{"total":224,"rows":[{"id":"2408.10189","title":"Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models","created":"2024-08-19","cited_by_count":67,"area":"ssm"},{"id":"2408.01129","title":"A Survey of Mamba","created":"2024-08-02","cited_by_count":39,"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":"2504.03193","title":"Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentation","created":"2025-04-04","cited_by_count":24,"area":"mllm"},{"id":"2409.07163","title":"Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Models","created":"2024-09-11","cited_by_count":23,"area":"diffusion"},{"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":"2411.15941","title":"MobileMamba: Lightweight Multi-Receptive Visual Mamba Network","created":"2024-11-24","cited_by_count":16,"area":"ssm"},{"id":"2411.07500","title":"MaDiNet: Mamba Diffusion Network for SAR Target Detection","created":"2024-11-12","cited_by_count":13,"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":"2511.21016","title":"Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression","created":"2025-11-26","cited_by_count":11,"area":null},{"id":"2412.16626","title":"Mamba-SEUNet: Mamba UNet for Monaural Speech Enhancement","created":"2024-12-21","cited_by_count":10,"area":"ssm"},{"id":"2506.22246","title":"EAMamba: Efficient All-Around Vision State Space Model for Image Restoration","created":"2025-06-27","cited_by_count":10,"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":"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":"2409.19937","title":"MaskMamba: A Hybrid Mamba-Transformer Model for Masked Image Generation","created":"2024-09-30","cited_by_count":8,"area":"ssm"},{"id":"2505.16811","title":"Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining","created":"2025-05-22","cited_by_count":8,"area":null},{"id":"2410.06718","title":"MatMamba: A Matryoshka State Space Model","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2503.24067","title":"TransMamba: A Sequence-Level Hybrid Transformer-Mamba Language Model","created":"2025-03-31","cited_by_count":7,"area":"ssm"},{"id":"2504.17515","title":"Mamba-Sea: A Mamba-based Framework with Global-to-Local Sequence Augmentation for Generalizable Medical Image Segmentation","created":"2025-04-24","cited_by_count":7,"area":"ssm"},{"id":"2507.10800","title":"ThinkingViT: Matryoshka Thinking Vision Transformer for Elastic Inference","created":"2025-07-14","cited_by_count":7,"area":null},{"id":"2510.10982","title":"Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization","created":"2025-10-13","cited_by_count":7,"area":null},{"id":"2601.07832","title":"MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head","created":"2026-01-12","cited_by_count":7,"area":null},{"id":"2408.11289","title":"HMT-UNet: A hybird Mamba-Transformer Vision UNet for Medical Image Segmentation","created":"2024-08-21","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":"2503.13440","title":"MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling","created":"2025-03-17","cited_by_count":6,"area":"mllm"},{"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":"2505.07793","title":"Overflow Prevention Enhances Long-Context Recurrent LLMs","created":"2025-05-12","cited_by_count":6,"area":"ssm"},{"id":"2411.15469","title":"Mamba-CL: Optimizing Selective State Space Model in Null Space for Continual Learning","created":"2024-11-23","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":"2502.00462","title":"MambaGlue: Fast and Robust Local Feature Matching With Mamba","created":"2025-02-01","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":"2504.00037","title":"ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models","created":"2025-03-30","cited_by_count":5,"area":null},{"id":"2508.09140","title":"RadioMamba: Breaking the Accuracy-Efficiency Trade-off in Radio Map Construction via a Hybrid Mamba-UNet","created":"2025-07-28","cited_by_count":5,"area":"ssm"},{"id":"2409.08688","title":"GenMapping: Unleashing the Potential of Inverse Perspective Mapping for Robust Online HD Map Construction","created":"2024-09-13","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":"2501.16738","title":"Post-Training Quantization for Vision Mamba with k-Scaled Quantization and Reparameterization","created":"2025-01-28","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":"2503.12355","title":"Atlas: Multi-Scale Attention Improves Long Context Image Modeling","created":"2025-03-16","cited_by_count":4,"area":null},{"id":"2504.07395","title":"FAIR-SIGHT: Fairness Assurance in Image Recognition via Simultaneous Conformal Thresholding and Dynamic Output Repair","created":"2025-04-10","cited_by_count":4,"area":null},{"id":"2504.10967","title":"An Efficient and Mixed Heterogeneous Model for Image Restoration","created":"2025-04-15","cited_by_count":4,"area":"ssm"},{"id":"2506.23283","title":"MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition","created":"2025-06-29","cited_by_count":4,"area":"ssm"},{"id":"2508.05049","title":"MedMambaLite: Hardware-Aware Mamba for Medical Image Classification","created":"2025-08-07","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":"2603.16423","title":"SF-Mamba: Rethinking State Space Model for Vision","created":"2026-03-17","cited_by_count":4,"area":"ssm"},{"id":"2604.24575","title":"Diffusion Model as a Generalist Segmentation Learner","created":"2026-04-27","cited_by_count":4,"area":"diffusion"},{"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":"2409.14403","title":"GraspMamba: A Mamba-based Language-driven Grasp Detection Framework with Hierarchical Feature Learning","created":"2024-09-22","cited_by_count":3,"area":"ssm"},{"id":"2411.12635","title":"M3D: Dual-Stream Selective State Spaces and Depth-Driven Framework for High-Fidelity Single-View 3D Reconstruction","created":"2024-11-19","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":"2502.14090","title":"MambaLiteSR: Image Super-Resolution with Low-Rank Mamba using Knowledge Distillation","created":"2025-02-19","cited_by_count":3,"area":"ssm"},{"id":"2503.06569","title":"Global-Aware Monocular Semantic Scene Completion with State Space Models","created":"2025-03-09","cited_by_count":3,"area":"ssm"},{"id":"2503.12332","title":"VideoMAP: Toward Scalable Mamba-based Video Autoregressive Pretraining","created":"2025-03-16","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":"2509.20006","title":"Revisiting Image Manipulation Localization under Realistic Manipulation Scenarios","created":"2025-09-24","cited_by_count":3,"area":null},{"id":"2510.13253","title":"End-to-End Multi-Modal Diffusion Mamba","created":"2025-10-15","cited_by_count":3,"area":"ssm"},{"id":"2602.01194","title":"EMFormer: Efficient Multi-Scale Transformer for Accumulative Context Weather Forecasting","created":"2026-02-01","cited_by_count":3,"area":null},{"id":"2603.01361","title":"MixerCSeg: An Efficient Mixer Architecture for Crack Segmentation via Decoupled Mamba Attention","created":"2026-03-02","cited_by_count":3,"area":"ssm"},{"id":"2604.14724","title":"HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNet","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2604.18721","title":"A Controlled Benchmark of Visual State-Space Backbones with Domain-Shift and Boundary Analysis for Remote-Sensing Segmentation","created":"2026-04-20","cited_by_count":3,"area":"ssm"},{"id":"2606.30461","title":"MuonSSM: Orthogonalizing State Space Models for Sequence Modeling","created":"2026-06-29","cited_by_count":3,"area":"ssm"},{"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":"2412.16745","title":"ViM-Disparity: Bridging the Gap of Speed, Accuracy and Memory for Disparity Map Generation","created":"2024-12-21","cited_by_count":2,"area":"ssm"},{"id":"2501.07101","title":"SAMKD: Spatial-aware Adaptive Masking Knowledge Distillation for Object Detection","created":"2025-01-13","cited_by_count":2,"area":"distill"},{"id":"2502.11178","title":"DA-Mamba: Domain Adaptive Hybrid Mamba-Transformer Based One-Stage Object Detection","created":"2025-02-16","cited_by_count":2,"area":"ssm"},{"id":"2503.11030","title":"FMNet: Frequency-Assisted Mamba-Like Linear Attention Network for Camouflaged Object Detection","created":"2025-03-14","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":"2506.18184","title":"Memba: Membrane-driven Parameter-Efficient Fine-Tuning for Mamba","created":"2025-06-22","cited_by_count":2,"area":"ssm"},{"id":"2506.23783","title":"Mamba-FETrack V2: Revisiting State Space Model for Frame-Event based Visual Object Tracking","created":"2025-06-30","cited_by_count":2,"area":"ssm"},{"id":"2510.00399","title":"How Can Mamba Learn In Context with Outliers and Generalize Provably?","created":"2025-10-01","cited_by_count":2,"area":"ssm"},{"id":"2510.12573","title":"Learning Human Motion with Temporally Conditional Mamba","created":"2025-10-14","cited_by_count":2,"area":"ssm"},{"id":"2510.14946","title":"EdgeNavMamba: Mamba Optimized Object Detection for Energy Efficient Edge Devices","created":"2025-10-16","cited_by_count":2,"area":"ssm"},{"id":"2511.01315","title":"MVSMamba: Multi-View Stereo with State Space Model","created":"2025-11-03","cited_by_count":2,"area":"ssm"},{"id":"2512.09383","title":"Perception-Inspired Color Space Design for Photo White Balance Editing","created":"2025-12-10","cited_by_count":2,"area":null},{"id":"2602.20981","title":"Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2408.11679","title":"BadVim: Unveiling Backdoor Threats in Visual State Space Model","created":"2024-08-21","cited_by_count":1,"area":null},{"id":"2409.05587","title":"DSDFormer: An Innovative Transformer-Mamba Framework for Robust High-Precision Driver Distraction Identification","created":"2024-09-09","cited_by_count":1,"area":"ssm"},{"id":"2411.13181","title":"Cross-Camera Distracted Driver Classification through Feature Disentanglement and Contrastive Learning","created":"2024-11-20","cited_by_count":1,"area":null},{"id":"2502.18225","title":"Liver Cirrhosis Stage Estimation from MRI with Deep Learning","created":"2025-02-23","cited_by_count":1,"area":null},{"id":"2503.17938","title":"Selecting and Pruning: A Differentiable Causal Sequentialized State-Space Model for Two-View Correspondence Learning","created":"2025-03-23","cited_by_count":1,"area":"ssm"},{"id":"2504.11438","title":"Mamba-Based Ensemble learning for White Blood Cell Classification","created":"2025-04-15","cited_by_count":1,"area":"ssm"},{"id":"2505.04088","title":"SMMT: Siamese Motion Mamba with Self-attention for Thermal Infrared Target Tracking","created":"2025-05-07","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":"2505.16083","title":"FR-Mamba: Time-Series Physical Field Reconstruction Based on State Space Model","created":"2025-05-21","cited_by_count":1,"area":"ssm"},{"id":"2506.15940","title":"Polyline Path Masked Attention for Vision Transformer","created":"2025-06-19","cited_by_count":1,"area":null},{"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":"2506.22591","title":"BrainMT: A Hybrid Mamba-Transformer Architecture for Modeling Long-Range Dependencies in Functional MRI Data","created":"2025-06-27","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":"2507.16624","title":"A2Mamba: Attention-augmented State Space Models for Visual Recognition","created":"2025-07-22","cited_by_count":1,"area":"ssm"},{"id":"2507.17479","title":"SRMambaV2: Biomimetic Attention for Sparse Point Cloud Upsampling in Autonomous Driving","created":"2025-07-23","cited_by_count":1,"area":null},{"id":"2507.18512","title":"Explaining How Visual, Textual and Multimodal Encoders Share Concepts","created":"2025-07-24","cited_by_count":1,"area":"mechinterp"},{"id":"2507.20765","title":"Onboard Hyperspectral Super-Resolution with Deep Pushbroom Neural Network","created":"2025-07-28","cited_by_count":1,"area":null},{"id":"2508.00383","title":"$MV_{Hybrid}$: Improving Spatial Transcriptomics Prediction with Hybrid State Space-Vision Transformer Backbone in Pathology Vision Foundation Models","created":"2025-08-01","cited_by_count":1,"area":null},{"id":"2508.01210","title":"RoadMamba: A Dual Branch Visual State Space Model for Road Surface Classification","created":"2025-08-02","cited_by_count":1,"area":"ssm"},{"id":"2508.11531","title":"Multi-State Tracker: Enhancing Efficient Object Tracking via Multi-State Specialization and Interaction","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2508.17679","title":"Characterizing the Behavior of Training Mamba-based State Space Models on GPUs","created":"2025-08-25","cited_by_count":1,"area":"ssm"},{"id":"2509.25570","title":"AttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNs","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2510.23043","title":"HieraMamba: Video Temporal Grounding via Hierarchical Anchor-Mamba Pooling","created":"2025-10-27","cited_by_count":1,"area":"ssm"}],"next_cursor":"100"}