{"total":72,"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":"2203.14343","title":"Diagonal State Spaces are as Effective as Structured State Spaces","created":"2022-03-27","cited_by_count":350,"area":"ssm"},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328,"area":"ssm"},{"id":"2403.17695","title":"PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition","created":"2024-03-26","cited_by_count":141,"area":"ssm"},{"id":"2403.07487","title":"Motion Mamba: Efficient and Long Sequence Motion Generation","created":"2024-03-12","cited_by_count":112,"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":"2403.18795","title":"Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstruction","created":"2024-03-27","cited_by_count":56,"area":"ssm"},{"id":"2405.14858","title":"Mamba-R: Vision Mamba ALSO Needs Registers","created":"2024-05-23","cited_by_count":41,"area":"ssm"},{"id":"2405.15574","title":"Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models","created":"2024-05-24","cited_by_count":30,"area":"ssm"},{"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":"2412.10707","title":"MambaPro: Multi-Modal Object Re-Identification with Mamba Aggregation and Synergistic Prompt","created":"2024-12-14","cited_by_count":20,"area":"ssm"},{"id":"2404.11375","title":"Text-controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motion","created":"2024-04-17","cited_by_count":16,"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":"2411.06481","title":"KMM: Key Frame Mask Mamba for Extended Motion Generation","created":"2024-11-10","cited_by_count":16,"area":"ssm"},{"id":"2502.06438","title":"FEMBA: Efficient and Scalable EEG Analysis with a Bidirectional Mamba Foundation Model","created":"2025-02-10","cited_by_count":16,"area":"ssm"},{"id":"2406.05427","title":"Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL","created":"2024-06-08","cited_by_count":15,"area":"ssm"},{"id":"2506.10915","title":"M4V: Multimodal Mamba for Efficient Text-to-Video Generation","created":"2025-06-12","cited_by_count":12,"area":"ssm"},{"id":"2406.08234","title":"MaIL: Improving Imitation Learning with Mamba","created":"2024-06-12","cited_by_count":11,"area":"ssm"},{"id":"2502.19090","title":"EndoMamba: An Efficient Foundation Model for Endoscopic Videos via Hierarchical Pre-training","created":"2025-02-26","cited_by_count":11,"area":"ssm"},{"id":"2503.10392","title":"RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing","created":"2025-03-13","cited_by_count":11,"area":"ssm"},{"id":"2407.10374","title":"An Empirical Study of Mamba-based Pedestrian Attribute Recognition","created":"2024-07-15","cited_by_count":10,"area":"ssm"},{"id":"2410.07599","title":"Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency","created":"2024-10-10","cited_by_count":9,"area":"ssm"},{"id":"2405.20881","title":"S4Fusion: Saliency-aware Selective State Space Model for Infrared Visible Image Fusion","created":"2024-05-31","cited_by_count":8,"area":"ssm"},{"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":"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":"2501.17088","title":"Mamba-Shedder: Post-Transformer Compression for Efficient Selective Structured State Space Models","created":"2025-01-28","cited_by_count":7,"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":"2409.11513","title":"Mamba Fusion: Learning Actions Through Questioning","created":"2024-09-17","cited_by_count":5,"area":"ssm"},{"id":"2502.16214","title":"SalM$^{2}$: An Extremely Lightweight Saliency Mamba Model for Real-Time Cognitive Awareness of Driver Attention","created":"2025-02-22","cited_by_count":4,"area":"ssm"},{"id":"2505.09827","title":"Dyadic Mamba: Long-term Dyadic Human Motion Synthesis","created":"2025-05-14","cited_by_count":4,"area":"ssm"},{"id":"2506.10390","title":"DART: Differentiable Dynamic Adaptive Region Tokenizer for Vision Foundation Models","created":"2025-06-12","cited_by_count":4,"area":"ssm"},{"id":"2506.23283","title":"MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition","created":"2025-06-29","cited_by_count":4,"area":"ssm"},{"id":"2408.04916","title":"PTrajM: Efficient and Semantic-rich Trajectory Learning with Pretrained Trajectory-Mamba","created":"2024-08-09","cited_by_count":3,"area":"ssm"},{"id":"2409.08513","title":"Mamba-YOLO-World: Marrying YOLO-World with Mamba for Open-Vocabulary Detection","created":"2024-09-13","cited_by_count":3,"area":"ssm"},{"id":"2409.14403","title":"GraspMamba: A Mamba-based Language-driven Grasp Detection Framework with Hierarchical Feature Learning","created":"2024-09-22","cited_by_count":3,"area":"ssm"},{"id":"2411.00151","title":"NIMBA: Towards Robust and Principled Processing of Point Clouds With SSMs","created":"2024-10-31","cited_by_count":3,"area":"ssm"},{"id":"2503.12332","title":"VideoMAP: Toward Scalable Mamba-based Video Autoregressive Pretraining","created":"2025-03-16","cited_by_count":3,"area":"ssm"},{"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":"2510.13253","title":"End-to-End Multi-Modal Diffusion Mamba","created":"2025-10-15","cited_by_count":3,"area":"ssm"},{"id":"2408.14868","title":"ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learning","created":"2024-08-27","cited_by_count":2,"area":"ssm"},{"id":"2501.06138","title":"MS-Temba: Multi-Scale Temporal Mamba for Understanding Long Untrimmed Videos","created":"2025-01-10","cited_by_count":2,"area":"ssm"},{"id":"2503.06446","title":"M$^3$amba: CLIP-driven Mamba Model for Multi-modal Remote Sensing Classification","created":"2025-03-09","cited_by_count":2,"area":"ssm"},{"id":"2503.23121","title":"Efficient Explicit Joint-level Interaction Modeling with Mamba for Text-guided HOI Generation","created":"2025-03-29","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":"2505.12685","title":"Mamba-Adaptor: State Space Model Adaptor for Visual Recognition","created":"2025-05-19","cited_by_count":2,"area":"ssm"},{"id":"2506.23783","title":"Mamba-FETrack V2: Revisiting State Space Model for Frame-Event based Visual Object Tracking","created":"2025-06-30","cited_by_count":2,"area":"ssm"},{"id":"2403.10696","title":"On the low-shot transferability of [V]-Mamba","created":"2024-03-15","cited_by_count":1,"area":"ssm"},{"id":"2404.17235","title":"Optimizing Universal Lesion Segmentation: State Space Model-Guided Hierarchical Networks with Feature Importance Adjustment","created":"2024-04-26","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":"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":"2503.06897","title":"Multi-granular body modeling with Redundancy-Free Spatiotemporal Fusion for Text-Driven Motion Generation","created":"2025-03-10","cited_by_count":1,"area":"ssm"},{"id":"2504.15669","title":"UINO-FSS: Unifying Representation Learning and Few-shot Segmentation via Hierarchical Distillation and Mamba-HyperCorrelation","created":"2025-04-22","cited_by_count":1,"area":"ssm"},{"id":"2504.19683","title":"GPA-RAM: Grasp-Pretraining Augmented Robotic Attention Mamba for Spatial Task Learning","created":"2025-04-28","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":"2510.23043","title":"HieraMamba: Video Temporal Grounding via Hierarchical Anchor-Mamba Pooling","created":"2025-10-27","cited_by_count":1,"area":"ssm"},{"id":"2601.06891","title":"CLIMP: Contrastive Language-Image Mamba Pretraining","created":"2026-01-11","cited_by_count":1,"area":"ssm"},{"id":"2408.17081","title":"Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training","created":"2024-08-30","cited_by_count":0,"area":"ssm"},{"id":"2503.19589","title":"Prompt-Guided Dual-Path UNet with Mamba for Medical Image Segmentation","created":"2025-03-25","cited_by_count":0,"area":"ssm"},{"id":"2505.18525","title":"TK-Mamba: Marrying KAN With Mamba for Text-Driven 3D Medical Image Segmentation","created":"2025-05-24","cited_by_count":0,"area":"ssm"},{"id":"2506.19439","title":"AMF-MedIT: An Efficient Align-Modulation-Fusion Framework for Medical Image-Tabular Data","created":"2025-06-24","cited_by_count":0,"area":"ssm"},{"id":"2510.16444","title":"RefAtomNet++: Advancing Referring Atomic Video Action Recognition using Semantic Retrieval based Multi-Trajectory Mamba","created":"2025-10-18","cited_by_count":0,"area":"ssm"},{"id":"2511.13113","title":"Semantics and Content Matter: Towards Multi-Prior Hierarchical Mamba for Image Deraining","created":"2025-11-17","cited_by_count":0,"area":"ssm"},{"id":"2602.00650","title":"A Hybrid Mamba-SAM Architecture for Efficient 3D Medical Image Segmentation","created":"2026-01-31","cited_by_count":0,"area":"ssm"},{"id":"2602.11673","title":"RI-Mamba: Rotation-Invariant Mamba for Robust Text-to-Shape Retrieval","created":"2026-02-12","cited_by_count":0,"area":"ssm"},{"id":"2603.18757","title":"DA-Mamba: Learning Domain-Aware State Space Model for Global-Local Alignment in Domain Adaptive Object Detection","created":"2026-03-19","cited_by_count":0,"area":"ssm"},{"id":"2605.13202","title":"STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition","created":"2026-05-13","cited_by_count":0,"area":"ssm"},{"id":"2606.04772","title":"Coarse-to-fine Hierarchical Architecture with Sequential Mamba for Brain Reconstruction","created":"2026-06-03","cited_by_count":0,"area":"ssm"},{"id":"2607.18625","title":"Norm or Direction? Decoding Vision Mambas for High-Resolution Vision","created":"2026-07-21","cited_by_count":0,"area":"ssm"},{"id":"2607.28571","title":"Finding Change in Satellite Archives from Text: How to Combine Before-and-After Images Efficiently","created":"2026-07-30","cited_by_count":0,"area":"ssm"},{"id":"2608.07999","title":"PE-Mamba: Bidirectional Selective Layer Aggregation for AI-Generated Image Detection","created":"2026-08-08","cited_by_count":0,"area":"ssm"},{"id":"2609.21322","title":"S3VD: Semantic-Guidance Spatio-Temporal Scanning for Video Deraining","created":"2026-09-18","cited_by_count":0,"area":"ssm"},{"id":"2609.24337","title":"LiAuto-MindViT: A Hybrid Vision Backbone with Adaptive Bidirectional Mamba","created":"2026-09-21","cited_by_count":0,"area":"ssm"}],"next_cursor":null}