{"total":48,"rows":[{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788,"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":"2203.14343","title":"Diagonal State Spaces are as Effective as Structured State Spaces","created":"2022-03-27","cited_by_count":350,"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":"2405.07992","title":"MambaOut: Do We Really Need Mamba for Vision?","created":"2024-05-13","cited_by_count":143,"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":"2504.05298","title":"One-Minute Video Generation with Test-Time Training","created":"2025-04-07","cited_by_count":101,"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":"2410.05355","title":"Falcon Mamba: The First Competitive Attention-free 7B Language Model","created":"2024-10-07","cited_by_count":46,"area":"ssm"},{"id":"2402.03170","title":"Is Mamba Capable of In-Context Learning?","created":"2024-02-05","cited_by_count":45,"area":"ssm"},{"id":"2504.16053","title":"LongMamba: Enhancing Mamba's Long Context Capabilities via Training-Free Receptive Field Enlargement","created":"2025-04-22","cited_by_count":42,"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":"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":"2510.04800","title":"Hybrid Architectures for Language Models: Systematic Analysis and Design Insights","created":"2025-10-06","cited_by_count":14,"area":"ssm"},{"id":"2503.04953","title":"Spectral Informed Mamba for Robust Point Cloud Processing","created":"2025-03-06","cited_by_count":10,"area":"ssm"},{"id":"2410.04271","title":"Fundamental Limitations on Subquadratic Alternatives to Transformers","created":"2024-10-05","cited_by_count":9,"area":"ssm"},{"id":"2411.15459","title":"MambaVLT: Time-Evolving Multimodal State Space Model for Vision-Language Tracking","created":"2024-11-23","cited_by_count":9,"area":"ssm"},{"id":"2506.10918","title":"Sequential-Parallel Duality in Prefix Scannable Models","created":"2025-06-12","cited_by_count":8,"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":"2407.05489","title":"How Effective are State Space Models for Machine Translation?","created":"2024-07-07","cited_by_count":6,"area":"ssm"},{"id":"2502.00462","title":"MambaGlue: Fast and Robust Local Feature Matching With Mamba","created":"2025-02-01","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":"2409.11018","title":"Unleashing the Potential of Mamba: Boosting a LiDAR 3D Sparse Detector by Using Cross-Model Knowledge Distillation","created":"2024-09-17","cited_by_count":4,"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":"2504.20922","title":"DYNAMAX: Dynamic computing for Transformers and Mamba based architectures","created":"2025-04-29","cited_by_count":3,"area":"ssm"},{"id":"2510.03279","title":"MemMamba: Rethinking Memory Patterns in State Space Model","created":"2025-09-28","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":"2510.14027","title":"Context-Selective State Space Models: Feedback is All You Need","created":"2025-10-15","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":"2501.14679","title":"Surface Vision Mamba: Leveraging Bidirectional State Space Model for Efficient Spherical Manifold Representation","created":"2025-01-24","cited_by_count":1,"area":"ssm"},{"id":"2506.08297","title":"SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging","created":"2025-06-10","cited_by_count":1,"area":"ssm"},{"id":"2508.17679","title":"Characterizing the Behavior of Training Mamba-based State Space Models on GPUs","created":"2025-08-25","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":"2603.20997","title":"When Does Content-Based Routing Work? Representation Requirements for Selective Attention in Hybrid Sequence Models","created":"2026-03-22","cited_by_count":1,"area":"ssm"},{"id":"2402.15290","title":"Efficient State Space Model via Fast Tensor Convolution and Block Diagonalization","created":"2024-02-23","cited_by_count":0,"area":"ssm"},{"id":"2408.10517","title":"Decision MetaMamba: Enhancing Selective SSM in Offline RL with Heterogeneous Sequence Mixing","created":"2024-08-20","cited_by_count":0,"area":"ssm"},{"id":"2506.08512","title":"MLVTG: Mamba-Based Feature Alignment and LLM-Driven Purification for Multi-Modal Video Temporal Grounding","created":"2025-06-10","cited_by_count":0,"area":"ssm"},{"id":"2507.13998","title":"ParallelTime: Dynamically Weighting the Balance of Short- and Long-Term Temporal Dependencies","created":"2025-07-18","cited_by_count":0,"area":"ssm"},{"id":"2509.00935","title":"SCOUT: Toward Sub-Quadratic Attention via Segment Compression for Optimized Utility in Transformers","created":"2025-08-31","cited_by_count":0,"area":"ssm"},{"id":"2511.08349","title":"Hybrid Quantum-Classical Selective State Space Artificial Intelligence","created":"2025-11-11","cited_by_count":0,"area":"ssm"},{"id":"2602.19805","title":"Decision MetaMamba: Enhancing Selective SSM in Offline RL with Heterogeneous Sequence Mixing","created":"2026-02-23","cited_by_count":0,"area":"ssm"},{"id":"2603.03001","title":"MaBERT:A Padding Safe Interleaved Transformer Mamba Hybrid Encoder for Efficient Extended Context Masked Language Modeling","created":"2026-03-03","cited_by_count":0,"area":"ssm"},{"id":"2603.18031","title":"InfoMamba: An Attention-Free Hybrid Mamba-Transformer Model","created":"2026-03-08","cited_by_count":0,"area":"ssm"},{"id":"2604.18580","title":"Sessa: Selective State Space Attention","created":"2026-04-20","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":"2609.32486","title":"Elastic Selective Spectral Hybrids for Train-Once, Export-Many Budgeted Inference","created":"2026-09-26","cited_by_count":0,"area":"ssm"}],"next_cursor":null}