{"total":236,"rows":[{"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":"2410.12781","title":"Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats","created":"2024-10-16","cited_by_count":114,"area":null},{"id":"2404.06564","title":"MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection","created":"2024-04-09","cited_by_count":113,"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":"2404.16112","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":"2404.09476","title":"FreqMamba: Viewing Mamba from a Frequency Perspective for Image Deraining","created":"2024-04-15","cited_by_count":57,"area":"ssm"},{"id":"2407.21773","title":"RainMamba: Enhanced Locality Learning with State Space Models for Video Deraining","created":"2024-07-31","cited_by_count":56,"area":"ssm"},{"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":"2412.20066","title":"MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration","created":"2024-12-28","cited_by_count":45,"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":"2403.19888","title":"MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection","created":"2024-03-29","cited_by_count":40,"area":"ssm"},{"id":"2408.01129","title":"A Survey of Mamba","created":"2024-08-02","cited_by_count":39,"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":"2501.13484","title":"MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods","created":"2025-01-23","cited_by_count":29,"area":"ssm"},{"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":"2406.06367","title":"MVGamba: Unify 3D Content Generation as State Space Sequence Modeling","created":"2024-06-10","cited_by_count":23,"area":"diffusion"},{"id":"2406.07537","title":"Autoregressive Pretraining with Mamba in Vision","created":"2024-06-11","cited_by_count":22,"area":"ssm"},{"id":"2503.12461","title":"MambaIC: State Space Models for High-Performance Learned Image Compression","created":"2025-03-16","cited_by_count":20,"area":null},{"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":"2412.18076","title":"COMO: Cross-Mamba Interaction and Offset-Guided Fusion for Multimodal Object Detection","created":"2024-12-24","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":"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":"2408.11758","title":"MambaCSR: Dual-Interleaved Scanning for Compressed Image Super-Resolution With SSMs","created":"2024-08-21","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":"2403.10935","title":"Understanding Robustness of Visual State Space Models for Image Classification","created":"2024-03-16","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":"2410.05100","title":"IGroupSS-Mamba: Interval Group Spatial-Spectral Mamba for Hyperspectral Image Classification","created":"2024-10-07","cited_by_count":11,"area":"ssm"},{"id":"2411.04168","title":"DiMSUM: Diffusion Mamba -- A Scalable and Unified Spatial-Frequency Method for Image Generation","created":"2024-11-06","cited_by_count":11,"area":"diffusion"},{"id":"2412.13615","title":"MambaLCT: Boosting Tracking via Long-term Context State Space Model","created":"2024-12-18","cited_by_count":11,"area":null},{"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":"2412.20386","title":"PTQ4VM: Post-Training Quantization for Visual Mamba","created":"2024-12-29","cited_by_count":10,"area":"ssm"},{"id":"2503.12009","title":"UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detection","created":"2025-03-15","cited_by_count":10,"area":"ssm"},{"id":"2507.10689","title":"CWNet: Causal Wavelet Network for Low-Light Image Enhancement","created":"2025-07-14","cited_by_count":10,"area":null},{"id":"2406.09546","title":"QMamba: On First Exploration of Vision Mamba for Image Quality Assessment","created":"2024-06-13","cited_by_count":9,"area":"ssm"},{"id":"2408.14415","title":"LoG-VMamba: Local-Global Vision Mamba for Medical Image Segmentation","created":"2024-08-26","cited_by_count":9,"area":"ssm"},{"id":"2409.10699","title":"CoMamba: Real-time Cooperative Perception Unlocked with State Space Models","created":"2024-09-16","cited_by_count":9,"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":"2602.13301","title":"DriveMamba: Task-Centric Scalable State Space Model for Efficient End-to-End Autonomous Driving","created":"2026-02-09","cited_by_count":9,"area":"driving"},{"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":"2405.16470","title":"Image Deraining with Frequency-Enhanced State Space Model","created":"2024-05-26","cited_by_count":7,"area":null},{"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":"2409.01728","title":"Shuffle Mamba: State Space Models with Random Shuffle for Multi-Modal Image Fusion","created":"2024-09-03","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":"2406.08444","title":"PixMamba: Leveraging State Space Models in a Dual-Level Architecture for Underwater Image Enhancement","created":"2024-06-12","cited_by_count":6,"area":null},{"id":"2409.05395","title":"Shaking Up VLMs: Comparing Transformers and Structured State Space Models for Vision & Language Modeling","created":"2024-09-09","cited_by_count":6,"area":"mllm"},{"id":"2410.05624","title":"Remote Sensing Image Segmentation Using Vision Mamba and Multi-Scale Multi-Frequency Feature Fusion","created":"2024-10-08","cited_by_count":6,"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":"2503.12758","title":"VasTSD: Learning 3D Vascular Tree-state Space Diffusion Model for Angiography Synthesis","created":"2025-03-17","cited_by_count":6,"area":"diffusion"},{"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":"2403.18063","title":"Heracles: A Hybrid SSM-Transformer Model for High-Resolution Image and Time-Series Analysis","created":"2024-03-26","cited_by_count":5,"area":"ssm"},{"id":"2406.05700","title":"HDMba: Hyperspectral Remote Sensing Imagery Dehazing with State Space Model","created":"2024-06-09","cited_by_count":5,"area":"ssm"},{"id":"2410.23356","title":"Sequential Order-Robust Mamba for Time Series Forecasting","created":"2024-10-30","cited_by_count":5,"area":"ssm"},{"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":"2503.10959","title":"OuroMamba: A Data-Free Quantization Framework for Vision Mamba","created":"2025-03-13","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":"2410.20922","title":"FACTS: A Factored State-Space Framework For World Modelling","created":"2024-10-28","cited_by_count":4,"area":"wm"},{"id":"2501.01618","title":"Merging Context Clustering with Visual State Space Models for Medical Image Segmentation","created":"2025-01-03","cited_by_count":4,"area":null},{"id":"2501.12381","title":"Parallel Sequence Modeling via Generalized Spatial Propagation Network","created":"2025-01-21","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":"2503.06369","title":"Spectral State Space Model for Rotation-Invariant Visual Representation Learning","created":"2025-03-09","cited_by_count":4,"area":null},{"id":"2503.10665","title":"Small Vision-Language Models: A Survey on Compact Architectures and Techniques","created":"2025-03-09","cited_by_count":4,"area":"mllm"},{"id":"2407.19248","title":"Mamba-UIE: Enhancing Underwater Images with Physical Model Constraint","created":"2024-07-27","cited_by_count":3,"area":"ssm"},{"id":"2408.05699","title":"MacFormer: Semantic Segmentation with Fine Object Boundaries","created":"2024-08-11","cited_by_count":3,"area":null},{"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":"2411.11717","title":"RAWMamba: Unified sRGB-to-RAW De-rendering With State Space Model","created":"2024-11-18","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":"2501.08163","title":"DH-Mamba: Exploring Dual-domain Hierarchical State Space Models for MRI Reconstruction","created":"2025-01-14","cited_by_count":3,"area":"ssm"},{"id":"2501.18500","title":"HSRMamba: Contextual Spatial-Spectral State Space Model for Single Image Hyperspectral Super-Resolution","created":"2025-01-30","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":"2503.17261","title":"Cross-Modal Interactive Perception Network with Mamba for Lung Tumor Segmentation in PET-CT Images","created":"2025-03-21","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":"2506.18679","title":"MARL-MambaContour: Unleashing Multi-Agent Deep Reinforcement Learning for Active Contour Optimization in Medical Image Segmentation","created":"2025-06-23","cited_by_count":3,"area":null},{"id":"2507.01384","title":"MUG: Pseudo Labeling Augmented Audio-Visual Mamba Network for Audio-Visual Video Parsing","created":"2025-07-02","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":"2601.12954","title":"StyMam: A Mamba-Based Generator for Artistic Style Transfer","created":"2026-01-19","cited_by_count":3,"area":"ssm"}],"next_cursor":"100"}