{"total":102,"rows":[{"id":"2411.15269","title":"MambaIRv2: Attentive State Space Restoration","created":"2024-11-22","cited_by_count":94,"area":"ssm"},{"id":"2501.12352","title":"Test-time regression: a unifying framework for designing sequence models with associative memory","created":"2025-01-21","cited_by_count":74,"area":null},{"id":"2412.06590","title":"Bridging the Divide: Reconsidering Softmax and Linear Attention","created":"2024-12-09","cited_by_count":48,"area":null},{"id":"2409.02097","title":"LinFusion: 1 GPU, 1 Minute, 16K Image","created":"2024-09-03","cited_by_count":43,"area":"diffusion"},{"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":"2408.01129","title":"A Survey of Mamba","created":"2024-08-02","cited_by_count":39,"area":"ssm"},{"id":"2411.07635","title":"Breaking the Low-Rank Dilemma of Linear Attention","created":"2024-11-12","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":"2412.16112","title":"CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up","created":"2024-12-20","cited_by_count":28,"area":"diffusion"},{"id":"2408.08665","title":"QMambaBSR: Burst Image Super-Resolution with Query State Space Model","created":"2024-08-16","cited_by_count":27,"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":"2512.01643","title":"ViT$^3$: Unlocking Test-Time Training in Vision","created":"2025-12-01","cited_by_count":18,"area":null},{"id":"2411.15241","title":"EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality","created":"2024-11-22","cited_by_count":17,"area":"ssm"},{"id":"2602.01077","title":"PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers","created":"2026-02-01","cited_by_count":17,"area":"diffusion"},{"id":"2507.00698","title":"Rectifying Magnitude Neglect in Linear Attention","created":"2025-07-01","cited_by_count":16,"area":null},{"id":"2410.16746","title":"SpikMamba: When SNN meets Mamba in Event-based Human Action Recognition","created":"2024-10-22","cited_by_count":10,"area":"ssm"},{"id":"2411.15459","title":"MambaVLT: Time-Evolving Multimodal State Space Model for Vision-Language Tracking","created":"2024-11-23","cited_by_count":9,"area":"ssm"},{"id":"2505.20941","title":"PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adapter","created":"2025-05-27","cited_by_count":9,"area":"ssm"},{"id":"2411.06959","title":"ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis","created":"2024-11-11","cited_by_count":8,"area":null},{"id":"2407.06136","title":"Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning","created":"2024-07-08","cited_by_count":7,"area":"ssm"},{"id":"2503.24067","title":"TransMamba: A Sequence-Level Hybrid Transformer-Mamba Language Model","created":"2025-03-31","cited_by_count":7,"area":"ssm"},{"id":"2603.26735","title":"Distilled Large Language Model-Driven Dynamic Sparse Expert Activation Mechanism","created":"2026-03-21","cited_by_count":7,"area":"moe"},{"id":"2410.03810","title":"Exploring the Limitations of Mamba in COPY and CoT Reasoning","created":"2024-10-04","cited_by_count":6,"area":"lr"},{"id":"2501.01262","title":"Detail Matters: Mamba-Inspired Joint Unfolding Network for Snapshot Spectral Compressive Imaging","created":"2025-01-02","cited_by_count":6,"area":"ssm"},{"id":"2504.19198","title":"Adaptive Dual-domain Learning for Underwater Image Enhancement","created":"2025-04-27","cited_by_count":6,"area":null},{"id":"2505.11196","title":"DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling","created":"2025-05-16","cited_by_count":6,"area":"diffusion"},{"id":"2411.16170","title":"CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction","created":"2024-11-25","cited_by_count":5,"area":null},{"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":"2502.16249","title":"Linear Attention for Efficient Bidirectional Sequence Modeling","created":"2025-02-22","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":"2505.17637","title":"Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2505.17852","title":"Scaling Recurrent Neural Networks to a Billion Parameters with Zero-Order Optimization","created":"2025-05-23","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":"2509.18184","title":"URNet: Uncertainty-aware Refinement Network for Event-based Stereo Depth Estimation","created":"2025-09-18","cited_by_count":4,"area":null},{"id":"2511.00833","title":"Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials","created":"2025-11-02","cited_by_count":4,"area":null},{"id":"2603.16063","title":"ViT-AdaLA: Adapting Vision Transformers with Linear Attention","created":"2026-03-17","cited_by_count":4,"area":null},{"id":"2603.26380","title":"Switch Attention: Towards Dynamic and Fine-grained Hybrid Transformers","created":"2026-03-27","cited_by_count":4,"area":null},{"id":"2409.02597","title":"Rate-Adaptive Generative Semantic Communication Using Conditional Diffusion Models","created":"2024-09-04","cited_by_count":3,"area":"diffusion"},{"id":"2409.03223","title":"Why mamba is effective? Exploit Linear Transformer-Mamba Network for Multi-Modality Image Fusion","created":"2024-09-05","cited_by_count":3,"area":"ssm"},{"id":"2411.15255","title":"OSMamba: Omnidirectional Spectral Mamba with Dual-Domain Prior Generator for Exposure Correction","created":"2024-11-22","cited_by_count":3,"area":"diffusion"},{"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":"2507.04369","title":"MambaFusion: Height-Fidelity Dense Global Fusion for Multi-modal 3D Object Detection","created":"2025-07-06","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":"2509.20882","title":"On Theoretical Interpretations of Concept-Based In-Context Learning","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2509.21265","title":"MedVSR: Medical Video Super-Resolution with Cross State-Space Propagation","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2510.22197","title":"Multi-dataset Joint Pre-training of Emotional EEG Enables Generalizable Affective Computing","created":"2025-10-25","cited_by_count":3,"area":null},{"id":"2511.00907","title":"Transformers as Intrinsic Optimizers: Forward Inference through the Energy Principle","created":"2025-11-02","cited_by_count":3,"area":null},{"id":"2602.22719","title":"Interpreting and Steering State-Space Models via Activation Subspace Bottlenecks","created":"2026-02-26","cited_by_count":3,"area":"ssm"},{"id":"2603.06522","title":"Artificial Intelligence for Detecting Fetal Orofacial Clefts and Advancing Medical Education","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2604.20368","title":"LaplacianFormer:Rethinking Linear Attention with Laplacian Kernel","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2410.23738","title":"MLLA-UNet: Mamba-like Linear Attention in an Efficient U-Shape Model for Medical Image Segmentation","created":"2024-10-31","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":"2505.05397","title":"PillarMamba: Learning Local-Global Context for Roadside Point Cloud via Hybrid State Space Model","created":"2025-05-08","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":"2507.00966","title":"MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement","created":"2025-07-01","cited_by_count":2,"area":"ssm"},{"id":"2507.03340","title":"Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency","created":"2025-07-04","cited_by_count":2,"area":null},{"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":"2510.12160","title":"State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding","created":"2025-10-14","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":"2412.00776","title":"Learning Mamba as a Continual Learner: Meta-Learning Selective State Space Models for Continual Learning","created":"2024-12-01","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":"2505.14062","title":"FractalMamba++: Scaling Vision Mamba Across Resolutions via Hilbert Fractal Geometry","created":"2025-05-20","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":"2506.15940","title":"Polyline Path Masked Attention for Vision Transformer","created":"2025-06-19","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":"2507.16624","title":"A2Mamba: Attention-augmented State Space Models for Visual Recognition","created":"2025-07-22","cited_by_count":1,"area":"ssm"},{"id":"2509.24093","title":"Clebsch-Gordan Transformer: Fast and Global Equivariant Attention","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2510.24260","title":"DeshadowMamba: Deshadowing as 1D Sequential Similarity","created":"2025-10-28","cited_by_count":1,"area":"ssm"},{"id":"2511.18380","title":"RNN as Linear Transformer: A Closer Investigation into Representational Potentials of Visual Mamba Models","created":"2025-11-23","cited_by_count":1,"area":"ssm"},{"id":"2603.09138","title":"Rotation Equivariant Mamba for Vision Tasks","created":"2026-03-10","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":"2604.25570","title":"Vision SmolMamba: Spike-Guided Token Pruning for Energy-Efficient Spiking State-Space Vision Models","created":"2026-04-28","cited_by_count":1,"area":"inference"},{"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":"2608.30129","title":"Efficient and High-Quality Depth Estimation via Pixel-Space Diffusion with Linear Attention","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2412.19628","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","created":"2024-12-27","cited_by_count":0,"area":null},{"id":"2501.02040","title":"A Separable Self-attention Inspired by the State Space Model for Computer Vision","created":"2025-01-03","cited_by_count":0,"area":"ssm"},{"id":"2503.12914","title":"Efficient Multimodal 3D Object Detector via Instance-Level Contrastive Distillation","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2505.19472","title":"Balancing Computation Load and Representation Expressivity in Parallel Hybrid Neural Networks","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2507.00577","title":"BadViM: Backdoor Attack against Vision Mamba","created":"2025-07-01","cited_by_count":0,"area":"ssm"},{"id":"2508.07363","title":"Keyword Mamba: Spoken Keyword Spotting with State Space Models","created":"2025-08-10","cited_by_count":0,"area":"ssm"},{"id":"2509.22691","title":"Sequential Token Merging: Revisiting Hidden States","created":"2025-09-19","cited_by_count":0,"area":"ssm"},{"id":"2509.24358","title":"An Enhanced Pyramid Feature Network Based on Long-Range Dependencies for Multi-Organ Medical Image Segmentation","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2510.27296","title":"Versatile and Efficient Medical Image Super-Resolution Via Frequency-Gated Mamba","created":"2025-10-31","cited_by_count":0,"area":"ssm"},{"id":"2601.05527","title":"DeMa: Dual-Path Delay-Aware Mamba for Efficient Multivariate Time Series Analysis","created":"2026-01-09","cited_by_count":0,"area":"ssm"},{"id":"2602.01435","title":"BioTamperNet: Affinity-Guided State-Space Model Detecting Tampered Biomedical Images","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.04346","title":"MirrorLA: Reflecting Feature Map for Vision Linear Attention","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.00175","title":"Self-Attention And Beyond the Infinite: Towards Linear Transformers with Infinite Self-Attention","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2603.02727","title":"Gated Differential Linear Attention: A Linear-Time Decoder for High-Fidelity Medical Segmentation","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2603.05255","title":"CATNet: Collaborative Alignment and Transformation Network for Cooperative Perception","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.14816","title":"M2IR: Proactive All-in-One Image Restoration via Mamba-style Modulation and Mixture-of-Experts","created":"2026-03-16","cited_by_count":0,"area":"moe"},{"id":"2603.19563","title":"Dual-Domain Representation Alignment: Bridging 2D and 3D Vision via Geometry-Aware Architecture Search","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2603.28503","title":"Bridging the Geometry Mismatch: Frequency-Aware Anisotropic Serialization for Thin-Structure SSMs","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.18549","title":"Advancing Vision Transformer with Enhanced Spatial Priors","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.11131","title":"USEMA: a Scalable Efficient Mamba Like Attention for Medical Image Segmentation","created":"2026-05-11","cited_by_count":0,"area":"ssm"},{"id":"2605.25949","title":"Small Models, Strong Priors: Architectural Inductive Bias for Parameter-Efficient Neural PDE Solvers","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.03341","title":"Cross-Modality Feature Fusion Based on Structured State Space Duality for Multimodal Image Registration Network","created":"2026-06-02","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":"2607.14711","title":"VideoSEMA: a scalable and efficient Mamba-like attention for video understanding","created":"2026-07-16","cited_by_count":0,"area":"ssm"}],"next_cursor":"100"}