{"total":98,"rows":[{"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":"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":"2406.04303","title":"Vision-LSTM: xLSTM as Generic Vision Backbone","created":"2024-06-06","cited_by_count":51,"area":null},{"id":"2404.04478","title":"Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion Models","created":"2024-04-06","cited_by_count":41,"area":"diffusion"},{"id":"2407.18232","title":"LION: Linear Group RNN for 3D Object Detection in Point Clouds","created":"2024-07-25","cited_by_count":38,"area":"ssm"},{"id":"2407.11087","title":"Restore-RWKV: Efficient and Effective Medical Image Restoration with RWKV","created":"2024-07-14","cited_by_count":36,"area":null},{"id":"2505.19147","title":"Shifting AI Efficiency From Model-Centric to Data-Centric Compression","created":"2025-05-25","cited_by_count":29,"area":"mllm"},{"id":"2406.06973","title":"RWKV-CLIP: A Robust Vision-Language Representation Learner","created":"2024-06-11","cited_by_count":23,"area":null},{"id":"2502.05741","title":"Linear Attention Modeling for Learned Image Compression","created":"2025-02-09","cited_by_count":23,"area":null},{"id":"2405.15214","title":"PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learning","created":"2024-05-24","cited_by_count":21,"area":null},{"id":"2406.19369","title":"Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Model","created":"2024-06-27","cited_by_count":18,"area":"ssm"},{"id":"2410.04960","title":"On Efficient Variants of Segment Anything Model: A Survey","created":"2024-10-07","cited_by_count":16,"area":null},{"id":"2411.15941","title":"MobileMamba: Lightweight Multi-Receptive Visual Mamba Network","created":"2024-11-24","cited_by_count":16,"area":"ssm"},{"id":"2405.18425","title":"ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention","created":"2024-05-28","cited_by_count":13,"area":null},{"id":"2408.09764","title":"Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms","created":"2024-08-19","cited_by_count":12,"area":null},{"id":"2405.16504","title":"Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation","created":"2024-05-26","cited_by_count":11,"area":"ssm"},{"id":"2404.15349","title":"A Survey on Multimodal Wearable Sensor-based Human Action Recognition","created":"2024-04-14","cited_by_count":10,"area":null},{"id":"2405.13636","title":"Audio Mamba: Pretrained Audio State Space Model For Audio Tagging","created":"2024-05-22","cited_by_count":10,"area":"ssm"},{"id":"2405.21022","title":"You Only Scan Once: Efficient Multi-dimension Sequential Modeling with LightNet","created":"2024-05-31","cited_by_count":9,"area":null},{"id":"2409.19987","title":"OccRWKV: Rethinking Efficient 3D Semantic Occupancy Prediction with Linear Complexity","created":"2024-09-30","cited_by_count":9,"area":null},{"id":"2504.13112","title":"Hadamard product in deep learning: Introduction, Advances and Challenges","created":"2025-04-17","cited_by_count":9,"area":null},{"id":"2507.02591","title":"AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding","created":"2025-07-03","cited_by_count":9,"area":null},{"id":"2501.08458","title":"RWKV-UNet: Improving UNet with Long-Range Cooperation for Effective Medical Image Segmentation","created":"2025-01-14","cited_by_count":7,"area":null},{"id":"2504.10018","title":"RGB-Event based Pedestrian Attribute Recognition: A Benchmark Dataset and An Asymmetric RWKV Fusion Framework","created":"2025-04-14","cited_by_count":7,"area":null},{"id":"2412.14847","title":"A Survey of RWKV","created":"2024-12-19","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":"2505.07793","title":"Overflow Prevention Enhances Long-Context Recurrent LLMs","created":"2025-05-12","cited_by_count":6,"area":"ssm"},{"id":"2412.06674","title":"EMOv2: Pushing 5M Vision Model Frontier","created":"2024-12-09","cited_by_count":5,"area":null},{"id":"2503.21772","title":"LOCORE: Image Re-ranking with Long-Context Sequence Modeling","created":"2025-03-27","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":"2509.23316","title":"C3-OWD: A Curriculum Cross-modal Contrastive Learning Framework for Open-World Detection","created":"2025-09-27","cited_by_count":5,"area":null},{"id":"2411.05636","title":"Video RWKV:Video Action Recognition Based RWKV","created":"2024-11-08","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":"2502.15021","title":"Thicker and Quicker: A Jumbo Token for Fast Plain Vision Transformers","created":"2025-02-20","cited_by_count":4,"area":null},{"id":"2505.03803","title":"RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization","created":"2025-05-02","cited_by_count":4,"area":null},{"id":"2506.04956","title":"FEAT: Full-Dimensional Efficient Attention Transformer for Medical Video Generation","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2406.04342","title":"Learning 1D Causal Visual Representation with De-focus Attention Networks","created":"2024-06-06","cited_by_count":3,"area":null},{"id":"2407.17028","title":"Enhancing Environmental Monitoring through Multispectral Imaging: The WasteMS Dataset for Semantic Segmentation of Lakeside Waste","created":"2024-07-24","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":"2505.22195","title":"S2AFormer: Strip Self-Attention for Efficient Vision Transformer","created":"2025-05-28","cited_by_count":3,"area":null},{"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":"2511.01768","title":"UniLION: Towards Unified Autonomous Driving Model with Linear Group RNNs","created":"2025-11-03","cited_by_count":3,"area":"driving"},{"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":"2602.21712","title":"Innovative Tooth Segmentation Using Hierarchical Features and Bidirectional Sequence Modeling","created":"2026-02-25","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":"2604.20368","title":"LaplacianFormer:Rethinking Linear Attention with Laplacian Kernel","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2409.03939","title":"Experimentation in Content Moderation using RWKV","created":"2024-09-05","cited_by_count":2,"area":null},{"id":"2411.17061","title":"SCASeg: Strip Cross-Attention for Efficient Semantic Segmentation","created":"2024-11-26","cited_by_count":2,"area":null},{"id":"2412.19535","title":"StyleRWKV: High-Quality and High-Efficiency Style Transfer with RWKV-like Architecture","created":"2024-12-27","cited_by_count":2,"area":null},{"id":"2505.02705","title":"Multi-View Learning with Context-Guided Receptance for Image Denoising","created":"2025-05-05","cited_by_count":2,"area":null},{"id":"2506.11997","title":"pLSTM: parallelizable Linear Source Transition Mark networks","created":"2025-06-13","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":"2506.21185","title":"Out-of-Distribution Semantic Occupancy Prediction","created":"2025-06-26","cited_by_count":2,"area":null},{"id":"2507.03184","title":"EvRWKV: A Continuous Interactive RWKV Framework for Effective Event-Guided Low-Light Image Enhancement","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2507.11415","title":"U-RWKV: Lightweight medical image segmentation with direction-adaptive RWKV","created":"2025-07-15","cited_by_count":2,"area":null},{"id":"2507.18594","title":"DRWKV: Focusing on Object Edges for Low-Light Image Enhancement","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2512.08161","title":"Fourier-RWKV: A Multi-State Perception Network for Efficient Image Dehazing","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2411.02795","title":"The Evolution of RWKV: Advancements in Efficient Language Modeling","created":"2024-11-05","cited_by_count":1,"area":null},{"id":"2502.20852","title":"Delta-WKV: A Novel Meta-in-Context Learner for MRI Super-Resolution","created":"2025-02-28","cited_by_count":1,"area":null},{"id":"2503.22223","title":"DREMnet: An Interpretable Denoising Framework for Semi-Airborne Transient Electromagnetic Signal","created":"2025-03-28","cited_by_count":1,"area":null},{"id":"2504.01257","title":"FLAMES: A Hybrid Spiking-State Space Model for Adaptive Memory Retention in Event-Based Learning","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2510.08951","title":"FS-RWKV: Leveraging Frequency Spatial-Aware RWKV for 3T-to-7T MRI Translation","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2511.06717","title":"MRT: Learning Compact Representations with Mixed RWKV-Transformer for Extreme Image Compression","created":"2025-11-10","cited_by_count":1,"area":null},{"id":"2511.09878","title":"RWKV-PCSSC: Exploring RWKV Model for Point Cloud Semantic Scene Completion","created":"2025-11-13","cited_by_count":1,"area":null},{"id":"2601.11164","title":"SoLA-Vision: Fine-grained Layer-wise Linear Softmax Hybrid Attention","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2602.10491","title":"Towards Remote Sensing Change Detection with Neural Memory","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.19567","title":"Efficiency Follows Global-Local Decoupling","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2603.25296","title":"Towards Controllable Low-Light Image Enhancement: A Continuous Multi-illumination Dataset and Efficient State Space Framework","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2605.10341","title":"PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents","created":"2026-05-11","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":"2412.10730","title":"MAL: Cluster-Masked and Multi-Task Pretraining for Enhanced xLSTM Vision Performance","created":"2024-12-14","cited_by_count":0,"area":null},{"id":"2501.01460","title":"GDSR: Global-Detail Integration through Dual-Branch Network with Wavelet Losses for Remote Sensing Image Super-Resolution","created":"2024-12-31","cited_by_count":0,"area":null},{"id":"2503.20382","title":"RSRWKV: A Linear-Complexity 2D Attention Mechanism for Efficient Remote Sensing Vision Task","created":"2025-03-26","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":"2509.08583","title":"EfficientIML: Efficient High-Resolution Image Manipulation Localization","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2509.25998","title":"VRWKV-Editor: Reducing quadratic complexity in transformer-based video editing","created":"2025-09-30","cited_by_count":0,"area":"diffusion"},{"id":"2510.10679","title":"Synergistic Modality-and-Slice Memory Framework for Cross-Modal 3D Brain Tumor Segmentation","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2510.21479","title":"ITC-RWKV: Interactive Tissue-Cell Modeling with Recurrent Key-Value Aggregation for Histopathological Subtyping","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2511.05803","title":"MACMD: Multi-dilated Contextual Attention and Channel Mixer Decoding for Medical Image Segmentation","created":"2025-11-08","cited_by_count":0,"area":null},{"id":"2511.06741","title":"Otter: Mitigating Background Distractions of Wide-Angle Few-Shot Action Recognition with Enhanced RWKV","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2511.12270","title":"TM-UNet: Token-Memory Enhanced Sequential Modeling for Efficient Medical Image Segmentation","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2512.07884","title":"GSPN-2: Efficient Parallel Sequence Modeling","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2601.03633","title":"MFC-RFNet: A Multi-scale Guided Rectified Flow Network for Radar Sequence Prediction","created":"2026-01-07","cited_by_count":0,"area":"diffusion"},{"id":"2601.14165","title":"ASBA: A-line State Space Model and B-line Attention for Sparse Optical Doppler Tomography Reconstruction","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2602.01115","title":"KAN We Flow? Advancing Robotic Manipulation with 3D Flow Matching via KAN & RWKV","created":"2026-02-01","cited_by_count":0,"area":"diffusion"},{"id":"2602.04346","title":"MirrorLA: Reflecting Feature Map for Vision Linear Attention","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.14377","title":"LoCAtion: Long-time Collaborative Attention Framework for High Dynamic Range Video Reconstruction","created":"2026-03-15","cited_by_count":0,"area":null},{"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":"2604.06782","title":"EventFace: Event-Based Face Recognition via Structure-Driven Spatiotemporal Modeling","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.14622","title":"Multigrain-aware Semantic Prototype Scanning and Tri-Token Prompt Learning Embraced High-Order RWKV for Pan-Sharpening","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.17278","title":"PestVL-Net: Enabling Multimodal Pest Learning via Fine-grained Vision-Language Interaction","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.14926","title":"SCRWKV: Ultra-Compact Structure-Calibrated Vision-RWKV for Topological Crack Segmentation","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.00746","title":"Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.30027","title":"Cross-Modal Iteration Distillation for Robust IHD Screening: The IDNet Framework and A New Benchmark","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.21467","title":"CLUIE: Clustering-Aware Recurrent Propagation with Local Structural Compensation for Underwater Image Enhancement","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.26607","title":"FU-Mamba: A Frequency-Enhanced Dynamic Scanning Framework for Oralscan Image Segmentation","created":"2026-08-27","cited_by_count":0,"area":"ssm"},{"id":"2609.19966","title":"Beyond the Foreground: FOV-Aware Polyp Image Synthesis via Lesion-Guided Adaptive Mucosal Context Propagation","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.05191","title":"Order Matters: Competition-Guided Query Ordering for RNN-Based Object Detection","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}