{"total":31,"rows":[{"id":"2312.06635","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","created":"2023-12-11","cited_by_count":514,"area":"ssm"},{"id":"2406.07887","title":"An Empirical Study of Mamba-based Language Models","created":"2024-06-12","cited_by_count":186,"area":"ssm"},{"id":"2406.07522","title":"Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling","created":"2024-06-11","cited_by_count":174,"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":"2411.12537","title":"Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues","created":"2024-11-19","cited_by_count":101,"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":"2502.14458","title":"Llamba: Scaling Distilled Recurrent Models for Efficient Language Processing","created":"2025-02-20","cited_by_count":35,"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":"2501.13484","title":"MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods","created":"2025-01-23","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":"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":"2407.12397","title":"Mamba-PTQ: Outlier Channels in Recurrent Large Language Models","created":"2024-07-17","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":"2501.17088","title":"Mamba-Shedder: Post-Transformer Compression for Efficient Selective Structured State Space Models","created":"2025-01-28","cited_by_count":7,"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":"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":"2510.26912","title":"Understanding and Enhancing Mamba-Transformer Hybrids for Memory Recall and Language Modeling","created":"2025-10-30","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":"2406.00209","title":"Mamba State-Space Models Are Lyapunov-Stable Learners","created":"2024-05-31","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":"2506.01206","title":"Mamba Drafters for Speculative Decoding","created":"2025-06-01","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":"2510.13253","title":"End-to-End Multi-Modal Diffusion Mamba","created":"2025-10-15","cited_by_count":3,"area":"ssm"},{"id":"2604.14191","title":"Attention to Mamba: A Recipe for Cross-Architecture Distillation","created":"2026-04-01","cited_by_count":3,"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":"2511.22849","title":"PerfMamba: Performance Analysis and Pruning of Selective State Space Models","created":"2025-11-28","cited_by_count":1,"area":"ssm"},{"id":"2608.00027","title":"Motif-Mamba: network motif improved mamba for long-range sequence modeling","created":"2026-07-14","cited_by_count":0,"area":"ssm"},{"id":"2610.13341","title":"Understanding Mamba-3 Through Oscillatory Dynamics","created":"2026-10-09","cited_by_count":0,"area":"ssm"}],"next_cursor":null}