{"total":84,"rows":[{"id":"2405.16605","title":"Demystify Mamba in Vision: A Linear Attention Perspective","created":"2024-05-26","cited_by_count":102,"area":"ssm"},{"id":"2407.11633","title":"Scaling Diffusion Transformers to 16 Billion Parameters","created":"2024-07-16","cited_by_count":66,"area":"diffusion"},{"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":"2407.00783","title":"Diffusion Models and Representation Learning: A Survey","created":"2024-06-30","cited_by_count":54,"area":"diffusion"},{"id":"2407.09646","title":"Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba","created":"2024-07-12","cited_by_count":45,"area":"ssm"},{"id":"2412.20066","title":"MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration","created":"2024-12-28","cited_by_count":45,"area":"ssm"},{"id":"2409.02097","title":"LinFusion: 1 GPU, 1 Minute, 16K Image","created":"2024-09-03","cited_by_count":43,"area":"diffusion"},{"id":"2410.11795","title":"Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices","created":"2024-10-15","cited_by_count":41,"area":"diffusion"},{"id":"2408.01129","title":"A Survey of Mamba","created":"2024-08-02","cited_by_count":39,"area":"ssm"},{"id":"2502.20313","title":"FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction","created":"2025-02-27","cited_by_count":23,"area":null},{"id":"2406.07537","title":"Autoregressive Pretraining with Mamba in Vision","created":"2024-06-11","cited_by_count":22,"area":"ssm"},{"id":"2501.04765","title":"TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training","created":"2025-01-08","cited_by_count":21,"area":"diffusion"},{"id":"2405.01726","title":"SSUMamba: Spatial-Spectral Selective State Space Model for Hyperspectral Image Denoising","created":"2024-05-02","cited_by_count":20,"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":"2502.11234","title":"MaskFlow: Discrete Flows For Flexible and Efficient Long Video Generation","created":"2025-02-16","cited_by_count":12,"area":null},{"id":"2503.08686","title":"OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models","created":"2025-03-11","cited_by_count":12,"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":"2411.04168","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":"2412.06787","title":"[MASK] is All You Need","created":"2024-12-09","cited_by_count":11,"area":"diffusion"},{"id":"2501.12976","title":"LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation","created":"2025-01-22","cited_by_count":10,"area":"diffusion"},{"id":"2504.02697","title":"Learning Phase Distortion with Selective State Space Models for Video Turbulence Mitigation","created":"2025-04-03","cited_by_count":9,"area":"ssm"},{"id":"2503.16726","title":"EDiT: Efficient Diffusion Transformers with Linear Compressed Attention","created":"2025-03-20","cited_by_count":8,"area":"diffusion"},{"id":"2409.07040","title":"Retinex-RAWMamba: Bridging Demosaicing and Denoising for Low-Light RAW Image Enhancement","created":"2024-09-11","cited_by_count":6,"area":null},{"id":"2502.15130","title":"TransMamba: Fast Universal Architecture Adaption from Transformers to Mamba","created":"2025-02-21","cited_by_count":6,"area":"ssm"},{"id":"2503.12758","title":"VasTSD: Learning 3D Vascular Tree-state Space Diffusion Model for Angiography Synthesis","created":"2025-03-17","cited_by_count":6,"area":"diffusion"},{"id":"2505.17581","title":"MODEM: A Morton-Order Degradation Estimation Mechanism for Adverse Weather Image Recovery","created":"2025-05-23","cited_by_count":6,"area":null},{"id":"2511.15927","title":"DiffuMamba: High-Throughput Diffusion LMs with Mamba Backbone","created":"2025-11-19","cited_by_count":6,"area":"diffusion"},{"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":"2503.10959","title":"OuroMamba: A Data-Free Quantization Framework for Vision Mamba","created":"2025-03-13","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":"2504.00037","title":"ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models","created":"2025-03-30","cited_by_count":5,"area":null},{"id":"2504.13499","title":"U-Shape Mamba: State Space Model for faster diffusion","created":"2025-04-18","cited_by_count":5,"area":"diffusion"},{"id":"2409.16592","title":"MambaJSCC: Adaptive Deep Joint Source-Channel Coding with Generalized State Space Model","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2412.02632","title":"Scaling Image Tokenizers with Grouped Spherical Quantization","created":"2024-12-03","cited_by_count":4,"area":null},{"id":"2501.15461","title":"Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space","created":"2025-01-26","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":"2412.12423","title":"GG-SSMs: Graph-Generating State Space Models","created":"2024-12-17","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":"2506.18679","title":"MARL-MambaContour: Unleashing Multi-Agent Deep Reinforcement Learning for Active Contour Optimization in Medical Image Segmentation","created":"2025-06-23","cited_by_count":3,"area":null},{"id":"2508.04797","title":"RetinexDual: Retinex-based Dual Nature Approach for Generalized Ultra-High-Definition Image Restoration","created":"2025-08-06","cited_by_count":3,"area":"ssm"},{"id":"2510.13253","title":"End-to-End Multi-Modal Diffusion Mamba","created":"2025-10-15","cited_by_count":3,"area":"ssm"},{"id":"2510.16834","title":"Schr\\\"odinger Bridge Mamba for One-Step Speech Enhancement","created":"2025-10-19","cited_by_count":3,"area":"ssm"},{"id":"2601.12954","title":"StyMam: A Mamba-Based Generator for Artistic Style Transfer","created":"2026-01-19","cited_by_count":3,"area":"ssm"},{"id":"2607.28611","title":"Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers","created":"2026-07-30","cited_by_count":3,"area":"diffusion"},{"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":"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":"2505.22535","title":"RiverMamba: A State Space Model for Global River Discharge and Flood Forecasting","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2508.10522","title":"EgoMusic-driven Human Dance Motion Estimation with Skeleton Mamba","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2510.12573","title":"Learning Human Motion with Temporally Conditional Mamba","created":"2025-10-14","cited_by_count":2,"area":"ssm"},{"id":"2511.18312","title":"DiM-TS: Bridge the Gap between Selective State Space Models and Time Series for Generative Modeling","created":"2025-11-23","cited_by_count":2,"area":"ssm"},{"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":"2603.26357","title":"MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model","created":"2026-03-27","cited_by_count":2,"area":"diffusion"},{"id":"2407.01299","title":"Preserving Full Degradation Details for Blind Image Super-Resolution","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2410.24075","title":"Identifying Spatio-Temporal Drivers of Extreme Events","created":"2024-10-31","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":"2508.10453","title":"Trajectory-aware Shifted State Space Models for Online Video Super-Resolution","created":"2025-08-14","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":"2509.11394","title":"MixANT: Observation-dependent Memory Propagation for Stochastic Dense Action Anticipation","created":"2025-09-14","cited_by_count":1,"area":null},{"id":"2602.04170","title":"Partial Ring Scan: Revisiting Scan Order in Vision State Space Models","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2409.07746","title":"Learning Brain Tumor Representation in 3D High-Resolution MR Images via Interpretable State Space Models","created":"2024-09-12","cited_by_count":0,"area":null},{"id":"2410.14024","title":"Ensemble-based, large-eddy reconstruction of wind turbine inflow in a near-stationary atmospheric boundary layer through generative artificial intelligence","created":"2024-10-17","cited_by_count":0,"area":null},{"id":"2503.13004","title":"TFDM: Time-Variant Frequency-Based Point Cloud Diffusion with Mamba","created":"2025-03-17","cited_by_count":0,"area":"diffusion"},{"id":"2507.07687","title":"Tree-Mamba: A Tree-Aware Mamba for Underwater Monocular Depth Estimation","created":"2025-07-10","cited_by_count":0,"area":"ssm"},{"id":"2508.07011","title":"HiMat: DiT-based Ultra-High Resolution SVBRDF Generation","created":"2025-08-09","cited_by_count":0,"area":null},{"id":"2508.13599","title":"Towards Efficient Vision State Space Models via Token Merging","created":"2025-08-19","cited_by_count":0,"area":"inference"},{"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":"2509.17651","title":"SISMA: Semantic Face Image Synthesis with Mamba","created":"2025-09-22","cited_by_count":0,"area":"diffusion"},{"id":"2511.11243","title":"Arcee: Differentiable Recurrent State Chain for Generative Vision Modeling with Mamba SSMs","created":"2025-11-14","cited_by_count":0,"area":"ssm"},{"id":"2512.03852","title":"Traffic Image Restoration under Adverse Weather via Frequency-Aware Mamba","created":"2025-12-03","cited_by_count":0,"area":"ssm"},{"id":"2601.01322","title":"LinMU: Multimodal Understanding Made Linear","created":"2026-01-04","cited_by_count":0,"area":"mllm"},{"id":"2601.13683","title":"Dynamic Differential Linear Attention: Enhancing Linear Diffusion Transformer for High-Quality Image Generation","created":"2026-01-20","cited_by_count":0,"area":"diffusion"},{"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":"2602.04102","title":"DMS2F-HAD: A Dual-branch Mamba-based Spatial-Spectral Fusion Network for Hyperspectral Anomaly Detection","created":"2026-02-04","cited_by_count":0,"area":"ssm"},{"id":"2602.06419","title":"Learning Human Visual Attention on 3D Surfaces through Geometry-Queried Semantic Priors","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2603.17637","title":"DSS-GAN: Directional State Space GAN with Mamba backbone for Class-Conditional Image Synthesis","created":"2026-03-18","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":"2604.06129","title":"PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer","created":"2026-04-07","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":"2604.15611","title":"CLIMB: Controllable Longitudinal Brain Image Generation using Mamba-based Latent Diffusion Model and Gaussian-aligned Autoencoder","created":"2026-04-17","cited_by_count":0,"area":"diffusion"},{"id":"2604.25545","title":"TopoMamba: Topology-Aware Scanning and Fusion for Segmenting Heterogeneous Medical Visual Media","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.10581","title":"Polygon-mamba: Retinal vessel segmentation using polygon scanning mamba and space-frequency collaborative attention","created":"2026-05-11","cited_by_count":0,"area":"ssm"},{"id":"2605.14597","title":"VMU-Diff: A Coarse-to-fine Multi-source Data Fusion Framework for Precipitation Nowcasting","created":"2026-05-14","cited_by_count":0,"area":"diffusion"},{"id":"2606.14757","title":"Spatial Priors via Space Filling Curves for Small and Limited Data Vision Transformers","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.25329","title":"State Space Models Meet Remote Sensing: A Survey","created":"2026-06-24","cited_by_count":0,"area":null}],"next_cursor":null}