{"total":84,"rows":[{"id":"2402.10739","title":"PointMamba: A Simple State Space Model for Point Cloud Analysis","created":"2024-02-16","cited_by_count":167,"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":"2403.07487","title":"Motion Mamba: Efficient and Long Sequence Motion Generation","created":"2024-03-12","cited_by_count":112,"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":"2403.01590","title":"The Hidden Attention of Mamba Models","created":"2024-03-03","cited_by_count":91,"area":"ssm"},{"id":"2403.13802","title":"ZigMa: A DiT-style Zigzag Mamba Diffusion Model","created":"2024-03-20","cited_by_count":84,"area":"diffusion"},{"id":"2403.00762","title":"Point Cloud Mamba: Point Cloud Learning via State Space Model","created":"2024-03-01","cited_by_count":66,"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":"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":"2503.04130","title":"STORM: Token-Efficient Long Video Understanding for Multimodal LLMs","created":"2025-03-06","cited_by_count":49,"area":"mllm"},{"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":"2501.13484","title":"MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods","created":"2025-01-23","cited_by_count":29,"area":"ssm"},{"id":"2407.08476","title":"VideoMamba: Spatio-Temporal Selective State Space Model","created":"2024-07-11","cited_by_count":25,"area":"ssm"},{"id":"2405.03025","title":"Matten: Video Generation with Mamba-Attention","created":"2024-05-05","cited_by_count":24,"area":"diffusion"},{"id":"2404.18174","title":"Mamba-FETrack: Frame-Event Tracking via State Space Model","created":"2024-04-28","cited_by_count":22,"area":"ssm"},{"id":"2406.07537","title":"Autoregressive Pretraining with Mamba in Vision","created":"2024-06-11","cited_by_count":22,"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":"2512.01643","title":"ViT$^3$: Unlocking Test-Time Training in Vision","created":"2025-12-01","cited_by_count":18,"area":null},{"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":"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":"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":"2506.10915","title":"M4V: Multimodal Mamba for Efficient Text-to-Video Generation","created":"2025-06-12","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":"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":"2406.19006","title":"Snakes and Ladders: Two Steps Up for VideoMamba","created":"2024-06-27","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":"2507.02591","title":"AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding","created":"2025-07-03","cited_by_count":9,"area":null},{"id":"2509.00649","title":"MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation","created":"2025-08-31","cited_by_count":9,"area":null},{"id":"2410.06718","title":"MatMamba: A Matryoshka State Space Model","created":"2024-10-09","cited_by_count":7,"area":null},{"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":"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":"2411.06968","title":"Mamba-based Decoder-Only Approach with Bidirectional Speech Modeling for Speech Recognition","created":"2024-11-11","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":"2506.01037","title":"Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolution","created":"2025-06-01","cited_by_count":5,"area":"diffusion"},{"id":"2411.15224","title":"Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation","created":"2024-11-21","cited_by_count":4,"area":"ssm"},{"id":"2501.12381","title":"Parallel Sequence Modeling via Generalized Spatial Propagation Network","created":"2025-01-21","cited_by_count":4,"area":null},{"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":"2406.04342","title":"Learning 1D Causal Visual Representation with De-focus Attention Networks","created":"2024-06-06","cited_by_count":3,"area":null},{"id":"2501.08837","title":"MANTA: Diffusion Mamba for Efficient and Effective Stochastic Long-Term Dense Anticipation","created":"2025-01-15","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":"2510.13245","title":"CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation","created":"2025-10-15","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":"2410.03292","title":"Demystifying the Token Dynamics of Deep Selective State Space Models","created":"2024-10-04","cited_by_count":2,"area":"ssm"},{"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":"2504.16003","title":"MVQA: Mamba with Unified Sampling for Efficient Video Quality Assessment","created":"2025-04-22","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":"2506.11997","title":"pLSTM: parallelizable Linear Source Transition Mark networks","created":"2025-06-13","cited_by_count":2,"area":"ssm"},{"id":"2508.10522","title":"EgoMusic-driven Human Dance Motion Estimation with Skeleton Mamba","created":"2025-08-14","cited_by_count":2,"area":null},{"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":"2408.11679","title":"BadVim: Unveiling Backdoor Threats in Visual State Space Model","created":"2024-08-21","cited_by_count":1,"area":null},{"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":"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":"2507.01535","title":"TrackingMiM: Efficient Mamba-in-Mamba Serialization for Real-time UAV Object Tracking","created":"2025-07-02","cited_by_count":1,"area":"ssm"},{"id":"2605.25220","title":"Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2608.01760","title":"Pixel Ignores, Superpixel Sees: Adverse Weather Image Restoration via Semantic-Center SSM","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2405.17659","title":"Enhancing Global Sensitivity and Uncertainty Quantification in Medical Image Reconstruction with Monte Carlo Arbitrary-Masked Mamba","created":"2024-05-27","cited_by_count":0,"area":"ssm"},{"id":"2503.01306","title":"From Claims to Evidence: A Unified Framework and Critical Analysis of CNN vs. Transformer vs. Mamba in Medical Image Segmentation","created":"2025-03-03","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":"2505.20698","title":"Sparsified State-Space Models are Efficient Highway Networks","created":"2025-05-27","cited_by_count":0,"area":"inference"},{"id":"2507.21394","title":"Systolic Array-based Accelerator for Structured State-Space Models","created":"2025-07-29","cited_by_count":0,"area":"ssm"},{"id":"2508.07363","title":"Keyword Mamba: Spoken Keyword Spotting with State Space Models","created":"2025-08-10","cited_by_count":0,"area":"ssm"},{"id":"2509.09151","title":"Video Understanding by Design: How Datasets Shape Video Models","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2509.18691","title":"An overview of neural architectures for self-supervised audio representation learning from masked spectrograms","created":"2025-09-23","cited_by_count":0,"area":"ssm"},{"id":"2510.27296","title":"Versatile and Efficient Medical Image Super-Resolution Via Frequency-Gated Mamba","created":"2025-10-31","cited_by_count":0,"area":"ssm"},{"id":"2511.21550","title":"MMA: A Momentum Mamba Architecture for Human Activity Recognition with Inertial Sensors","created":"2025-11-26","cited_by_count":0,"area":"ssm"},{"id":"2511.22455","title":"Beyond Real versus Fake Towards Intent-Aware Video Analysis","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2512.07884","title":"GSPN-2: Efficient Parallel Sequence Modeling","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2601.17288","title":"Fluxamba: Topology-Aware Anisotropic State Space Models for Geological Lineament Segmentation in Multi-Source Remote Sensing","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2602.16915","title":"StereoAdapter-2: Globally Structure-Consistent Underwater Stereo Depth Estimation","created":"2026-02-18","cited_by_count":0,"area":null},{"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":"2603.28503","title":"Bridging the Geometry Mismatch: Frequency-Aware Anisotropic Serialization for Thin-Structure SSMs","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.11089","title":"Structured State-Space Regularization for Generation-Friendly Image Tokenization","created":"2026-04-13","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":"2605.11563","title":"TCP-SSM: Efficient Vision State Space Models with Token-Conditioned Poles","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.23126","title":"MambaADv2: Evolving Duality-enhanced State Space Model for Unsupervised Anomaly Detection","created":"2026-06-22","cited_by_count":0,"area":"ssm"},{"id":"2607.19378","title":"Native Multi-Dimensional Subquadratic Operators via Input Dependent Long Convolutions","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2609.33325","title":"VisionHOPE: Visual Backbones as Self-Modifying Learning Systems","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33688","title":"TopoMamba: A Load-Support Relation-Guided Multi-Directional State-Space Model for Topology Optimization","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}