{"total":79,"rows":[{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056,"area":"ssm"},{"id":"2403.09338","title":"LocalMamba: Visual State Space Model with Windowed Selective Scan","created":"2024-03-14","cited_by_count":236,"area":"ssm"},{"id":"2407.08083","title":"MambaVision: A Hybrid Mamba-Transformer Vision Backbone","created":"2024-07-10","cited_by_count":224,"area":"ssm"},{"id":"2403.09977","title":"EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba","created":"2024-03-15","cited_by_count":146,"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":"2405.04404","title":"Vision Mamba: A Comprehensive Survey and Taxonomy","created":"2024-05-07","cited_by_count":54,"area":"ssm"},{"id":"2407.09646","title":"Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba","created":"2024-07-12","cited_by_count":45,"area":"ssm"},{"id":"2404.18861","title":"Visual Mamba: A Survey and New Outlooks","created":"2024-04-29","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":"2403.17839","title":"ReMamber: Referring Image Segmentation with Mamba Twister","created":"2024-03-26","cited_by_count":38,"area":"ssm"},{"id":"2412.11023","title":"Exploring Enhanced Contextual Information for Video-Level Object Tracking","created":"2024-12-15","cited_by_count":37,"area":"ssm"},{"id":"2405.15574","title":"Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models","created":"2024-05-24","cited_by_count":30,"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":"2406.07537","title":"Autoregressive Pretraining with Mamba in Vision","created":"2024-06-11","cited_by_count":22,"area":"ssm"},{"id":"2409.19613","title":"Hybrid Mamba for Few-Shot Segmentation","created":"2024-09-29","cited_by_count":21,"area":"ssm"},{"id":"2406.05835","title":"Mamba YOLO: A Simple Baseline for Object Detection with State Space Model","created":"2024-06-09","cited_by_count":19,"area":"ssm"},{"id":"2406.19369","title":"Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Model","created":"2024-06-27","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":"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":"2412.13611","title":"Robust Tracking via Mamba-based Context-aware Token Learning","created":"2024-12-18","cited_by_count":15,"area":"ssm"},{"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":"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":"2410.00871","title":"MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining","created":"2024-10-01","cited_by_count":12,"area":"ssm"},{"id":"2412.20386","title":"PTQ4VM: Post-Training Quantization for Visual Mamba","created":"2024-12-29","cited_by_count":10,"area":"ssm"},{"id":"2404.16302","title":"CFMW: Cross-modality Fusion Mamba for Robust Object Detection under Adverse Weather","created":"2024-04-25","cited_by_count":8,"area":"ssm"},{"id":"2409.19937","title":"MaskMamba: A Hybrid Mamba-Transformer Model for Masked Image Generation","created":"2024-09-30","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":"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":"2502.15130","title":"TransMamba: Fast Universal Architecture Adaption from Transformers to Mamba","created":"2025-02-21","cited_by_count":6,"area":"ssm"},{"id":"2503.19721","title":"EventMamba: Enhancing Spatio-Temporal Locality with State Space Models for Event-Based Video Reconstruction","created":"2025-03-25","cited_by_count":6,"area":"ssm"},{"id":"2411.15761","title":"MambaTrack: Exploiting Dual-Enhancement for Night UAV Tracking","created":"2024-11-24","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":"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":"2503.17700","title":"MAMAT: 3D Mamba-Based Atmospheric Turbulence Removal and its Object Detection Capability","created":"2025-03-22","cited_by_count":5,"area":"ssm"},{"id":"2603.16423","title":"SF-Mamba: Rethinking State Space Model for Vision","created":"2026-03-17","cited_by_count":4,"area":"ssm"},{"id":"2409.08513","title":"Mamba-YOLO-World: Marrying YOLO-World with Mamba for Open-Vocabulary Detection","created":"2024-09-13","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":"2510.10160","title":"SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation","created":"2025-10-11","cited_by_count":3,"area":"ssm"},{"id":"2410.05938","title":"EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment","created":"2024-10-08","cited_by_count":2,"area":"ssm"},{"id":"2412.00626","title":"MambaNUT: Nighttime UAV Tracking via Mamba-based Adaptive Curriculum Learning","created":"2024-12-01","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":"2507.15212","title":"MeshMamba: State Space Models for Articulated 3D Mesh Generation and Reconstruction","created":"2025-07-21","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":"2512.20128","title":"milliMamba: Specular-Aware Human Pose Estimation via Dual mmWave Radar with Multi-Frame Mamba Fusion","created":"2025-12-23","cited_by_count":2,"area":"ssm"},{"id":"2604.23399","title":"Breaking the Resource Wall: Geometry-Guided Sequence Modeling for Efficient Semantic Segmentation","created":"2026-04-25","cited_by_count":2,"area":"ssm"},{"id":"2410.10316","title":"GlobalMamba: Global Image Serialization for Vision Mamba","created":"2024-10-14","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":"2504.15669","title":"UINO-FSS: Unifying Representation Learning and Few-shot Segmentation via Hierarchical Distillation and Mamba-HyperCorrelation","created":"2025-04-22","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":"2506.08297","title":"SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging","created":"2025-06-10","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":"2506.18346","title":"BSMamba: Brightness and Semantic Modeling for Long-Range Interaction in Low-Light Image Enhancement","created":"2025-06-23","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":"2511.18380","title":"RNN as Linear Transformer: A Closer Investigation into Representational Potentials of Visual Mamba Models","created":"2025-11-23","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":"2602.23890","title":"DACESR: Degradation-Aware Conditional Embedding for Real-World Image Super-Resolution","created":"2026-02-27","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"},{"id":"2502.00594","title":"Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing","created":"2025-02-01","cited_by_count":0,"area":"ssm"},{"id":"2504.18068","title":"S3MOT: Monocular 3D Object Tracking with Selective State Space Model","created":"2025-04-25","cited_by_count":0,"area":"ssm"},{"id":"2506.08735","title":"InceptionMamba: An Efficient Hybrid Network with Large Band Convolution and Bottleneck Mamba","created":"2025-06-10","cited_by_count":0,"area":"ssm"},{"id":"2507.15308","title":"Few-Shot Object Detection via Spatial-Channel State Space Model","created":"2025-07-21","cited_by_count":0,"area":"ssm"},{"id":"2512.18718","title":"Rectification Reimagined: A Unified Mamba Model for Image Correction and Rectangling with Prompts","created":"2025-12-21","cited_by_count":0,"area":"ssm"},{"id":"2603.03806","title":"Separators in Enhancing Autoregressive Pretraining for Vision Mamba","created":"2026-03-04","cited_by_count":0,"area":"ssm"},{"id":"2603.18031","title":"InfoMamba: An Attention-Free Hybrid Mamba-Transformer Model","created":"2026-03-08","cited_by_count":0,"area":"ssm"},{"id":"2604.20606","title":"Beyond ZOH: Advanced Discretization Strategies for Vision Mamba","created":"2026-04-22","cited_by_count":0,"area":"ssm"},{"id":"2605.11300","title":"Can Graphs Help Vision SSMs See Better?","created":"2026-05-11","cited_by_count":0,"area":"ssm"},{"id":"2605.12640","title":"MambaPanoptic: A Vision Mamba-based Structured State Space Framework for Panoptic Segmentation","created":"2026-05-12","cited_by_count":0,"area":"ssm"},{"id":"2606.17966","title":"Reload-Mamba: Hierarchical Anti-Dilution State-Space Modeling for Multi-Class Semantic Segmentation","created":"2026-06-16","cited_by_count":0,"area":"ssm"},{"id":"2609.16656","title":"Channel-Wise and Token-Aware Post-Training Quantization for Visual State Space Duality","created":"2026-09-15","cited_by_count":0,"area":"ssm"},{"id":"2609.24337","title":"LiAuto-MindViT: A Hybrid Vision Backbone with Adaptive Bidirectional Mamba","created":"2026-09-21","cited_by_count":0,"area":"ssm"}],"next_cursor":null}