{"total":105,"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":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969,"area":null},{"id":"2402.15648","title":"MambaIR: A Simple Baseline for Image Restoration with State-Space Model","created":"2024-02-23","cited_by_count":352,"area":"ssm"},{"id":"2404.05726","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","created":"2024-04-08","cited_by_count":229,"area":"mllm"},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178,"area":null},{"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":"2402.05079","title":"Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentation","created":"2024-02-07","cited_by_count":133,"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":"2403.02308","title":"Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures","created":"2024-03-04","cited_by_count":98,"area":null},{"id":"2403.01590","title":"The Hidden Attention of Mamba Models","created":"2024-03-03","cited_by_count":91,"area":"ssm"},{"id":"2408.10189","title":"Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models","created":"2024-08-19","cited_by_count":67,"area":"ssm"},{"id":"2406.12846","title":"DrVideo: Document Retrieval Based Long Video Understanding","created":"2024-06-18","cited_by_count":65,"area":null},{"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":"2404.04346","title":"Koala: Key frame-conditioned long video-LLM","created":"2024-04-05","cited_by_count":57,"area":null},{"id":"2403.18795","title":"Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstruction","created":"2024-03-27","cited_by_count":56,"area":"ssm"},{"id":"2402.03170","title":"Is Mamba Capable of In-Context Learning?","created":"2024-02-05","cited_by_count":45,"area":"ssm"},{"id":"2501.04944","title":"MambaHSI: Spatial-Spectral Mamba for Hyperspectral Image Classification","created":"2025-01-09","cited_by_count":44,"area":"ssm"},{"id":"2403.17839","title":"ReMamber: Referring Image Segmentation with Mamba Twister","created":"2024-03-26","cited_by_count":38,"area":"ssm"},{"id":"2404.08406","title":"MambaDFuse: A Mamba-based Dual-phase Model for Multi-modality Image Fusion","created":"2024-04-12","cited_by_count":35,"area":"ssm"},{"id":"2311.05908","title":"FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores","created":"2023-11-10","cited_by_count":33,"area":null},{"id":"2406.07592","title":"MambaLRP: Explaining Selective State Space Sequence Models","created":"2024-06-11","cited_by_count":32,"area":"ssm"},{"id":"2307.02064","title":"Facing Off World Model Backbones: RNNs, Transformers, and S4","created":"2023-07-05","cited_by_count":31,"area":"wm"},{"id":"2402.10887","title":"Weak-Mamba-UNet: Visual Mamba Makes CNN and ViT Work Better for Scribble-based Medical Image Segmentation","created":"2024-02-16","cited_by_count":29,"area":"ssm"},{"id":"2405.15413","title":"MambaVC: Learned Visual Compression with Selective State Spaces","created":"2024-05-24","cited_by_count":28,"area":"ssm"},{"id":"2409.18962","title":"Exploring Token Pruning in Vision State Space Models","created":"2024-09-27","cited_by_count":28,"area":"inference"},{"id":"2502.06020","title":"Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding","created":"2025-02-09","cited_by_count":28,"area":null},{"id":"2406.01159","title":"Dimba: Transformer-Mamba Diffusion Models","created":"2024-06-03","cited_by_count":26,"area":"diffusion"},{"id":"2407.08476","title":"VideoMamba: Spatio-Temporal Selective State Space Model","created":"2024-07-11","cited_by_count":25,"area":"ssm"},{"id":"2405.03008","title":"DVMSR: Distillated Vision Mamba for Efficient Super-Resolution","created":"2024-05-05","cited_by_count":24,"area":"ssm"},{"id":"2410.23782","title":"Video Token Merging for Long-form Video Understanding","created":"2024-10-31","cited_by_count":23,"area":"inference"},{"id":"2404.18174","title":"Mamba-FETrack: Frame-Event Tracking via State Space Model","created":"2024-04-28","cited_by_count":22,"area":"ssm"},{"id":"2402.07245","title":"Semi-Mamba-UNet: Pixel-Level Contrastive and Pixel-Level Cross-Supervised Visual Mamba-based UNet for Semi-Supervised Medical Image Segmentation","created":"2024-02-11","cited_by_count":20,"area":"ssm"},{"id":"2407.08132","title":"DMM: Disparity-guided Multispectral Mamba for Oriented Object Detection in Remote Sensing","created":"2024-07-11","cited_by_count":20,"area":"ssm"},{"id":"2406.12272","title":"Slot State Space Models","created":"2024-06-18","cited_by_count":17,"area":"ssm"},{"id":"2503.08585","title":"HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding","created":"2025-03-11","cited_by_count":17,"area":"mllm"},{"id":"2407.21757","title":"Learning Video Context as Interleaved Multimodal Sequences","created":"2024-07-31","cited_by_count":16,"area":null},{"id":"2404.00272","title":"HSIMamba: Hyperpsectral Imaging Efficient Feature Learning with Bidirectional State Space for Classification","created":"2024-03-30","cited_by_count":14,"area":null},{"id":"2409.06299","title":"Enhancing Long Video Understanding via Hierarchical Event-Based Memory","created":"2024-09-10","cited_by_count":14,"area":null},{"id":"2406.05815","title":"What Can We Learn from State Space Models for Machine Learning on Graphs?","created":"2024-06-09","cited_by_count":13,"area":null},{"id":"2407.06839","title":"A Mamba-based Siamese Network for Remote Sensing Change Detection","created":"2024-07-08","cited_by_count":13,"area":"ssm"},{"id":"2305.14952","title":"Focus Your Attention (with Adaptive IIR Filters)","created":"2023-05-24","cited_by_count":12,"area":null},{"id":"2405.17149","title":"LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling","created":"2024-05-27","cited_by_count":12,"area":"ssm"},{"id":"2408.17443","title":"HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics","created":"2024-08-30","cited_by_count":11,"area":null},{"id":"2412.19634","title":"Deep Continuous-Time State-Space Models for Marked Event Sequences","created":"2024-12-27","cited_by_count":11,"area":null},{"id":"2403.17432","title":"Integrating Mamba Sequence Model and Hierarchical Upsampling Network for Accurate Semantic Segmentation of Multiple Sclerosis Legion","created":"2024-03-26","cited_by_count":8,"area":"ssm"},{"id":"2409.09808","title":"Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion","created":"2024-09-15","cited_by_count":8,"area":"ssm"},{"id":"2405.16555","title":"Building Vision Models upon Heat Conduction","created":"2024-05-26","cited_by_count":7,"area":null},{"id":"2410.14214","title":"MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging","created":"2024-10-18","cited_by_count":7,"area":"ssm"},{"id":"2411.12593","title":"AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction","created":"2024-11-19","cited_by_count":7,"area":null},{"id":"2503.16134","title":"Binarized Mamba-Transformer for Lightweight Quad Bayer HybridEVS Demosaicing","created":"2025-03-20","cited_by_count":7,"area":"ssm"},{"id":"2412.06182","title":"Towards Long Video Understanding via Fine-detailed Video Story Generation","created":"2024-12-09","cited_by_count":6,"area":null},{"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":"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":"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":"2601.08602","title":"WaveFormer: Frequency-Time Decoupled Vision Modeling with Wave Equation","created":"2026-01-13","cited_by_count":5,"area":null},{"id":"2409.09673","title":"SITSMamba for Crop Classification based on Satellite Image Time Series","created":"2024-09-15","cited_by_count":4,"area":"ssm"},{"id":"2410.20922","title":"FACTS: A Factored State-Space Framework For World Modelling","created":"2024-10-28","cited_by_count":4,"area":"wm"},{"id":"2506.18145","title":"Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection","created":"2025-06-22","cited_by_count":4,"area":"moe"},{"id":"2507.06689","title":"Spatial-Temporal Graph Mamba for Music-Guided Dance Video Synthesis","created":"2025-07-09","cited_by_count":4,"area":"ssm"},{"id":"2509.09456","title":"FlexiD-Fuse: Flexible number of inputs multi-modal medical image fusion based on diffusion model","created":"2025-09-11","cited_by_count":4,"area":"diffusion"},{"id":"2512.09354","title":"Video-QTR: Query-Driven Temporal Reasoning Framework for Lightweight Video Understanding","created":"2025-12-10","cited_by_count":4,"area":"lr"},{"id":"2408.10679","title":"Alignment-free Raw Video Demoireing","created":"2024-08-20","cited_by_count":3,"area":"ssm"},{"id":"2411.13683","title":"Extending Video Masked Autoencoders to 128 frames","created":"2024-11-20","cited_by_count":3,"area":null},{"id":"2412.03814","title":"Exploring Real&Synthetic Dataset and Linear Attention in Image Restoration","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2412.10002","title":"NowYouSee Me: Context-Aware Automatic Audio Description","created":"2024-12-13","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":"2502.18232","title":"A Reverse Mamba Attention Network for Pathological Liver Segmentation","created":"2025-02-23","cited_by_count":3,"area":"ssm"},{"id":"2602.17869","title":"Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models","created":"2026-02-19","cited_by_count":3,"area":"mllm"},{"id":"2406.00449","title":"Dual Hyperspectral Mamba for Efficient Spectral Compressive Imaging","created":"2024-06-01","cited_by_count":2,"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":"2408.08087","title":"ColorMamba: Towards High-quality NIR-to-RGB Spectral Translation with Mamba","created":"2024-08-15","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":"2504.05491","title":"REEF: Relevance-Aware and Efficient LLM Adapter for Video Understanding","created":"2025-04-07","cited_by_count":2,"area":"mllm"},{"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":"2507.06204","title":"Differential Mamba","created":"2025-07-08","cited_by_count":2,"area":"ssm"},{"id":"2507.19778","title":"HydraMamba: Multi-Head State Space Model for Global Point Cloud Learning","created":"2025-07-26","cited_by_count":2,"area":"ssm"},{"id":"2508.06058","title":"Lightweight Quad Bayer HybridEVS Demosaicing via State Space Augmented Cross-Attention","created":"2025-08-08","cited_by_count":2,"area":null},{"id":"2407.01299","title":"Preserving Full Degradation Details for Blind Image Super-Resolution","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2408.15887","title":"SpineMamba: Enhancing 3D Spinal Segmentation in Clinical Imaging through Residual Visual Mamba Layers and Shape Priors","created":"2024-08-28","cited_by_count":1,"area":"ssm"},{"id":"2409.16604","title":"Semi-LLIE: Semi-supervised Contrastive Learning with Mamba-based Low-light Image Enhancement","created":"2024-09-25","cited_by_count":1,"area":"ssm"},{"id":"2409.16953","title":"PASS: Path-selective State Space Model for Event-based Recognition","created":"2024-09-25","cited_by_count":1,"area":"ssm"},{"id":"2410.09844","title":"HASN: Hybrid Attention Separable Network for Efficient Image Super-resolution","created":"2024-10-13","cited_by_count":1,"area":null},{"id":"2412.07704","title":"GEXIA: Granularity Expansion and Iterative Approximation for Scalable Multi-grained Video-language Learning","created":"2024-12-10","cited_by_count":1,"area":null},{"id":"2501.11949","title":"GLAM: Global-Local Variation Awareness in Mamba-based World Model","created":"2025-01-21","cited_by_count":1,"area":"wm"},{"id":"2507.06603","title":"Cross-Modal Dual-Causal Learning for Long-Term Action Recognition","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2507.14042","title":"Training-free Token Reduction for Vision Mamba","created":"2025-07-18","cited_by_count":1,"area":"ssm"},{"id":"2508.13712","title":"Diversity-enhanced Collaborative Mamba for Semi-supervised Medical Image Segmentation","created":"2025-08-19","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":"2603.11439","title":"Stay in your Lane: Role Specific Queries with Overlap Suppression Loss for Dense Video Captioning","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2604.10527","title":"STORM: End-to-End Referring Multi-Object Tracking in Videos","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2411.09363","title":"When Mamba Meets xLSTM: An Efficient and Precise Method with the xLSTM-VMUNet Model for Skin lesion Segmentation","created":"2024-11-14","cited_by_count":0,"area":"ssm"},{"id":"2503.09408","title":"Diff-CL: A Novel Cross Pseudo-Supervision Method for Semi-supervised Medical Image Segmentation","created":"2025-03-12","cited_by_count":0,"area":null},{"id":"2509.01080","title":"SpectMamba: Integrating Frequency and State Space Models for Enhanced Medical Image Detection","created":"2025-09-01","cited_by_count":0,"area":"ssm"},{"id":"2509.02471","title":"ESTM: An Enhanced Dual-Branch Spectral-Temporal Mamba for Anomalous Sound Detection","created":"2025-09-02","cited_by_count":0,"area":"ssm"},{"id":"2509.03426","title":"Time-Scaling State-Space Models for Dense Video Captioning","created":"2025-09-03","cited_by_count":0,"area":null},{"id":"2509.09151","title":"Video Understanding by Design: How Datasets Shape Video Models","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2512.00208","title":"ReactionMamba: Generating Short & Long Human Reaction Sequences","created":"2025-11-28","cited_by_count":0,"area":"ssm"},{"id":"2603.01284","title":"FoSS: Modeling Long Range Dependencies and Multimodal Uncertainty in Trajectory Prediction via Fourier State Space Integration","created":"2026-03-01","cited_by_count":0,"area":null},{"id":"2604.08435","title":"HST-HGN: Heterogeneous Spatial-Temporal Hypergraph Networks with Bidirectional State Space Models for Global Fatigue Assessment","created":"2026-04-09","cited_by_count":0,"area":null}],"next_cursor":"100"}