{"total":59,"rows":[{"id":"2406.04339","title":"RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation","created":"2024-06-06","cited_by_count":103,"area":"vla"},{"id":"2405.04404","title":"Vision Mamba: A Comprehensive Survey and Taxonomy","created":"2024-05-07","cited_by_count":54,"area":"ssm"},{"id":"2404.18861","title":"Visual Mamba: A Survey and New Outlooks","created":"2024-04-29","cited_by_count":41,"area":"ssm"},{"id":"2408.01129","title":"A Survey of Mamba","created":"2024-08-02","cited_by_count":39,"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":"2410.01201","title":"Were RNNs All We Needed?","created":"2024-10-02","cited_by_count":38,"area":null},{"id":"2404.18895","title":"RSCaMa: Remote Sensing Image Change Captioning with State Space Model","created":"2024-04-29","cited_by_count":35,"area":"ssm"},{"id":"2410.00379","title":"CXPMRG-Bench: Pre-training and Benchmarking for X-ray Medical Report Generation on CheXpert Plus Dataset","created":"2024-10-01","cited_by_count":35,"area":null},{"id":"2405.03025","title":"Matten: Video Generation with Mamba-Attention","created":"2024-05-05","cited_by_count":24,"area":"diffusion"},{"id":"2405.03673","title":"MemoryMamba: Memory-Augmented State Space Model for Defect Recognition","created":"2024-05-06","cited_by_count":24,"area":null},{"id":"2405.08493","title":"Rethinking Scanning Strategies with Vision Mamba in Semantic Segmentation of Remote Sensing Imagery: An Experimental Study","created":"2024-05-14","cited_by_count":24,"area":"ssm"},{"id":"2404.18174","title":"Mamba-FETrack: Frame-Event Tracking via State Space Model","created":"2024-04-28","cited_by_count":22,"area":"ssm"},{"id":"2405.06116","title":"Rethinking Efficient and Effective Point-based Networks for Event Camera Classification and Regression: EventMamba","created":"2024-05-09","cited_by_count":19,"area":null},{"id":"2405.12003","title":"Mamba-in-Mamba: Centralized Mamba-Cross-Scan in Tokenized Mamba Model for Hyperspectral Image Classification","created":"2024-05-20","cited_by_count":18,"area":"ssm"},{"id":"2410.03105","title":"Mamba in Vision: A Comprehensive Survey of Techniques and Applications","created":"2024-10-04","cited_by_count":18,"area":"ssm"},{"id":"2503.22732","title":"Reasoning Beyond Limits: Advances and Open Problems for LLMs","created":"2025-03-26","cited_by_count":16,"area":"lr"},{"id":"2405.16440","title":"MambaTS: Improved Selective State Space Models for Long-term Time Series Forecasting","created":"2024-05-26","cited_by_count":14,"area":"ssm"},{"id":"2505.00315","title":"Mixture of Sparse Attention: Content-Based Learnable Sparse Attention via Expert-Choice Routing","created":"2025-05-01","cited_by_count":14,"area":"moe"},{"id":"2405.09873","title":"IRSRMamba: Infrared Image Super-Resolution via Mamba-based Wavelet Transform Feature Modulation Model","created":"2024-05-16","cited_by_count":13,"area":"ssm"},{"id":"2406.05815","title":"What Can We Learn from State Space Models for Machine Learning on Graphs?","created":"2024-06-09","cited_by_count":13,"area":null},{"id":"2408.09743","title":"R2GenCSR: Mining Contextual and Residual Information for LLMs-based Radiology Report Generation","created":"2024-08-19","cited_by_count":12,"area":null},{"id":"2408.10487","title":"MambaEVT: Event Stream based Visual Object Tracking using State Space Model","created":"2024-08-20","cited_by_count":12,"area":"ssm"},{"id":"2408.10854","title":"MambaDS: Near-Surface Meteorological Field Downscaling with Topography Constrained Selective State Space Modeling","created":"2024-08-20","cited_by_count":12,"area":"ssm"},{"id":"2406.08234","title":"MaIL: Improving Imitation Learning with Mamba","created":"2024-06-12","cited_by_count":11,"area":"ssm"},{"id":"2503.13299","title":"A Survey on Transformer Context Extension: Approaches and Evaluation","created":"2025-03-17","cited_by_count":11,"area":null},{"id":"2407.10374","title":"An Empirical Study of Mamba-based Pedestrian Attribute Recognition","created":"2024-07-15","cited_by_count":10,"area":"ssm"},{"id":"2408.09720","title":"Pedestrian Attribute Recognition: A New Benchmark Dataset and A Large Language Model Augmented Framework","created":"2024-08-19","cited_by_count":10,"area":null},{"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":"2505.09022","title":"Block-Biased Mamba for Long-Range Sequence Processing","created":"2025-05-13","cited_by_count":8,"area":"ssm"},{"id":"2404.17926","title":"Pre-training on High Definition X-ray Images: An Experimental Study","created":"2024-04-27","cited_by_count":7,"area":null},{"id":"2504.10018","title":"RGB-Event based Pedestrian Attribute Recognition: A Benchmark Dataset and An Asymmetric RWKV Fusion Framework","created":"2025-04-14","cited_by_count":7,"area":null},{"id":"2404.17929","title":"Spatio-Temporal Side Tuning Pre-trained Foundation Models for Video-based Pedestrian Attribute Recognition","created":"2024-04-27","cited_by_count":6,"area":null},{"id":"2411.15671","title":"Best of Both Worlds: Advantages of Hybrid Graph Sequence Models","created":"2024-11-23","cited_by_count":6,"area":null},{"id":"2405.15925","title":"MUCM-Net: A Mamba Powered UCM-Net for Skin Lesion Segmentation","created":"2024-05-24","cited_by_count":5,"area":"ssm"},{"id":"2410.20922","title":"FACTS: A Factored State-Space Framework For World Modelling","created":"2024-10-28","cited_by_count":4,"area":"wm"},{"id":"2510.05364","title":"The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures","created":"2025-10-06","cited_by_count":4,"area":null},{"id":"2408.13031","title":"VFM-Det: Towards High-Performance Vehicle Detection via Large Foundation Models","created":"2024-08-23","cited_by_count":3,"area":null},{"id":"2502.01673","title":"Multilingual State Space Models for Structured Question Answering in Indic Languages","created":"2025-02-01","cited_by_count":3,"area":null},{"id":"2510.16776","title":"EMRRG: Efficient Fine-Tuning Pre-trained X-ray Mamba Networks for Radiology Report Generation","created":"2025-10-19","cited_by_count":3,"area":"ssm"},{"id":"2405.20278","title":"Length independent generalization bounds for deep SSM architectures via Rademacher contraction and stability constraints","created":"2024-05-30","cited_by_count":2,"area":null},{"id":"2412.18322","title":"Exploring Graph Mamba: A Comprehensive Survey on State-Space Models for Graph Learning","created":"2024-12-24","cited_by_count":2,"area":"ssm"},{"id":"2501.04846","title":"EDMB: Edge Detector with Mamba","created":"2025-01-08","cited_by_count":2,"area":"ssm"},{"id":"2506.00077","title":"Gaussian mixture models as a proxy for interacting language models","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2506.23783","title":"Mamba-FETrack V2: Revisiting State Space Model for Frame-Event based Visual Object Tracking","created":"2025-06-30","cited_by_count":2,"area":"ssm"},{"id":"2507.18998","title":"GPSMamba: A Global Phase and Spectral Prompt-guided Mamba for Infrared Image Super-Resolution","created":"2025-07-25","cited_by_count":2,"area":"ssm"},{"id":"2509.22331","title":"Pedestrian Attribute Recognition via Hierarchical Cross-Modality HyperGraph Learning","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2511.21439","title":"EvRainDrop: HyperGraph-guided Completion for Effective Frame and Event Stream Aggregation","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2602.05389","title":"A Decomposition-based State Space Model for Multivariate Time-Series Forecasting","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2408.08078","title":"Treat Stillness with Movement: Remote Sensing Change Detection via Coarse-grained Temporal Foregrounds Mining","created":"2024-08-15","cited_by_count":1,"area":null},{"id":"2506.07652","title":"FMaMIL: Frequency-Driven Mamba Multi-Instance Learning for Weakly Supervised Lesion Segmentation in Medical Images","created":"2025-06-09","cited_by_count":1,"area":"ssm"},{"id":"2507.01535","title":"TrackingMiM: Efficient Mamba-in-Mamba Serialization for Real-time UAV Object Tracking","created":"2025-07-02","cited_by_count":1,"area":"ssm"},{"id":"2408.00629","title":"Cross-Scan Mamba with Masked Training for Robust Spectral Imaging","created":"2024-08-01","cited_by_count":0,"area":"ssm"},{"id":"2510.14542","title":"A Deep State-Space Model Compression Method using Upper Bound on Output Error","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2510.15371","title":"Cortical-SSM: A Deep State Space Model for Motor Imagery Decoding from EEG Signals","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2601.11322","title":"Enhancing Vision Language Models with Logic Reasoning for Situational Awareness","created":"2026-01-16","cited_by_count":0,"area":"lr"},{"id":"2603.05114","title":"UniPAR: A Unified Framework for Pedestrian Attribute Recognition","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.19565","title":"PFM-VEPAR: Prompting Foundation Models for RGB-Event Camera based Pedestrian Attribute Recognition","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2604.08050","title":"ABMAMBA: Multimodal Large Language Model with Aligned Hierarchical Bidirectional Scan for Efficient Video Captioning","created":"2026-04-09","cited_by_count":0,"area":"mllm"},{"id":"2606.31574","title":"Temperature Field Reconstruction of Tungsten Monoblock Divertor on EAST using Physics-aware Neural Operator Transformer","created":"2026-06-30","cited_by_count":0,"area":null}],"next_cursor":null}