{"total":25,"rows":[{"id":"2403.01590","title":"The Hidden Attention of Mamba Models","created":"2024-03-03","cited_by_count":91,"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":"2402.03170","title":"Is Mamba Capable of In-Context Learning?","created":"2024-02-05","cited_by_count":45,"area":"ssm"},{"id":"2404.03646","title":"Locating and Editing Factual Associations in Mamba","created":"2024-04-04","cited_by_count":37,"area":"ssm"},{"id":"2410.06672","title":"Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures","created":"2024-10-09","cited_by_count":31,"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":"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":"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":"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":"2411.03855","title":"MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba","created":"2024-11-06","cited_by_count":11,"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":"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":"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":"2410.06846","title":"Joint Fine-tuning and Conversion of Pretrained Speech and Language Models towards Linear Complexity","created":"2024-10-09","cited_by_count":2,"area":"ssm"},{"id":"2506.18184","title":"Memba: Membrane-driven Parameter-Efficient Fine-Tuning for Mamba","created":"2025-06-22","cited_by_count":2,"area":"ssm"},{"id":"2601.01972","title":"Hidden State Poisoning Attacks against Mamba-based Language Models","created":"2026-01-05","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":"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":"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":"2608.18592","title":"Infrared Universality of Collective Dynamics across Transformer and State-Space Architectures","created":"2026-08-19","cited_by_count":0,"area":"ssm"},{"id":"2609.08692","title":"Global Divergence, Local Convergence: Representation Geometry in SSMs and Transformers","created":"2026-09-08","cited_by_count":0,"area":"ssm"},{"id":"2609.24440","title":"Comparing Latent Concept Formation in State Space Models and Transformers via Sparse Autoencoders","created":"2026-09-21","cited_by_count":0,"area":"ssm"},{"id":"2609.32102","title":"Residual Streams Read, Recurrent States Remember: The Global Workspace in Mamba Models","created":"2026-09-26","cited_by_count":0,"area":"ssm"}],"next_cursor":null}