{"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":"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":"2410.05355","title":"Falcon Mamba: The First Competitive Attention-free 7B Language Model","created":"2024-10-07","cited_by_count":46,"area":"ssm"},{"id":"2408.01129","title":"A Survey of Mamba","created":"2024-08-02","cited_by_count":39,"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":"2510.04800","title":"Hybrid Architectures for Language Models: Systematic Analysis and Design Insights","created":"2025-10-06","cited_by_count":14,"area":"ssm"},{"id":"2408.15496","title":"ReMamba: Equip Mamba with Effective Long-Sequence Modeling","created":"2024-08-28","cited_by_count":13,"area":"ssm"},{"id":"2503.18970","title":"Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State-Space Architectures from S4 to Mamba","created":"2025-03-22","cited_by_count":9,"area":"ssm"},{"id":"2409.09808","title":"Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion","created":"2024-09-15","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":"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":"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":"2409.08513","title":"Mamba-YOLO-World: Marrying YOLO-World with Mamba for Open-Vocabulary Detection","created":"2024-09-13","cited_by_count":3,"area":"ssm"},{"id":"2507.00966","title":"MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement","created":"2025-07-01","cited_by_count":2,"area":"ssm"},{"id":"2507.06204","title":"Differential Mamba","created":"2025-07-08","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":"2406.16722","title":"Venturing into Uncharted Waters: The Navigation Compass from Transformer to Mamba","created":"2024-06-24","cited_by_count":1,"area":"ssm"},{"id":"2601.02944","title":"XLSR-MamBo: Scaling the Hybrid Mamba-Attention Backbone for Audio Deepfake Detection","created":"2026-01-06","cited_by_count":1,"area":"ssm"},{"id":"2603.12342","title":"MamTra: A Hybrid Mamba-Transformer Backbone for Speech Synthesis","created":"2026-03-12","cited_by_count":1,"area":"ssm"},{"id":"2506.13183","title":"MT-PCR: Hybrid Mamba-Transformer Network with Spatial Serialization for Point Cloud Registration","created":"2025-06-16","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":"2509.18691","title":"An overview of neural architectures for self-supervised audio representation learning from masked spectrograms","created":"2025-09-23","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":"2603.12206","title":"CLASP: Defending Hybrid Large Language Models Against Hidden State Poisoning Attacks","created":"2026-03-12","cited_by_count":0,"area":"ssm"},{"id":"2605.22416","title":"Asymmetric Virtual Memory Paging for Hybrid Mamba-Transformer Inference","created":"2026-05-21","cited_by_count":0,"area":"ssm"},{"id":"2610.14385","title":"Deep learning from a control vantage point","created":"2026-10-09","cited_by_count":0,"area":"ssm"}],"next_cursor":null}