{"total":62,"rows":[{"id":"2405.16605","title":"Demystify Mamba in Vision: A Linear Attention Perspective","created":"2024-05-26","cited_by_count":102,"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":"2407.18559","title":"VSSD: Vision Mamba with Non-Causal State Space Duality","created":"2024-07-26","cited_by_count":29,"area":"ssm"},{"id":"2407.10061","title":"InfiniMotion: Mamba Boosts Memory in Transformer for Arbitrary Long Motion Generation","created":"2024-07-14","cited_by_count":23,"area":"ssm"},{"id":"2408.06966","title":"DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs","created":"2024-08-13","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":"2412.13611","title":"Robust Tracking via Mamba-based Context-aware Token Learning","created":"2024-12-18","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":"2405.09873","title":"IRSRMamba: Infrared Image Super-Resolution via Mamba-based Wavelet Transform Feature Modulation Model","created":"2024-05-16","cited_by_count":13,"area":"ssm"},{"id":"2408.05696","title":"SMILES-Mamba: Chemical Mamba Foundation Models for Drug ADMET Prediction","created":"2024-08-11","cited_by_count":13,"area":"ssm"},{"id":"2405.12094","title":"Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?","created":"2024-05-20","cited_by_count":7,"area":"ssm"},{"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":"2409.00410","title":"A Hybrid Transformer-Mamba Network for Single Image Deraining","created":"2024-08-31","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":"2409.14617","title":"Protein-Mamba: Biological Mamba Models for Protein Function Prediction","created":"2024-09-22","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":"2511.17929","title":"MambaTAD: When State-Space Models Meet Long-Range Temporal Action Detection","created":"2025-11-22","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":"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":"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":"2507.22477","title":"LIDAR: Lightweight Adaptive Cue-Aware Fusion Vision Mamba for Multimodal Segmentation of Structural Cracks","created":"2025-07-30","cited_by_count":3,"area":"ssm"},{"id":"2409.07589","title":"miMamba: EEG-based Emotion Recognition with Multi-scale Inverted Mamba Models","created":"2024-09-11","cited_by_count":2,"area":"ssm"},{"id":"2503.07046","title":"MambaFlow: A Mamba-Centric Architecture for End-to-End Optical Flow Estimation","created":"2025-03-10","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":"2505.14043","title":"Selective Structured State Space for Multispectral-fused Small Target Detection","created":"2025-05-20","cited_by_count":2,"area":"ssm"},{"id":"2508.16291","title":"Learning Long-Range Action Representation by Two-Stream Mamba Pyramid Network for Figure Skating Assessment","created":"2025-08-22","cited_by_count":2,"area":"ssm"},{"id":"2511.05833","title":"TYrPPG: Uncomplicated and Enhanced Learning Capability rPPG for Remote Heart Rate Estimation","created":"2025-11-08","cited_by_count":2,"area":"ssm"},{"id":"2406.05757","title":"Vision Mamba: Cutting-Edge Classification of Alzheimer's Disease with 3D MRI Scans","created":"2024-06-09","cited_by_count":1,"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":"2501.14679","title":"Surface Vision Mamba: Leveraging Bidirectional State Space Model for Efficient Spherical Manifold Representation","created":"2025-01-24","cited_by_count":1,"area":"ssm"},{"id":"2505.15234","title":"UNet with Self-Adaptive Mamba-Like Attention and Causal-Resonance Learning for Medical Image Segmentation","created":"2025-05-21","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":"2506.16353","title":"MambaHash: Visual State Space Deep Hashing Model for Large-Scale Image Retrieval","created":"2025-06-19","cited_by_count":1,"area":"ssm"},{"id":"2506.19561","title":"MambaOutRS: A Hybrid CNN-Fourier Architecture for Remote Sensing Image Classification","created":"2025-06-24","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":"2509.04729","title":"CD-Mamba: Cloud detection with long-range spatial dependency modeling","created":"2025-09-05","cited_by_count":1,"area":"ssm"},{"id":"2511.21298","title":"PathMamba: A Hybrid Mamba-Transformer for Topologically Coherent Road Segmentation in Satellite Imagery","created":"2025-11-26","cited_by_count":1,"area":"ssm"},{"id":"2603.24295","title":"RS-SSM: Refining Forgotten Specifics in State Space Model for Video Semantic Segmentation","created":"2026-03-25","cited_by_count":1,"area":"ssm"},{"id":"2604.15729","title":"MambaBack: Bridging Local Features and Global Contexts in Whole Slide Image Analysis","created":"2026-04-17","cited_by_count":1,"area":"ssm"},{"id":"2605.07552","title":"VIMCAN: Visual-Inertial 3D Human Pose Estimation with Hybrid Mamba-Cross-Attention Network","created":"2026-05-08","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":"2408.10517","title":"Decision MetaMamba: Enhancing Selective SSM in Offline RL with Heterogeneous Sequence Mixing","created":"2024-08-20","cited_by_count":0,"area":"ssm"},{"id":"2409.01093","title":"DS MYOLO: A Reliable Object Detector Based on SSMs for Driving Scenarios","created":"2024-09-02","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":"2507.00577","title":"BadViM: Backdoor Attack against Vision Mamba","created":"2025-07-01","cited_by_count":0,"area":"ssm"},{"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":"2510.21079","title":"WaveSeg: Enhancing Segmentation Precision via High-Frequency Prior and Mamba-Driven Spectrum Decomposition","created":"2025-10-24","cited_by_count":0,"area":"ssm"},{"id":"2511.15077","title":"MambaTrack3D: A State Space Model Framework for LiDAR-Based Object Tracking under High Temporal Variation","created":"2025-11-19","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":"2512.03424","title":"DM3D: Dynamic Mamba via Offset-Guided Feature Resampling for Point Cloud Understanding","created":"2025-12-03","cited_by_count":0,"area":"ssm"},{"id":"2602.19805","title":"Decision MetaMamba: Enhancing Selective SSM in Offline RL with Heterogeneous Sequence Mixing","created":"2026-02-23","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":"2603.20074","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":"2604.06622","title":"Balancing Efficiency and Restoration: Lightweight Mamba-Based Model for CT Metal Artifact Reduction","created":"2026-04-08","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":"2605.13202","title":"STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition","created":"2026-05-13","cited_by_count":0,"area":"ssm"},{"id":"2606.16749","title":"Structure-aware Knowledge-guided Heterogeneous Mamba for Zygomaticomaxillary Suture Assessment","created":"2026-06-15","cited_by_count":0,"area":"ssm"},{"id":"2606.17650","title":"MambaCount: Efficient Text-guided Open-vocabulary Object Counting with Spatial Sparse State Space Duality Block","created":"2026-06-16","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":"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":"2607.18625","title":"Norm or Direction? Decoding Vision Mambas for High-Resolution Vision","created":"2026-07-21","cited_by_count":0,"area":"ssm"},{"id":"2610.05182","title":"TIRMamba: A Thermal-Prior-Modulated State-Space Network for Sub-Million-Parameter Infrared Image Super-Resolution","created":"2026-10-04","cited_by_count":0,"area":"ssm"}],"next_cursor":null}