{"total":91,"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":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328,"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":"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":"2403.19654","title":"RSMamba: Remote Sensing Image Classification with State Space Model","created":"2024-03-28","cited_by_count":95,"area":"ssm"},{"id":"2403.01590","title":"The Hidden Attention of Mamba Models","created":"2024-03-03","cited_by_count":91,"area":"ssm"},{"id":"2403.15360","title":"SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series","created":"2024-03-22","cited_by_count":82,"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":"2405.04404","title":"Vision Mamba: A Comprehensive Survey and Taxonomy","created":"2024-05-07","cited_by_count":54,"area":"ssm"},{"id":"2407.09941","title":"Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers","created":"2024-07-13","cited_by_count":44,"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":"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":"2406.03344","title":"Audio Mamba: Bidirectional State Space Model for Audio Representation Learning","created":"2024-06-05","cited_by_count":37,"area":"ssm"},{"id":"2403.13642","title":"H-vmunet: High-order Vision Mamba UNet for Medical Image Segmentation","created":"2024-03-20","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":"2406.07537","title":"Autoregressive Pretraining with Mamba in Vision","created":"2024-06-11","cited_by_count":22,"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":"2407.13772","title":"GroupMamba: Efficient Group-Based Visual State Space Model","created":"2024-07-18","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":"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":"2411.03855","title":"MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba","created":"2024-11-06","cited_by_count":11,"area":"ssm"},{"id":"2406.19006","title":"Snakes and Ladders: Two Steps Up for VideoMamba","created":"2024-06-27","cited_by_count":10,"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":"2410.07599","title":"Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency","created":"2024-10-10","cited_by_count":9,"area":"ssm"},{"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":"2407.03552","title":"Vision Mamba for Classification of Breast Ultrasound Images","created":"2024-07-04","cited_by_count":7,"area":"ssm"},{"id":"2405.16542","title":"Mamba4KT:An Efficient and Effective Mamba-based Knowledge Tracing Model","created":"2024-05-26","cited_by_count":6,"area":"ssm"},{"id":"2409.00410","title":"A Hybrid Transformer-Mamba Network for Single Image Deraining","created":"2024-08-31","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":"2502.15130","title":"TransMamba: Fast Universal Architecture Adaption from Transformers to Mamba","created":"2025-02-21","cited_by_count":6,"area":"ssm"},{"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":"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":"2409.04803","title":"Cross-attention Inspired Selective State Space Models for Target Sound Extraction","created":"2024-09-07","cited_by_count":4,"area":"ssm"},{"id":"2410.16020","title":"START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation","created":"2024-10-21","cited_by_count":4,"area":"ssm"},{"id":"2502.02209","title":"On the Expressivity of Selective State-Space Layers: A Multivariate Polynomial Approach","created":"2025-02-04","cited_by_count":4,"area":"ssm"},{"id":"2506.10390","title":"DART: Differentiable Dynamic Adaptive Region Tokenizer for Vision Foundation Models","created":"2025-06-12","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":"2510.19266","title":"Data Efficient Any Transformer-to-Mamba Distillation via Attention Bridge","created":"2025-10-22","cited_by_count":4,"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":"2411.00151","title":"NIMBA: Towards Robust and Principled Processing of Point Clouds With SSMs","created":"2024-10-31","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":"2406.05992","title":"MHS-VM: Multi-Head Scanning in Parallel Subspaces for Vision Mamba","created":"2024-06-10","cited_by_count":2,"area":"ssm"},{"id":"2406.08486","title":"On Evaluating Adversarial Robustness of Volumetric Medical Segmentation Models","created":"2024-06-12","cited_by_count":2,"area":"ssm"},{"id":"2408.14868","title":"ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learning","created":"2024-08-27","cited_by_count":2,"area":"ssm"},{"id":"2501.06138","title":"MS-Temba: Multi-Scale Temporal Mamba for Understanding Long Untrimmed Videos","created":"2025-01-10","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":"2505.14043","title":"Selective Structured State Space for Multispectral-fused Small Target Detection","created":"2025-05-20","cited_by_count":2,"area":"ssm"},{"id":"2506.11997","title":"pLSTM: parallelizable Linear Source Transition Mark networks","created":"2025-06-13","cited_by_count":2,"area":"ssm"},{"id":"2506.18184","title":"Memba: Membrane-driven Parameter-Efficient Fine-Tuning for Mamba","created":"2025-06-22","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":"2403.10696","title":"On the low-shot transferability of [V]-Mamba","created":"2024-03-15","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":"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":"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":"2603.09138","title":"Rotation Equivariant Mamba for Vision Tasks","created":"2026-03-10","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":"2408.01986","title":"DeMansia: Mamba Never Forgets Any Tokens","created":"2024-08-04","cited_by_count":0,"area":"ssm"},{"id":"2408.17081","title":"Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training","created":"2024-08-30","cited_by_count":0,"area":"ssm"},{"id":"2409.11867","title":"StableMamba: Distillation-free Scaling of Large SSMs for Images and Videos","created":"2024-09-18","cited_by_count":0,"area":"ssm"},{"id":"2501.02040","title":"A Separable Self-attention Inspired by the State Space Model for Computer Vision","created":"2025-01-03","cited_by_count":0,"area":"ssm"},{"id":"2501.02559","title":"KM-UNet KAN Mamba UNet for medical image segmentation","created":"2025-01-05","cited_by_count":0,"area":"ssm"},{"id":"2501.13353","title":"Contrast: A Hybrid Architecture of Transformers and State Space Models for Low-Level Vision","created":"2025-01-23","cited_by_count":0,"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":"2503.20258","title":"Mamba-3D as Masked Autoencoders for Accurate and Data-Efficient Analysis of Medical Ultrasound Videos","created":"2025-03-26","cited_by_count":0,"area":"ssm"},{"id":"2508.21135","title":"HiddenObject: Modality-Agnostic Fusion for Multimodal Hidden Object Detection","created":"2025-08-28","cited_by_count":0,"area":"ssm"},{"id":"2509.18005","title":"M3ET: Efficient Vision-Language Learning for Robotics based on Multimodal Mamba-Enhanced Transformer","created":"2025-09-22","cited_by_count":0,"area":"ssm"},{"id":"2509.22691","title":"Sequential Token Merging: Revisiting Hidden States","created":"2025-09-19","cited_by_count":0,"area":"ssm"},{"id":"2512.02727","title":"DF-Mamba: Deformable State Space Modeling for 3D Hand Pose Estimation in Interactions","created":"2025-12-02","cited_by_count":0,"area":"ssm"},{"id":"2512.10353","title":"Hybrid Transformer-Mamba for Weakly Supervised Volumetric Medical Segmentation","created":"2025-12-11","cited_by_count":0,"area":"ssm"},{"id":"2512.14309","title":"PSMamba: Progressive Self-supervised Vision Mamba for Plant Disease Recognition","created":"2025-12-16","cited_by_count":0,"area":"ssm"},{"id":"2601.08608","title":"SfMamba: Efficient Source-Free Domain Adaptation via Selective Scan Modeling","created":"2026-01-13","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":"2603.20074","title":"MFil-Mamba: Multi-Filter Scanning for Spatial Redundancy-Aware Visual State Space Models","created":"2026-03-20","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":"2605.01935","title":"ViM-Q: Scalable Algorithm-Hardware Co-Design for Vision Mamba Model Inference on FPGA","created":"2026-05-03","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":"2607.18625","title":"Norm or Direction? Decoding Vision Mambas for High-Resolution Vision","created":"2026-07-21","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}