{"total":146,"rows":[{"id":"2407.08083","title":"MambaVision: A Hybrid Mamba-Transformer Vision Backbone","created":"2024-07-10","cited_by_count":224,"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":"2403.17695","title":"PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition","created":"2024-03-26","cited_by_count":141,"area":"ssm"},{"id":"2405.16605","title":"Demystify Mamba in Vision: A Linear Attention Perspective","created":"2024-05-26","cited_by_count":102,"area":"ssm"},{"id":"2404.09498","title":"FusionMamba: Dynamic Feature Enhancement for Multimodal Image Fusion with Mamba","created":"2024-04-15","cited_by_count":81,"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":"2405.16105","title":"MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space","created":"2024-05-25","cited_by_count":48,"area":null},{"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":"2408.01129","title":"A Survey of Mamba","created":"2024-08-02","cited_by_count":39,"area":"ssm"},{"id":"2404.01705","title":"Samba: Semantic Segmentation of Remotely Sensed Images with State Space Model","created":"2024-04-02","cited_by_count":37,"area":"ssm"},{"id":"2412.00678","title":"2DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification","created":"2024-12-01","cited_by_count":35,"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":"2503.09590","title":"BIMBA: Selective-Scan Compression for Long-Range Video Question Answering","created":"2025-03-12","cited_by_count":24,"area":null},{"id":"2406.07537","title":"Autoregressive Pretraining with Mamba in Vision","created":"2024-06-11","cited_by_count":22,"area":"ssm"},{"id":"2405.17680","title":"Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports","created":"2024-05-27","cited_by_count":19,"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":"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":"2512.01643","title":"ViT$^3$: Unlocking Test-Time Training in Vision","created":"2025-12-01","cited_by_count":18,"area":null},{"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":"2501.07810","title":"AVS-Mamba: Exploring Temporal and Multi-modal Mamba for Audio-Visual Segmentation","created":"2025-01-14","cited_by_count":16,"area":"ssm"},{"id":"2407.13772","title":"GroupMamba: Efficient Group-Based Visual State Space Model","created":"2024-07-18","cited_by_count":15,"area":"ssm"},{"id":"2411.17473","title":"TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba","created":"2024-11-26","cited_by_count":15,"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":"2503.03437","title":"JamMa: Ultra-lightweight Local Feature Matching with Joint Mamba","created":"2025-03-05","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":"2406.17815","title":"SUM: Saliency Unification through Mamba for Visual Attention Modeling","created":"2024-06-25","cited_by_count":12,"area":"ssm"},{"id":"2408.03703","title":"CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications","created":"2024-08-07","cited_by_count":12,"area":null},{"id":"2405.14480","title":"Scalable Visual State Space Model with Fractal Scanning","created":"2024-05-23","cited_by_count":11,"area":null},{"id":"2404.18213","title":"S$^2$Mamba: A Spatial-spectral State Space Model for Hyperspectral Image Classification","created":"2024-04-28","cited_by_count":10,"area":"ssm"},{"id":"2407.19832","title":"ML-Mamba: Efficient Multi-Modal Large Language Model Utilizing Mamba-2","created":"2024-07-29","cited_by_count":10,"area":"mllm"},{"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":"2409.09808","title":"Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion","created":"2024-09-15","cited_by_count":8,"area":"ssm"},{"id":"2502.16907","title":"MambaFlow: A Novel and Flow-guided State Space Model for Scene Flow Estimation","created":"2025-02-24","cited_by_count":8,"area":"ssm"},{"id":"2511.01243","title":"CenterMamba-SAM: Center-Prioritized Scanning and Temporal Prototypes for Brain Lesion Segmentation","created":"2025-11-03","cited_by_count":8,"area":null},{"id":"2602.21917","title":"Scan Clusters, Not Pixels: A Cluster-Centric Paradigm for Efficient Ultra-high-definition Image Restoration","created":"2026-02-25","cited_by_count":8,"area":null},{"id":"2406.15910","title":"Soft Masked Mamba Diffusion Model for CT to MRI Conversion","created":"2024-06-22","cited_by_count":7,"area":"diffusion"},{"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":"2409.07040","title":"Retinex-RAWMamba: Bridging Demosaicing and Denoising for Low-Light RAW Image Enhancement","created":"2024-09-11","cited_by_count":6,"area":null},{"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":"2501.01262","title":"Detail Matters: Mamba-Inspired Joint Unfolding Network for Snapshot Spectral Compressive Imaging","created":"2025-01-02","cited_by_count":6,"area":"ssm"},{"id":"2504.04787","title":"Dynamic Vision Mamba","created":"2025-04-07","cited_by_count":6,"area":"ssm"},{"id":"2504.19198","title":"Adaptive Dual-domain Learning for Underwater Image Enhancement","created":"2025-04-27","cited_by_count":6,"area":null},{"id":"2412.06674","title":"EMOv2: Pushing 5M Vision Model Frontier","created":"2024-12-09","cited_by_count":5,"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":"2511.06593","title":"Spatial-Frequency Enhanced Mamba for Multi-Modal Image Fusion","created":"2025-11-10","cited_by_count":5,"area":"ssm"},{"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":"2501.16738","title":"Post-Training Quantization for Vision Mamba with k-Scaled Quantization and Reparameterization","created":"2025-01-28","cited_by_count":4,"area":"ssm"},{"id":"2603.02629","title":"Towards an Incremental Unified Multimodal Anomaly Detection: Augmenting Multimodal Denoising From an Information Bottleneck Perspective","created":"2026-03-03","cited_by_count":4,"area":null},{"id":"2603.16423","title":"SF-Mamba: Rethinking State Space Model for Vision","created":"2026-03-17","cited_by_count":4,"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":"2412.16146","title":"Mamba2D: A Natively Multi-Dimensional State-Space Model for Vision Tasks","created":"2024-12-20","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":"2507.06140","title":"LangMamba: A Language-driven Mamba Framework for Low-dose CT Denoising with Vision-language Models","created":"2025-07-08","cited_by_count":3,"area":"mllm"},{"id":"2602.01194","title":"EMFormer: Efficient Multi-Scale Transformer for Accumulative Context Weather Forecasting","created":"2026-02-01","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":"2412.07481","title":"Manta: Enhancing Mamba for Few-Shot Action Recognition of Long Sub-Sequence","created":"2024-12-10","cited_by_count":2,"area":"ssm"},{"id":"2412.11214","title":"Image Forgery Localization with State Space Models","created":"2024-12-15","cited_by_count":2,"area":null},{"id":"2502.11178","title":"DA-Mamba: Domain Adaptive Hybrid Mamba-Transformer Based One-Stage Object Detection","created":"2025-02-16","cited_by_count":2,"area":"ssm"},{"id":"2503.01633","title":"SparseMamba-PCL: Scribble-Supervised Medical Image Segmentation via SAM-Guided Progressive Collaborative Learning","created":"2025-03-03","cited_by_count":2,"area":"ssm"},{"id":"2503.16910","title":"Salient Object Detection in Traffic Scene through the TSOD10K Dataset","created":"2025-03-21","cited_by_count":2,"area":null},{"id":"2504.01466","title":"Mesh Mamba: A Unified State Space Model for Saliency Prediction in Non-Textured and Textured Meshes","created":"2025-04-02","cited_by_count":2,"area":"ssm"},{"id":"2505.03113","title":"Image Recognition with Online Lightweight Vision Transformer: A Survey","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2505.12685","title":"Mamba-Adaptor: State Space Model Adaptor for Visual Recognition","created":"2025-05-19","cited_by_count":2,"area":"ssm"},{"id":"2506.21137","title":"Norm$\\times$Direction: Restoring the Missing Query Norm in Vision Linear Attention","created":"2025-06-26","cited_by_count":2,"area":null},{"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":"2508.17299","title":"FoundDiff: Foundational Diffusion Model for Generalizable Low-Dose CT Denoising","created":"2025-08-24","cited_by_count":2,"area":"diffusion"},{"id":"2509.16900","title":"ME-Mamba: Multi-Expert Mamba with Efficient Knowledge Capture and Fusion for Multimodal Survival Analysis","created":"2025-09-21","cited_by_count":2,"area":"ssm"},{"id":"2511.01315","title":"MVSMamba: Multi-View Stereo with State Space Model","created":"2025-11-03","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":"2410.10316","title":"GlobalMamba: Global Image Serialization for Vision Mamba","created":"2024-10-14","cited_by_count":1,"area":"ssm"},{"id":"2410.24075","title":"Identifying Spatio-Temporal Drivers of Extreme Events","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2411.17283","title":"BadScan: An Architectural Backdoor Attack on Visual State Space Models","created":"2024-11-26","cited_by_count":1,"area":null},{"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":"2503.19427","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":"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":"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":"2508.06113","title":"GMF-Drive: Gated Mamba Fusion with Spatial-Aware BEV Representation for End-to-End Autonomous Driving","created":"2025-08-08","cited_by_count":1,"area":"driving"},{"id":"2508.13712","title":"Diversity-enhanced Collaborative Mamba for Semi-supervised Medical Image Segmentation","created":"2025-08-19","cited_by_count":1,"area":"ssm"},{"id":"2509.25570","title":"AttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNs","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2601.11164","title":"SoLA-Vision: Fine-grained Layer-wise Linear Softmax Hybrid Attention","created":"2026-01-16","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"},{"id":"2602.04170","title":"Partial Ring Scan: Revisiting Scan Order in Vision State Space Models","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2604.08038","title":"Beyond Mamba: Enhancing State-space Models with Deformable Dilated Convolutions for Multi-scale Traffic Object Detection","created":"2026-04-09","cited_by_count":1,"area":"ssm"},{"id":"2607.03589","title":"Vision Non-Causal Trapezoidal Mamba: Eliminating Directional Scanning in Vision SSMs with Second-Order Dynamics","created":"2026-07-03","cited_by_count":1,"area":"ssm"}],"next_cursor":"100"}