{"total":143,"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":"2506.23858","title":"VMoBA: Mixture-of-Block Attention for Video Diffusion Models","created":"2025-06-30","cited_by_count":37,"area":"diffusion"},{"id":"2506.21977","title":"StableCodec: Taming One-Step Diffusion for Extreme Image Compression","created":"2025-06-27","cited_by_count":33,"area":"diffusion"},{"id":"2411.03670","title":"Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?","created":"2024-11-06","cited_by_count":31,"area":null},{"id":"2407.18559","title":"VSSD: Vision Mamba with Non-Causal State Space Duality","created":"2024-07-26","cited_by_count":29,"area":"ssm"},{"id":"2507.22412","title":"UAVScenes: A Multi-Modal Dataset for UAVs","created":"2025-07-30","cited_by_count":27,"area":null},{"id":"2406.06367","title":"MVGamba: Unify 3D Content Generation as State Space Sequence Modeling","created":"2024-06-10","cited_by_count":23,"area":"diffusion"},{"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":"2512.01643","title":"ViT$^3$: Unlocking Test-Time Training in Vision","created":"2025-12-01","cited_by_count":18,"area":null},{"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":"2510.07318","title":"Artificial Hippocampus Networks for Efficient Long-Context Modeling","created":"2025-10-08","cited_by_count":11,"area":null},{"id":"2507.12006","title":"Frequency-Dynamic Attention Modulation for Dense Prediction","created":"2025-07-16","cited_by_count":10,"area":null},{"id":"2502.12627","title":"DAMamba: Vision State Space Model with Dynamic Adaptive Scan","created":"2025-02-18","cited_by_count":9,"area":null},{"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":"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":"2512.12229","title":"Ultra-Low Bitrate Perceptual Image Compression with Shallow Encoder","created":"2025-12-13","cited_by_count":7,"area":null},{"id":"2602.17929","title":"ZACH-ViT: Regime-Dependent Inductive Bias in Compact Vision Transformers for Medical Imaging","created":"2026-02-20","cited_by_count":7,"area":null},{"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":"2406.14086","title":"Seg-LSTM: Performance of xLSTM for Semantic Segmentation of Remotely Sensed Images","created":"2024-06-20","cited_by_count":5,"area":null},{"id":"2411.16760","title":"LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions","created":"2024-11-24","cited_by_count":5,"area":null},{"id":"2412.06674","title":"EMOv2: Pushing 5M Vision Model Frontier","created":"2024-12-09","cited_by_count":5,"area":null},{"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":"2409.14617","title":"Protein-Mamba: Biological Mamba Models for Protein Function Prediction","created":"2024-09-22","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":"2504.05583","title":"Gaze-Guided Learning: Avoiding Shortcut Bias in Visual Classification","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2508.02168","title":"After the Party: Navigating the Mapping From Color to Ambient Lighting","created":"2025-08-04","cited_by_count":4,"area":null},{"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":"2511.16595","title":"TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding","created":"2025-11-20","cited_by_count":4,"area":"mllm"},{"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":"2502.18538","title":"Revisiting Convolution Architecture in the Realm of DNA Foundation Models","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2505.22195","title":"S2AFormer: Strip Self-Attention for Efficient Vision Transformer","created":"2025-05-28","cited_by_count":3,"area":null},{"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":"2509.12817","title":"SAGA: Selective Adaptive Gating for Efficient and Expressive Linear Attention","created":"2025-09-16","cited_by_count":3,"area":null},{"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":"2604.14724","title":"HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNet","created":"2026-04-16","cited_by_count":3,"area":null},{"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":"2506.21137","title":"Norm$\\times$Direction: Restoring the Missing Query Norm in Vision Linear Attention","created":"2025-06-26","cited_by_count":2,"area":null},{"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":"2511.09942","title":"AdaptViG: Adaptive Vision GNN with Exponential Decay Gating","created":"2025-11-13","cited_by_count":2,"area":null},{"id":"2511.12572","title":"Through-Foliage Surface-Temperature Reconstruction for Early Wildfire Detection","created":"2025-11-16","cited_by_count":2,"area":null},{"id":"2601.17868","title":"VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding","created":"2026-01-25","cited_by_count":2,"area":null},{"id":"2602.21591","title":"CADC: Content Adaptive Diffusion-Based Generative Image Compression","created":"2026-02-25","cited_by_count":2,"area":"diffusion"},{"id":"2604.18484","title":"XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments","created":"2026-04-20","cited_by_count":2,"area":"vla"},{"id":"2605.21308","title":"Deformba: Vision State Space Model with Adaptive State Fusion","created":"2026-05-20","cited_by_count":2,"area":null},{"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":"2408.11679","title":"BadVim: Unveiling Backdoor Threats in Visual State Space Model","created":"2024-08-21","cited_by_count":1,"area":null},{"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":"2503.24166","title":"Foundation Models For Seismic Data Processing: An Extensive Review","created":"2025-03-31","cited_by_count":1,"area":null},{"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":"2507.09294","title":"Geo-RepNet: Geometry-Aware Representation Learning for Surgical Phase Recognition in Endoscopic Submucosal Dissection","created":"2025-07-12","cited_by_count":1,"area":null},{"id":"2507.16624","title":"A2Mamba: Attention-augmented State Space Models for Visual Recognition","created":"2025-07-22","cited_by_count":1,"area":"ssm"},{"id":"2507.19807","title":"DS-Det: Single-Query Paradigm and Attention Disentangled Learning for Flexible Object Detection","created":"2025-07-26","cited_by_count":1,"area":null},{"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":"2509.23310","title":"Balanced Diffusion-Guided Fusion for Multimodal Remote Sensing Classification","created":"2025-09-27","cited_by_count":1,"area":"diffusion"},{"id":"2511.07929","title":"Federated CLIP for Resource-Efficient Heterogeneous Medical Image Classification","created":"2025-11-11","cited_by_count":1,"area":null},{"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":"2512.07078","title":"DFIR-DETR: Frequency-Domain Iterative Refinement and Dynamic Feature Aggregation for Small Object Detection","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2512.07385","title":"How Far are Modern Trackers from UAV-Anti-UAV? A Million-Scale Benchmark and New Baseline","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2602.00910","title":"Efficient Deep Learning for Medical Imaging: Bridging the Gap Between High-Performance AI and Clinical Deployment","created":"2026-01-31","cited_by_count":1,"area":null},{"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":"2606.00906","title":"hZACH-ViT: Curved Latent Geometry for Compact Vision Transformers in Low-Data Medical Imaging","created":"2026-05-30","cited_by_count":1,"area":null},{"id":"2606.01608","title":"Exploiting Semantic and Pixel Representations for Ultra-Low Bitrate Image Compression","created":"2026-06-01","cited_by_count":1,"area":"diffusion"},{"id":"2606.05999","title":"ATT-CR: Adaptive Triangular Transformer for Cloud Removal","created":"2026-06-04","cited_by_count":1,"area":null},{"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":"2408.04258","title":"UHNet: An Ultra-Lightweight and High-Speed Edge Detection Network","created":"2024-08-08","cited_by_count":0,"area":null},{"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":"2410.03174","title":"Efficient High-Resolution Visual Representation Learning with State Space Model for Human Pose Estimation","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2501.18124","title":"REMOTE: Real-time Ego-motion Tracking for Various Endoscopes via Multimodal Visual Feature Learning","created":"2025-01-30","cited_by_count":0,"area":null},{"id":"2502.07120","title":"Is Long Range Sequential Modeling Necessary For Colorectal Tumor Segmentation?","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2504.14832","title":"Protecting Your Voice: Temporal-aware Robust Watermarking","created":"2025-04-21","cited_by_count":0,"area":null},{"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":"2507.09940","title":"Long-Tailed Data Classification by Increasing and Decreasing Neurons During Training","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2507.15487","title":"DeSamba: Decoupled Spectral Adaptive Framework for 3D Multi-Sequence MRI Lesion Classification","created":"2025-07-21","cited_by_count":0,"area":null},{"id":"2508.12777","title":"SocialTrack: Multi-Object Tracking in Complex Urban Traffic Scenes Inspired by Social Behavior","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2508.17254","title":"A biological vision inspired framework for machine perception of abutting grating illusory contours","created":"2025-08-24","cited_by_count":0,"area":null},{"id":"2508.19850","title":"Image Quality Assessment for Machines: Paradigm, Large-scale Database, and Models","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2509.02575","title":"The Lifecycle Principle: Stabilizing Dynamic Neural Networks with State Memory","created":"2025-08-24","cited_by_count":0,"area":null}],"next_cursor":"100"}