{"total":29,"rows":[{"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":"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":"2406.14528","title":"DeciMamba: Exploring the Length Extrapolation Potential of Mamba","created":"2024-06-20","cited_by_count":49,"area":"ssm"},{"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":"2404.03646","title":"Locating and Editing Factual Associations in Mamba","created":"2024-04-04","cited_by_count":37,"area":"ssm"},{"id":"2605.22791","title":"Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention","created":"2026-05-21","cited_by_count":33,"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":"2509.19633","title":"Mamba Modulation: On the Length Generalization of Mamba","created":"2025-09-23","cited_by_count":16,"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":"2506.10918","title":"Sequential-Parallel Duality in Prefix Scannable Models","created":"2025-06-12","cited_by_count":8,"area":"ssm"},{"id":"2505.07793","title":"Overflow Prevention Enhances Long-Context Recurrent LLMs","created":"2025-05-12","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":"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":"2510.19266","title":"Data Efficient Any Transformer-to-Mamba Distillation via Attention Bridge","created":"2025-10-22","cited_by_count":4,"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":"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":"2410.03292","title":"Demystifying the Token Dynamics of Deep Selective State Space Models","created":"2024-10-04","cited_by_count":2,"area":"ssm"},{"id":"2409.11263","title":"Bio-Inspired Mamba: Temporal Locality and Bioplausible Learning in Selective State Space Models","created":"2024-09-17","cited_by_count":1,"area":"ssm"},{"id":"2506.05678","title":"Numerical Investigation of Sequence Modeling Theory using Controllable Memory Functions","created":"2025-06-06","cited_by_count":1,"area":"ssm"},{"id":"2508.10370","title":"eMamba: Efficient Acceleration Framework for Mamba Models in Edge Computing","created":"2025-08-14","cited_by_count":1,"area":"ssm"},{"id":"2509.04226","title":"LISM: Long-range Integrative State space Models via Input-Latent State Interactions","created":"2025-09-04","cited_by_count":1,"area":"ssm"},{"id":"2510.04944","title":"On Structured State-Space Duality","created":"2025-10-06","cited_by_count":1,"area":"ssm"},{"id":"2606.00930","title":"A Circuit, Not The Circuit: Non-Unique Causal Localisation of the Mamba-2 State Sink","created":"2026-05-30","cited_by_count":0,"area":"ssm"},{"id":"2606.24650","title":"Harmonic: Hierarchical State Space Models for Efficient Long-Context Language Modeling","created":"2026-05-30","cited_by_count":0,"area":"ssm"},{"id":"2607.21000","title":"Naju: A Native Discrete State-Space Model with Independent Retention and Writing for Long-Sequence Memory","created":"2026-07-23","cited_by_count":0,"area":"ssm"},{"id":"2609.32486","title":"Elastic Selective Spectral Hybrids for Train-Once, Export-Many Budgeted Inference","created":"2026-09-26","cited_by_count":0,"area":"ssm"},{"id":"2609.33051","title":"SketchSSM: Write to the Full State, Read from a Compact Sketch","created":"2026-09-27","cited_by_count":0,"area":"ssm"},{"id":"2609.39185","title":"Low-Discrepancy Dither for Quantized Recurrent State Caches","created":"2026-09-30","cited_by_count":0,"area":"ssm"}],"next_cursor":null}