{"total":52,"rows":[{"id":"2403.09626","title":"Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding","created":"2024-03-14","cited_by_count":108,"area":"ssm"},{"id":"2403.13600","title":"VL-Mamba: Exploring State Space Models for Multimodal Learning","created":"2024-03-20","cited_by_count":93,"area":"mllm"},{"id":"2403.01590","title":"The Hidden Attention of Mamba Models","created":"2024-03-03","cited_by_count":91,"area":"ssm"},{"id":"2403.13802","title":"ZigMa: A DiT-style Zigzag Mamba Diffusion Model","created":"2024-03-20","cited_by_count":84,"area":"diffusion"},{"id":"2403.00762","title":"Point Cloud Mamba: Point Cloud Learning via State Space Model","created":"2024-03-01","cited_by_count":66,"area":"ssm"},{"id":"2403.02148","title":"MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target Detection","created":"2024-03-04","cited_by_count":60,"area":"ssm"},{"id":"2404.09516","title":"State Space Model for New-Generation Network Alternative to Transformers: A Survey","created":"2024-04-15","cited_by_count":59,"area":null},{"id":"2405.04404","title":"Vision Mamba: A Comprehensive Survey and Taxonomy","created":"2024-05-07","cited_by_count":54,"area":"ssm"},{"id":"2404.15956","title":"A Survey on Visual Mamba","created":"2024-04-24","cited_by_count":50,"area":"ssm"},{"id":"2406.04207","title":"CDMamba: Incorporating Local Clues into Mamba for Remote Sensing Image Binary Change Detection","created":"2024-06-06","cited_by_count":48,"area":"ssm"},{"id":"2408.01129","title":"A Survey of Mamba","created":"2024-08-02","cited_by_count":39,"area":"ssm"},{"id":"2406.03344","title":"Audio Mamba: Bidirectional State Space Model for Audio Representation Learning","created":"2024-06-05","cited_by_count":37,"area":"ssm"},{"id":"2406.01159","title":"Dimba: Transformer-Mamba Diffusion Models","created":"2024-06-03","cited_by_count":26,"area":"diffusion"},{"id":"2404.01174","title":"SpikeMba: Multi-Modal Spiking Saliency Mamba for Temporal Video Grounding","created":"2024-04-01","cited_by_count":25,"area":"ssm"},{"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":"2402.15761","title":"Res-VMamba: Fine-Grained Food Category Visual Classification Using Selective State Space Models with Deep Residual Learning","created":"2024-02-24","cited_by_count":22,"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":"2404.11375","title":"Text-controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motion","created":"2024-04-17","cited_by_count":16,"area":"ssm"},{"id":"2410.02362","title":"A Comprehensive Survey of Mamba Architectures for Medical Image Analysis: Classification, Segmentation, Restoration and Beyond","created":"2024-10-03","cited_by_count":16,"area":"ssm"},{"id":"2505.08581","title":"ReSurgSAM2: Referring Segment Anything in Surgical Video via Credible Long-term Tracking","created":"2025-05-13","cited_by_count":15,"area":null},{"id":"2408.07889","title":"MambaVT: Spatio-Temporal Contextual Modeling for robust RGB-T Tracking","created":"2024-08-15","cited_by_count":14,"area":"ssm"},{"id":"2410.17241","title":"Frontiers in Intelligent Colonoscopy","created":"2024-10-22","cited_by_count":14,"area":null},{"id":"2405.18425","title":"ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention","created":"2024-05-28","cited_by_count":13,"area":null},{"id":"2403.08330","title":"Activating Wider Areas in Image Super-Resolution","created":"2024-03-13","cited_by_count":10,"area":null},{"id":"2405.01828","title":"FER-YOLO-Mamba: Facial Expression Detection and Classification Based on Selective State Space","created":"2024-05-03","cited_by_count":7,"area":"ssm"},{"id":"2405.12094","title":"Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?","created":"2024-05-20","cited_by_count":7,"area":"ssm"},{"id":"2406.12463","title":"LFMamba: Light Field Image Super-Resolution with State Space Model","created":"2024-06-18","cited_by_count":7,"area":null},{"id":"2509.19873","title":"SpecMamba: Accelerating Mamba Inference on FPGA with Speculative Decoding","created":"2025-09-24","cited_by_count":5,"area":"inference"},{"id":"2407.12319","title":"Serialized Point Mamba: A Serialized Point Cloud Mamba Segmentation Model","created":"2024-07-17","cited_by_count":4,"area":"ssm"},{"id":"2504.14371","title":"Efficient Spiking Point Mamba for Point Cloud Analysis","created":"2025-04-19","cited_by_count":4,"area":"ssm"},{"id":"2404.19394","title":"CLIP-Mamba: CLIP Pretrained Mamba Models with OOD and Hessian Evaluation","created":"2024-04-30","cited_by_count":3,"area":"ssm"},{"id":"2503.06569","title":"Global-Aware Monocular Semantic Scene Completion with State Space Models","created":"2025-03-09","cited_by_count":3,"area":"ssm"},{"id":"2507.16191","title":"Explicit Context Reasoning with Supervision for Visual Tracking","created":"2025-07-22","cited_by_count":3,"area":null},{"id":"2408.08583","title":"GrassNet: State Space Model Meets Graph Neural Network","created":"2024-08-16","cited_by_count":2,"area":null},{"id":"2506.04116","title":"A Diffusion-Driven Temporal Super-Resolution and Spatial Consistency Enhancement Framework for 4D MRI imaging","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2601.10124","title":"VQ-Seg: Vector-Quantized Token Perturbation for Semi-Supervised Medical Image Segmentation","created":"2026-01-15","cited_by_count":2,"area":null},{"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":"2504.09655","title":"OmniMamba4D: Spatio-temporal Mamba for longitudinal CT lesion segmentation","created":"2025-04-13","cited_by_count":1,"area":"ssm"},{"id":"2509.04729","title":"CD-Mamba: Cloud detection with long-range spatial dependency modeling","created":"2025-09-05","cited_by_count":1,"area":"ssm"},{"id":"2510.14516","title":"Vision Mamba for Permeability Prediction of Porous Media","created":"2025-10-16","cited_by_count":1,"area":"ssm"},{"id":"2602.01677","title":"SMTrack: State-Aware Mamba for Efficient Temporal Modeling in Visual Tracking","created":"2026-02-02","cited_by_count":1,"area":"ssm"},{"id":"2408.10488","title":"Event Stream-based Sign Language Translation: A High-Definition Benchmark Dataset and A Novel Baseline","created":"2024-08-20","cited_by_count":0,"area":null},{"id":"2506.02633","title":"ControlMambaIR: Conditional Controls with State-Space Model for Image Restoration","created":"2025-06-03","cited_by_count":0,"area":"diffusion"},{"id":"2508.19705","title":"FreeVPS: Repurposing Training-Free SAM2 for Generalizable Video Polyp Segmentation","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2510.00862","title":"Gather-Scatter Mamba: Accelerating Propagation with Efficient State Space Model","created":"2025-10-01","cited_by_count":0,"area":"ssm"},{"id":"2510.18213","title":"EMA-SAM: Exponential Moving-average for SAM-based PTMC Segmentation","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2511.14503","title":"Parameter Aware Mamba Model for Multi-task Dense Prediction","created":"2025-11-18","cited_by_count":0,"area":"ssm"},{"id":"2602.05882","title":"EoCD: Encoder only Remote Sensing Change Detection","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2603.19659","title":"CS-MUNet: A Channel-Spatial Dual-Stream Mamba Network for Multi-Organ Segmentation","created":"2026-03-20","cited_by_count":0,"area":"ssm"},{"id":"2604.26461","title":"$\\text{PKS}^4$:Parallel Kinematic Selective State Space Scanners for Efficient Video Understanding","created":"2026-04-29","cited_by_count":0,"area":"ssm"},{"id":"2605.26483","title":"Clinically-Grounded Counterfactual Reasoning for Medical Video Diagnosis","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2607.02922","title":"STAC: Selective Spatiotemporal Aggregation and Compression for Video Reasoning Segmentation","created":"2026-07-03","cited_by_count":0,"area":"inference"}],"next_cursor":null}