Efficient Processing of Variable-Length Sequences in Mamba training","created":"2024-08-07","cited_by_count":1,"area":"ssm"},{"id":"2408.15997","title":"Mamba or Transformer for Time Series Forecasting? Mixture of Universals (MoU) Is All You Need","created":"2024-08-28","cited_by_count":1,"area":"ssm"},{"id":"2410.10316","title":"GlobalMamba: Global Image Serialization for Vision Mamba","created":"2024-10-14","cited_by_count":1,"area":"ssm"},{"id":"2412.00776","title":"Learning Mamba as a Continual Learner: Meta-Learning Selective State Space Models for Continual Learning","created":"2024-12-01","cited_by_count":1,"area":"ssm"},{"id":"2505.14062","title":"FractalMamba++: Scaling Vision Mamba Across Resolutions via Hilbert Fractal Geometry","created":"2025-05-20","cited_by_count":1,"area":"ssm"},{"id":"2604.18580","title":"Sessa: Selective State Space Attention","created":"2026-04-20","cited_by_count":0,"area":"ssm"},{"id":"2604.20556","title":"LayerTracer: A Joint Task-Particle and Vulnerable-Layer Analysis framework for Arbitrary Large Language Model Architectures","created":"2026-04-22","cited_by_count":0,"area":"ssm"},{"id":"2605.09204","title":"LBI: Parallel Scan Backpropagation via Latent Bounded Interfaces","created":"2026-05-09","cited_by_count":0,"area":"ssm"},{"id":"2608.14757","title":"KHiM-Mamba: Injecting Pathology Knowledge into Mamba via Hidden-State Modulation for Whole Slide Image Analysis","created":"2026-08-14","cited_by_count":0,"area":"ssm"}],"next_cursor":null}