{"total":141,"rows":[{"id":"2405.07992","title":"MambaOut: Do We Really Need Mamba for Vision?","created":"2024-05-13","cited_by_count":143,"area":"ssm"},{"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":"2405.16605","title":"Demystify Mamba in Vision: A Linear Attention Perspective","created":"2024-05-26","cited_by_count":102,"area":"ssm"},{"id":"2406.01188","title":"UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation","created":"2024-06-03","cited_by_count":102,"area":"diffusion"},{"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":"2405.14174","title":"Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model","created":"2024-05-23","cited_by_count":62,"area":null},{"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":"2404.18861","title":"Visual Mamba: A Survey and New Outlooks","created":"2024-04-29","cited_by_count":41,"area":"ssm"},{"id":"2405.14858","title":"Mamba-R: Vision Mamba ALSO Needs Registers","created":"2024-05-23","cited_by_count":41,"area":"ssm"},{"id":"2410.15091","title":"Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusion","created":"2024-10-19","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":"2407.18559","title":"VSSD: Vision Mamba with Non-Causal State Space Duality","created":"2024-07-26","cited_by_count":29,"area":"ssm"},{"id":"2409.18962","title":"Exploring Token Pruning in Vision State Space Models","created":"2024-09-27","cited_by_count":28,"area":"inference"},{"id":"2502.03738","title":"Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More","created":"2025-02-06","cited_by_count":28,"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":"2406.06367","title":"MVGamba: Unify 3D Content Generation as State Space Sequence Modeling","created":"2024-06-10","cited_by_count":23,"area":"diffusion"},{"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":"2410.06806","title":"QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model","created":"2024-10-09","cited_by_count":18,"area":"ssm"},{"id":"2504.05794","title":"DefMamba: Deformable Visual State Space Model","created":"2025-04-08","cited_by_count":18,"area":"ssm"},{"id":"2411.15241","title":"EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality","created":"2024-11-22","cited_by_count":17,"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":"2411.15941","title":"MobileMamba: Lightweight Multi-Receptive Visual Mamba Network","created":"2024-11-24","cited_by_count":16,"area":"ssm"},{"id":"2503.01113","title":"SCSegamba: Lightweight Structure-Aware Vision Mamba for Crack Segmentation in Structures","created":"2025-03-03","cited_by_count":16,"area":"ssm"},{"id":"2409.09649","title":"SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks","created":"2024-09-15","cited_by_count":14,"area":"ssm"},{"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":"2406.02395","title":"GrootVL: Tree Topology is All You Need in State Space Model","created":"2024-06-04","cited_by_count":13,"area":null},{"id":"2406.17815","title":"SUM: Saliency Unification through Mamba for Visual Attention Modeling","created":"2024-06-25","cited_by_count":12,"area":"ssm"},{"id":"2405.14480","title":"Scalable Visual State Space Model with Fractal Scanning","created":"2024-05-23","cited_by_count":11,"area":null},{"id":"2412.20386","title":"PTQ4VM: Post-Training Quantization for Visual Mamba","created":"2024-12-29","cited_by_count":10,"area":"ssm"},{"id":"2508.09454","title":"Animate-X++: Universal Character Image Animation with Dynamic Backgrounds","created":"2025-08-13","cited_by_count":10,"area":null},{"id":"2410.07599","title":"Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency","created":"2024-10-10","cited_by_count":9,"area":"ssm"},{"id":"2502.12627","title":"DAMamba: Vision State Space Model with Dynamic Adaptive Scan","created":"2025-02-18","cited_by_count":9,"area":null},{"id":"2405.18679","title":"Vim-F: Visual State Space Model Benefiting from Learning in the Frequency Domain","created":"2024-05-29","cited_by_count":8,"area":"ssm"},{"id":"2502.07161","title":"A Survey on Mamba Architecture for Vision Applications","created":"2025-02-11","cited_by_count":8,"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":"2407.10923","title":"OPa-Ma: Text Guided Mamba for 360-degree Image Out-painting","created":"2024-07-15","cited_by_count":7,"area":"ssm"},{"id":"2408.08070","title":"MambaMIM: Pre-training Mamba with State Space Token Interpolation and its Application to Medical Image Segmentation","created":"2024-08-15","cited_by_count":7,"area":"ssm"},{"id":"2408.10575","title":"MUSE: Mamba is Efficient Multi-scale Learner for Text-video Retrieval","created":"2024-08-20","cited_by_count":7,"area":"ssm"},{"id":"2411.16481","title":"Deformable Mamba for Wide Field of View Segmentation","created":"2024-11-25","cited_by_count":7,"area":"ssm"},{"id":"2508.00421","title":"UIS-Mamba: Exploring Mamba for Underwater Instance Segmentation via Dynamic Tree Scan and Hidden State Weaken","created":"2025-08-01","cited_by_count":7,"area":"ssm"},{"id":"2410.10382","title":"V2M: Visual 2-Dimensional Mamba for Image Representation Learning","created":"2024-10-14","cited_by_count":6,"area":"ssm"},{"id":"2410.19894","title":"Topology-aware Mamba for Crack Segmentation in Structures","created":"2024-10-25","cited_by_count":6,"area":"ssm"},{"id":"2502.15130","title":"TransMamba: Fast Universal Architecture Adaption from Transformers to Mamba","created":"2025-02-21","cited_by_count":6,"area":"ssm"},{"id":"2504.04787","title":"Dynamic Vision Mamba","created":"2025-04-07","cited_by_count":6,"area":"ssm"},{"id":"2505.00630","title":"Vision Mamba in Remote Sensing: A Comprehensive Survey of Techniques, Applications and Outlook","created":"2025-05-01","cited_by_count":6,"area":"ssm"},{"id":"2505.17581","title":"MODEM: A Morton-Order Degradation Estimation Mechanism for Adverse Weather Image Recovery","created":"2025-05-23","cited_by_count":6,"area":null},{"id":"2412.12496","title":"Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training","created":"2024-12-17","cited_by_count":5,"area":"ssm"},{"id":"2503.15934","title":"SaMam: Style-aware State Space Model for Arbitrary Image Style Transfer","created":"2025-03-20","cited_by_count":5,"area":"ssm"},{"id":"2504.00037","title":"ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models","created":"2025-03-30","cited_by_count":5,"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":"2602.11534","title":"Krause Synchronization Transformers","created":"2026-02-12","cited_by_count":5,"area":null},{"id":"2408.02615","title":"LaMamba-Diff: Linear-Time High-Fidelity Diffusion Models Based on Local Attention and Mamba","created":"2024-08-05","cited_by_count":4,"area":"diffusion"},{"id":"2409.16592","title":"MambaJSCC: Adaptive Deep Joint Source-Channel Coding with Generalized State Space Model","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2501.15461","title":"Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space","created":"2025-01-26","cited_by_count":4,"area":"ssm"},{"id":"2509.04669","title":"VCMamba: Bridging Convolutions with Multi-Directional Mamba for Efficient Visual Representation","created":"2025-09-04","cited_by_count":4,"area":"ssm"},{"id":"2408.05699","title":"MacFormer: Semantic Segmentation with Fine Object Boundaries","created":"2024-08-11","cited_by_count":3,"area":null},{"id":"2408.10679","title":"Alignment-free Raw Video Demoireing","created":"2024-08-20","cited_by_count":3,"area":"ssm"},{"id":"2409.12108","title":"SPRMamba: Surgical Phase Recognition for Endoscopic Submucosal Dissection with Mamba","created":"2024-09-18","cited_by_count":3,"area":"ssm"},{"id":"2409.14403","title":"GraspMamba: A Mamba-based Language-driven Grasp Detection Framework with Hierarchical Feature Learning","created":"2024-09-22","cited_by_count":3,"area":"ssm"},{"id":"2412.12423","title":"GG-SSMs: Graph-Generating State Space Models","created":"2024-12-17","cited_by_count":3,"area":null},{"id":"2412.16146","title":"Mamba2D: A Natively Multi-Dimensional State-Space Model for Vision Tasks","created":"2024-12-20","cited_by_count":3,"area":"ssm"},{"id":"2503.09509","title":"ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mamba","created":"2025-03-12","cited_by_count":3,"area":"ssm"},{"id":"2503.10422","title":"Category Prompt Mamba Network for Nuclei Segmentation and Classification","created":"2025-03-13","cited_by_count":3,"area":"ssm"},{"id":"2505.22195","title":"S2AFormer: Strip Self-Attention for Efficient Vision Transformer","created":"2025-05-28","cited_by_count":3,"area":null},{"id":"2507.13384","title":"Flatten Wisely: How Patch Order Shapes Mamba-Powered Vision for MRI Segmentation","created":"2025-07-15","cited_by_count":3,"area":"ssm"},{"id":"2507.22477","title":"LIDAR: Lightweight Adaptive Cue-Aware Fusion Vision Mamba for Multimodal Segmentation of Structural Cracks","created":"2025-07-30","cited_by_count":3,"area":"ssm"},{"id":"2509.12817","title":"SAGA: Selective Adaptive Gating for Efficient and Expressive Linear Attention","created":"2025-09-16","cited_by_count":3,"area":null},{"id":"2604.14724","title":"HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNet","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2410.23738","title":"MLLA-UNet: Mamba-like Linear Attention in an Efficient U-Shape Model for Medical Image Segmentation","created":"2024-10-31","cited_by_count":2,"area":"ssm"},{"id":"2505.12020","title":"GeoMaNO: Geometric Mamba Neural Operator for Partial Differential Equations","created":"2025-05-17","cited_by_count":2,"area":"ssm"},{"id":"2505.12685","title":"Mamba-Adaptor: State Space Model Adaptor for Visual Recognition","created":"2025-05-19","cited_by_count":2,"area":"ssm"},{"id":"2506.03213","title":"ConMamba: Contrastive Vision Mamba for Plant Disease Detection","created":"2025-06-03","cited_by_count":2,"area":"ssm"},{"id":"2507.19778","title":"HydraMamba: Multi-Head State Space Model for Global Point Cloud Learning","created":"2025-07-26","cited_by_count":2,"area":"ssm"},{"id":"2508.02113","title":"DeflareMamba: Hierarchical Vision Mamba for Contextually Consistent Lens Flare Removal","created":"2025-08-04","cited_by_count":2,"area":"ssm"},{"id":"2509.18683","title":"LEAF-Mamba: Local Emphatic and Adaptive Fusion State Space Model for RGB-D Salient Object Detection","created":"2025-09-23","cited_by_count":2,"area":"ssm"},{"id":"2605.21308","title":"Deformba: Vision State Space Model with Adaptive State Fusion","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2407.01299","title":"Preserving Full Degradation Details for Blind Image Super-Resolution","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2407.02109","title":"HRSAM: Efficient Interactive Segmentation in High-Resolution Images","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2410.10316","title":"GlobalMamba: Global Image Serialization for Vision Mamba","created":"2024-10-14","cited_by_count":1,"area":"ssm"},{"id":"2411.03260","title":"ShadowMamba: State-Space Model with Boundary-Region Selective Scan for Shadow Removal","created":"2024-11-05","cited_by_count":1,"area":"ssm"},{"id":"2412.01422","title":"MamKPD: A Simple Mamba Baseline for Real-Time 2D Keypoint Detection","created":"2024-12-02","cited_by_count":1,"area":"ssm"},{"id":"2503.06897","title":"Multi-granular body modeling with Redundancy-Free Spatiotemporal Fusion for Text-Driven Motion Generation","created":"2025-03-10","cited_by_count":1,"area":"ssm"},{"id":"2503.11218","title":"Towards General Multimodal Visual Tracking","created":"2025-03-14","cited_by_count":1,"area":null},{"id":"2503.19427","title":"ASP-VMUNet: Atrous Shifted Parallel Vision Mamba U-Net for Skin Lesion Segmentation","created":"2025-03-25","cited_by_count":1,"area":"ssm"},{"id":"2504.11438","title":"Mamba-Based Ensemble learning for White Blood Cell Classification","created":"2025-04-15","cited_by_count":1,"area":"ssm"},{"id":"2505.14062","title":"FractalMamba++: Scaling Vision Mamba Across Resolutions via Hilbert Fractal Geometry","created":"2025-05-20","cited_by_count":1,"area":"ssm"},{"id":"2506.15976","title":"LBMamba: Locally Bi-directional Mamba","created":"2025-06-19","cited_by_count":1,"area":"ssm"},{"id":"2506.16353","title":"MambaHash: Visual State Space Deep Hashing Model for Large-Scale Image Retrieval","created":"2025-06-19","cited_by_count":1,"area":"ssm"},{"id":"2507.14042","title":"Training-free Token Reduction for Vision Mamba","created":"2025-07-18","cited_by_count":1,"area":"ssm"},{"id":"2507.16624","title":"A2Mamba: Attention-augmented State Space Models for Visual Recognition","created":"2025-07-22","cited_by_count":1,"area":"ssm"},{"id":"2508.10453","title":"Trajectory-aware Shifted State Space Models for Online Video Super-Resolution","created":"2025-08-14","cited_by_count":1,"area":"ssm"},{"id":"2508.10542","title":"Beyond Global Scanning: Adaptive Visual State Space Modeling for Salient Object Detection in Optical Remote Sensing Images","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2508.20376","title":"Enhancing Mamba Decoder with Bidirectional Interaction in Multi-Task Dense Prediction","created":"2025-08-28","cited_by_count":1,"area":"ssm"},{"id":"2509.24318","title":"Similarity-Aware Selective State-Space Modeling for Semantic Correspondence","created":"2025-09-29","cited_by_count":1,"area":"ssm"},{"id":"2511.08872","title":"SasMamba: A Lightweight Structure-Aware Stride State Space Model for 3D Human Pose Estimation","created":"2025-11-12","cited_by_count":1,"area":"ssm"},{"id":"2511.19882","title":"ChessMamba: Structure-Aware Interleaving of State Spaces for Change Detection in Remote Sensing Images","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2601.15929","title":"NeuroMamba: Multi-Perspective Feature Interaction with Visual Mamba for Neuron Segmentation","created":"2026-01-22","cited_by_count":1,"area":"ssm"}],"next_cursor":"100"}