Awesome-Vision-Mamba-Models

July 7, 2026 · View on GitHub

Awesome License: MIT GitHub last commit GitHub issues Arxiv Page

[NEWS.2024/11/10] The latest version of our paper (v3) is now available! This update includes numerous high-quality papers on visual Mamba.

[NEWS.2024/07/06] The updated version of our paper is now available!

[NEWS.2024/04/29] Our paper is released!

📢NOTE: If you have any questions, please don't hesitate to contact us at any of the following emails: xurui7943@gmail.com, syangcw@connect.ust.hk, ywangrm@connect.ust.hk, yu.cai@connect.ust.hk.

Mamba, a novel state space model, has gained recognition across diverse domains for its exceptional performance and efficient computational complexity. By addressing the limitations inherent in traditional visual foundation architectures, Mamba emerges as a promising contender poised to catalyze advancements in the field of computer vision.

:star: This repository hosts a curated collection of literature associated with Mamba models in computer vision. Feel free to star and fork. For further details, refer to the following paper:

Visual Mamba: A Survey and New Outlooks
Rui Xu, Shu Yang, Yihui Wang, Yu Cai, Bo Du, Hao Chen
SMART Lab, The Hong Kong University of Science and Technology

Contents

Mamba

VenuePaperFigureLinkCode
COLM 2024Mamba: Linear-Time Sequence Modeling with Selective State Spaces
LinkCode
ICML 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
LinkCode
ICLR 2026Mamba-3: Improved Sequence Modeling using State Space PrinciplesLinkCode
VenuePaperLink
Applied Sciences 2024A Survey on Visual MambaLink
Engineering Applications of AI 2025Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and ChallengesLink
IEEE TNNLS 2025Vision Mamba: A Comprehensive Survey and TaxonomyLink
ACM TIST 2026A Survey of MambaLink

Visual Mamba Backbone Networks

VenuePaperLinkCode
ICML 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space ModelLinkCode
NeurIPS 2024VMamba: Visual State Space ModelLinkCode
ECCV 2024 OralMamba-ND: Selective State Space Modeling for Multi-Dimensional DataLinkCode
ECCV 2024 WorkshopLocalMamba: Visual State Space Model with Windowed Selective ScanLinkCode
AAAI 2025EfficientVMamba: Atrous Selective Scan for Light Weight Visual MambaLinkCode
BMVC 2024PlainMamba: Improving Non-Hierarchical Mamba in Visual RecognitionLinkCode
NeurIPS 2024Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space ModelLinkCode
NeurIPS 2024Vision Mamba MenderLinkCode
NeurIPS 2024Exploring Token Pruning in Vision State Space ModelsLink
NeurIPS 2024QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space ModelLinkCode
WACV 2025PTQ4VM: Post-Training Quantization for Visual MambaLinkCode
CVPR 2025Mamba-R: Vision Mamba Also Needs RegistersLinkCode
PRICAI 2025Vim-F: Visual State Space Model Benefiting from Learning in the Frequency DomainLink
ICLR 2025Autoregressive Pretraining with Mamba in VisionLinkCode
CVPR 2025MambaVision: A Hybrid Mamba-Transformer Vision BackboneLinkCode
CVPR 2025GroupMamba: Parameter-Efficient and Accurate Group Visual State Space ModelLinkCode
ICCV 2025VSSD: Vision Mamba with Non-Causal State Space DualityLinkCode
ICML 2025Stochastic Layer-Wise Shuffle: A Stochastic Training Technique for Vision Mamba ModelsLink
AAAI 2025SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer NetworksLinkCode
ECCV 2024 WorkshopFamba-V: Fast Vision Mamba with Cross-Layer Token FusionLinkCode
IJCV 2026StableMamba: Distillation-free Scaling of Large SSMs for Images and VideosLink
CVPR 2025MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive PretrainingLinkCode
CVPR 2025Adventurer: Optimizing Vision Mamba Architecture Designs for Efficient Visual RecognitionLink
ICLR 2025Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Space DualityLinkCode
CVPR 2025EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space DualityLinkCode
CVPR 2025MobileMamba: Lightweight Multi-Receptive Visual Mamba NetworkLinkCode
ICCV 2025TinyViM: Frequency Decoupling for Tiny Hybrid Vision MambaLink
CVPR 2025GG-SSMs: Graph-Generating State Space ModelsLink
ICLR 2025MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation MethodsLinkCode
CVPR 2025DefMamba: Deformable Visual State Space ModelLink
CVPR 2025Mamba-Adaptor: State Space Model Adaptor for Visual RecognitionLink
ICCV 2025PVMamba: Parallelizing Vision Mamba via Dynamic State AggregationLink
NeurIPS 2025DAMamba: Vision State Space Model with Dynamic Adaptive ScanLinkCode
NeurIPS 2025TF-MAS: Training-free Mamba2 Architecture SearchLink
ICCV 2025OuroMamba: A Data-Free Quantization Framework for Vision MambaLink
ICASSP 2025MambaNext: An Enhanced Backbone Network with Focus Linear AttentionLink
AAAI 20262D-CrossScan Mamba: Enhancing State Space Models with Spatially Consistent Multi-Path 2D Information PropagationLink
WACV 2026Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated ProcessingLinkCode
CVPR 2026HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNetLink
ICML 2026Partial Ring Scan: Revisiting Scan Order in Vision State Space ModelsLink
ICML 2026Deformba: Vision State Space Model with Adaptive State FusionLinkCode
ICML 2026Spatial-Aware Reduction Framework: Towards Efficient and Faithful Visual State Space ModelsLink
ICML 2026SF-Mamba: Rethinking State Space Model for VisionLink
ICLR 2026Enabling True Global Perception in State Space Models for Visual TasksLink

Vision Application

Image

Natural Image

VenuePaperLinkCodeTask
ECCV 2024MambaIR: A Simple Baseline for Image Restoration with State-Space ModelLinkCodeImage Restoration
IEEE TCSVT 2025VmambaIR: Visual State Space Model for Image RestorationLinkCodeImage Restoration
ECCV 2024ZigMa: A DiT-style Zigzag Mamba Diffusion ModelLinkCodeGeneration
ACM MM 2024Learning Enriched Features via Selective State Spaces Model for Efficient Image DeblurringLinkDeblurring
IEEE TPAMI 2025Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstructionLink3D Reconstruction
NeurIPS 2024MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly DetectionLinkcodeAnomaly Detection
ACM MM 2024DGMamba: Domain Generalization via Generalized State Space ModelLinkCodeDomain Generalization
ACM MM 2024FreqMamba: Viewing Mamba from a Frequency Perspective for Image DerainingLinkCodeDeraining
MIPR 2024CU-Mamba: Selective State Space Models with Channel Learning for Image RestorationLinkImage Restoration
CVPR 2024 WorkshopDVMSR: Distillated Vision Mamba for Efficient Super-ResolutionLinkCodeSuper-Resolution
ICONIP 2024Retinexmamba: Retinex-based Mamba for Low-light Image EnhancementLinkCodeImage Enhancement
NeurIPS 2024MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State SpaceLinkCodeImage Enhancement
WACV 2025SUM: Saliency Unification through Mamba for Visual Attention ModelingLinkCodeSaliency Prediction
ECCV 2024MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based DecodersLinkCodeMulti-Task Dense Prediction
ICML 2024 WorkshopParallelizing Autoregressive Generation with Variational State Space ModelsLinkGeneration
PRCV 2024ALMRR: Anomaly Localization Mamba on Industrial Textured Surface with Feature Reconstruction and RefinementLinkCodeAnomaly Detection
NeurIPS 2024Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning MambaLinkCode3D Hand Mesh Recovery
BMVC 2024MxT: Mamba x Transformer for Image InpaintingLinkImage Inpainting
WBIR 2024 WorkshopMamba? Catch The Hype Or Rethink What Really Helps for Image RegistrationLinkCodeImage Registration
ACM MM 2024Wave-Mamba: Wavelet State Space Model for Ultra-High-Definition Low-Light Image EnhancementLinkCodeImage Enhancement
AAAI 2025ZeroMamba: Exploring Visual State Space Model for Zero-Shot LearningLinkCodeZero-Shot Learning
ICPR 2024DS MYOLO: A Reliable Object Detector Based on SSMs for Driving ScenariosLinkObject Detection
IEEE TITS 2025DSDFormer: An Innovative Transformer-Mamba Framework for Robust High-Precision Driver Distraction IdentificationLinkImage Classification
IEEE TCSVT 2025Retinex-RAWMamba: Bridging Demosaicing and Denoising for Low-Light RAW Image EnhancementLinkCodeImage Enhancement
WACV 2025Mamba-ST: State Space Model for Efficient Style TransferLinkCodeStyle Transfer
ACCV 2024OneBEV: Using One Panoramic Image for Bird's-Eye-View Semantic MappingLinkCodeBird's-Eye-View Semantic Mapping
Neurocomputing 2024MambaTSR: You only need 90k parameters for traffic sign recognitionLinkCodeImage Classification
Scientific Reports 2024Toward identity preserving in face sketch-photo synthesis using a hybrid CNN-Mamba frameworkLinkImage Synthesis
NeurIPS 2024Hybrid Mamba for Few-Shot SegmentationLinkCodeFew-Shot Segmentation
NeurIPS 2024START: A Generalized State Space Model with Saliency-Driven Token-Aware TransformationLinkCodeDomain Generalization
IJCV 2025Mamba Capsule Routing Towards Part-Whole Relational Camouflaged Object DetectionLinkCodeCamouflaged Object Detection
Automation in Construction 2024Topology-aware Mamba for Crack Segmentation in StructuresLinkCodeCrack Segmentation
ACCV 2024Wavelet-based Mamba with Fourier Adjustment for Low-light Image EnhancementLinkCodeImage Enhancement
Image and Vision Computing 2025ShadowMamba: State-Space Model with Boundary-Region Selective Scan for Shadow RemovalLinkShadow Removal
NeurIPS 2024ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure CorrectionLinkCodeExposure Correction
NeurIPS 2024DiMSUM: Diffusion Mamba -- A Scalable and Unified Spatial-Frequency Method for Image GenerationLinkCodeGeneration
ACM MM 2024Realistic Full-Body Motion Generation from Sparse Tracking with State Space ModelLinkMotion Generation
WACV 2025SEM-Net: Efficient Pixel Modelling for Image Inpainting with Spatially Enhanced SSMLinkCodeImage Inpainting
IEEE SPL 2024LFSamba: Marry SAM with Mamba for Light Field Salient Object DetectionLinkCodeSalient Object Detection
NeurIPS 2024 WorkshopDiverse capability and scaling of diffusion and auto-regressive models when learning abstract rulesLinkRule Learning/Reasoning
CVPR 2025OSMamba: Omnidirectional Spectral Mamba with Dual-Domain Prior Generator for Exposure CorrectionLinkExposure Correction
AAAI 2025Selective Visual Prompting in Vision MambaLinkCodeDomain Adaptation
IEEE TII 2025VarAD: Lightweight High-Resolution Image Anomaly Detection via Visual Autoregressive ModelingLinkCodeAnomaly Detection
CVPR 2025Efficient Visual State Space Model for Image DeblurringLinkCodeDeblurring
ACCV 2024Image Deraining with Frequency-Enhanced State Space ModelLinkDeraining
AAAI 2025Mamba YOLO: A Simple Baseline for Object Detection with State Space ModelLinkCodeObject Detection
ICML 2025FourierMamba: Fourier Learning Integration with State Space Models for Image DerainingLinkDeraining
ICML 2025QMamba: On First Exploration of Vision Mamba for Image Quality AssessmentLinkImage Quality Assessment
ACCV 2024Mamba-based Light Field Super-Resolution with Efficient Subspace ScanningLinkSuper-Resolution
ACCV 2024PixMamba: Leveraging State Space Models in a Dual-Level Architecture for Underwater Image EnhancementLinkCodeImage Enhancement
AAAI 2025Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN NetworkLink3D Human Pose Estimation
AAAI 2025PoseMamba: Monocular 3D Human Pose Estimation with Bidirectional Global-Local Spatio-Temporal State Space ModelLink3D Human Pose Estimation
IEEE TIFS 2026Neural Architecture Search-Based Global–Local Vision Mamba for Palm-Vein RecognitionLinkPalm-Vein Recognition
CVPR 2025QMambaBSR: Burst Image Super-Resolution with Query State Space ModelLinkCodeSuper-Resolution
IEEE TPAMI 2025MTMamba++: Enhancing Multi-Task Dense Scene Understanding via Mamba-Based DecodersLinkMulti-Task Dense Prediction
ICLR 2025MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for MambaLinkParameter-Efficient Fine-Tuning
CVPR 2025Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear TransformationLinkParameter-Efficient Fine-Tuning
CVPR 2025MambaIRv2: Attentive State Space RestorationLinkCodeImage Restoration
CVPR 2025 WorkshopXYScanNet: An Interpretable State Space Model for Perceptual Image DeblurringLinkDeblurring
ICASSP 2025ViM-Disparity: Bridging the Gap of Speed, Accuracy and Memory for Disparity Map GenerationLinkCodeDepth Estimation
CVPR 2025MaIR: A Locality- and Continuity-Preserving Mamba for Image RestorationLinkCodeImage Restoration
WACV 2025EDMB: Edge Detector with MambaLinkCodeEdge Detection
ACM MM 2025WMamba: Wavelet-based Mamba for Face Forgery DetectionLinkForgery Detection
IEEE TIP 2025UniUIR: Considering Underwater Image Restoration as An All-in-One LearnerLinkImage Restoration
CVPR 2025 HighlightMamba as a Bridge: Where VFMs Meet VLMs for Domain-Generalized Semantic SegmentationLinkCodeSemantic Segmentation
CVPR 2025Mesh Mamba: A Unified State Space Model for Saliency PredictionLinkSaliency Prediction
CVPR 2025MambaIC: State Space Models for High-Performance Learned Image CompressionLinkCodeImage Compression
CVPR 2025MambaFlow: A Mamba-Centric Architecture for End-to-End Optical Flow EstimationLinkOptical Flow Estimation
CVPR 2025JamMa: Ultra-lightweight Local Feature Matching with Joint MambaLinkFeature Matching
CVPR 2025Enhancing Online Continual Learning with Plug-and-Play State Space ModelLinkContinual Learning
ICCV 2025MambaML: Exploring State Space Models for Multi-Label Image ClassificationLinkMulti-Label Classification
ICCV 2025Cassic: Towards Content-Adaptive State-Space Models for Learned Image CompressionLinkImage Compression
ICCV 2025EAMamba: Efficient All-Around Vision State Space Model for Image RestorationLinkImage Restoration
ICCV 2025MeshMamba: State Space Models for Articulated 3D Mesh Generation and ReconstructionLink3D Human Mesh Recovery
IJCAI 2025Directing Mamba to Complex Textures: An Efficient Texture-Aware State Space Model for Image RestorationLinkImage Restoration
ACM MM 2025DeflareMamba: Hierarchical Vision Mamba for Contextually Consistent Lens Flare RemovalLinkCodeImage Restoration
ACM MM 2025UIS-Mamba: Exploring Mamba for Underwater Instance SegmentationLinkCodeInstance Segmentation
AAAI 2025SalM²: An Extremely Lightweight Saliency Mamba Model for Real-Time Cognitive Awareness of Driver AttentionLinkSaliency Prediction
CVPR 2025SCSegamba: Lightweight Structure-Aware Vision Mamba for Crack Segmentation in StructuresLinkCrack Segmentation
CVPR 2025Binarized Mamba-Transformer for Lightweight Quad Bayer HybridEVS DemosaicingLinkImage Demosaicing
IJCAI 2025Omni-Dimensional State Space Model-driven SAM for Pixel-level Anomaly DetectionLinkAnomaly Detection
ACM MM 2025ACMamba: Fast Unsupervised Anomaly Detection via An Asymmetrical Consensus State Space ModelLinkAnomaly Detection
IEEE Transactions on Cybernetics 2025Parameter Aware Mamba Model for Multi-task Dense PredictionLinkMulti-Task Dense Prediction
ICASSP 2025ICAA-Mamba: Vision Mamba for Image Color Aesthetics AssessmentLinkImage Quality Assessment
ICASSP 2025Cross-Modality Fusion Mamba for All-in-One Extreme Weather-Degraded Image RestorationLinkImage Restoration
ICASSP 2025EPI-Mamba: State Space Model for Semantic Segmentation from Light FieldsLinkSemantic Segmentation
ICASSP 2025MambaInst: Lightweight State Space Model for Real-Time Instance SegmentationLinkInstance Segmentation
ICASSP 2025Vision Mamba-Based Approach for Incomplete Boundary Document Image RectificationLinkImage Restoration
ICASSP 2025HandS3C: 3D Hand Mesh Reconstruction with State Space Spatial Channel Attention from RGB ImagesLink3D Hand Mesh Recovery
ICASSP 2025InsectMamba: State Space Model with Adaptive Composite Features for Insect RecognitionLinkImage Classification
ICASSP 2025StereoMamba: Enhancing Stereo Image Super-Resolution with Structured State Space Models and Bi-Directional Cross AttentionLinkSuper-Resolution
ICASSP 2025MS-RainMamba: Learning Multi-Scale State Space Models for Single Image DerainingLinkDeraining
ICASSP 2025RestorMamba: An Enhanced Synergistic State Space Model for Image RestorationLinkImage Restoration
ICASSP 2025 OralFirst-order State Space Model for Lightweight Image Super-resolutionLinkSuper-Resolution
ECAI 2025DA-Mamba: Domain Adaptive Hybrid Mamba-Transformer Based One-Stage Object DetectionLinkCodeObject Detection
AAAI 2026Depth-Synergized Mamba Meets Memory Experts for All-Day Image Reflection SeparationLinkImage Restoration
AAAI 2026Rectification Reimagined: A Unified Mamba Model for Image Correction and Rectangling with PromptsLinkImage Correction
AAAI 2026Disentangled Hypergraph-Guided Mamba Scanning for Fine-Grained Visual RecognitionLinkImage Classification
ICLR 2026WIMFRIS: WIndow Mamba Fusion and Parameter Efficient Tuning for Referring Image SegmentationLinkReferring Image Segmentation
ICLR 2026Content-Aware Mamba for Learned Image CompressionLinkImage Compression
WACV 2026DF-Mamba: Deformable State Space Modeling for 3D Hand Pose Estimation in InteractionsLink3D Hand Pose Estimation
WACV 2026SasMamba: A Lightweight Structure-Aware Stride State Space Model for 3D Human Pose EstimationLink3D Human Pose Estimation
WACV 2026Forensim: Can Image Splicing and Copy-Move Forgery Be Detected by the Same Model? An Attention-Based State-Space ApproachLinkForgery Detection
WACV 2026D2Mamba: Dual Domain Guided Informed Search in State Space Model for Underwater Image EnhancementLinkImage Enhancement
WACV 2026From Darkness to Detail: Frequency-Aware SSMs for Low-Light VisionLinkCodeImage Enhancement
WACV 2026Codebook Knowledge with Mamba-Transformer For Low-Light Image EnhancementLinkImage Enhancement
CVPR 2026DA-Mamba: Learning Domain-Aware State Space Model for Global-Local Alignment in Domain Adaptive Object DetectionLinkObject Detection
CVPR 2026MambaSIC: Mamba-based Stereo Image Compression with Bi-directional Multi-reference Entropy ModelLinkImage Compression
CVPR 2026MambaCS: Multi-Scale Gradient-Guided Unrolling Architecture with Adaptive Mamba for Compressive SensingLinkCodeCompressive Sensing
CVPR 2026MixerCSeg: An Efficient Mixer Architecture for Crack Segmentation via Decoupled Mamba AttentionLinkCodeCrack Segmentation
CVPR 2026CrackSSM: Reviving SSMs for Crack Segmentation via Dynamic ScanningLinkCrack Segmentation
CVPR 2026AKCMamba-YOLO: Selective State Space Models For Real-Time Object DetectionLinkObject Detection
CVPR 2026SSM-Aware Token-Efficient VMamba via Adaptive Patch Pruning and Merging for Person Re-IdentificationLinkPerson Re-Identification
CVPR 2026Scalable Feature Matching via State Space Modeling and Sparse CorrelationLinkCodeFeature Matching
CVPR 2026 FindingsQ-MambaIR: Accurate Quantized Mamba for Efficient Image RestorationLinkImage Restoration
ICASSP 2026STYMAM: A Mamba-Based Generator for Artistic Style TransferLinkStyle Transfer
ICASSP 2026Light Field Image Super-Resolution with Multi-Scale Context Aggregation MambaLinkSuper-Resolution
ECCV 2026MambaRaw: Selective State Space Modeling for Efficient 4K Raw Image ReconstructionLinkCodeImage Reconstruction

Remote Sensing Image

VenuePaperLinkCodeTask
IEEE TGRS 2024MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target DetectionLinkCodeObject Detection
IEEE GRSL 2024RSMamba: Remote Sensing Image Classification with State Space ModelLinkCodeRemote Sensing Image Classification
Heliyon 2024Samba: Semantic Segmentation of Remotely Sensed Images with State Space ModelLinkCodeSemantic Segmentation
IEEE GRSL 2024RS3Mamba: Visual State Space Model for Remote Sensing Images Semantic SegmentationLinkCodeSemantic Segmentation
IEEE TGRS 2025RS-Mamba for Large Remote Sensing Image Dense PredictionLinkCodeSemantic Segmentation
IEEE TGRS 2024ChangeMamba: Remote Sensing Change Detection with Spatio-Temporal State Space ModelLinkCodeChange Detection
IEEE TGRS 2024SSUMamba: Spatial-Spectral Selective State Space Model for Hyperspectral Image DenoisingLinkCodeHyperspectral Image Denoising
IEEE TMM 2024Frequency-Assisted Mamba for Remote Sensing Image Super-ResolutionLinkCodeSuper-Resolution
IEEE TGRS 2025GraphMamba: An Efficient Graph Structure Learning Vision Mamba for Hyperspectral Image ClassificationLinkCodeHyperspectral Image Classification
IEEE TGRS 2025DMM: Disparity-guided Multispectral Mamba for Oriented Object Detection in Remote SensingLinkCodeOriented Object Detection
IEEE TGRS 2025HTD-Mamba: Efficient Hyperspectral Target Detection with Pyramid State Space ModelLinkCodeHyperspectral Target Detection
IEEE TGRS 2025DualMamba: A Lightweight Spectral-Spatial Mamba-Convolution Network for Hyperspectral Image ClassificationLinkHyperspectral Image Classification
IEEE TGRS 2025CDMamba: Incorporating Local Clues Into Mamba for Remote Sensing Image Binary Change DetectionLinkCodeChange Detection
IEEE TGRS 20253DSS-Mamba: 3D-Spectral-Spatial Mamba for Hyperspectral Image ClassificationLinkHyperspectral Image Classification
Neurocomputing 2025Mamba-in-Mamba: Centralized Mamba-Cross-Scan in Tokenized Mamba Model for Hyperspectral Image ClassificationLinkCodeHyperspectral Image Classification
IEEE JSTARS 2024Rethinking Scanning Strategies with Vision Mamba in Semantic Segmentation of Remote Sensing Imagery: An Experimental StudyLinkSemantic Segmentation
IEEE TGRS 2024MambaHSI: Spatial–Spectral Mamba for Hyperspectral Image ClassificationLinkCodeHyperspectral Image Classification
Remote Sensing Letters 2025Multi-head Spatial-Spectral Mamba for Hyperspectral Image ClassificationLinkCodeHyperspectral Image Classification
IEEE GRSL 2024WaveMamba: Spatial-Spectral Wavelet Mamba for Hyperspectral Image ClassificationLinkCodeHyperspectral Image Classification
Neurocomputing 2025Spatial-Spectral Morphological Mamba for Hyperspectral Image ClassificationLinkCodeHyperspectral Image Classification
IEEE GRSL 2024UNetMamba: An Efficient UNet-Like Mamba for Semantic Segmentation of High-Resolution Remote Sensing ImagesLinkCodeSemantic Segmentation
IEEE GRSL 2024MambaFormerSR: A Lightweight model for Remote-Sensing Image Super-ResolutionLinkSuper-Resolution
Scientific Reports 2024YOLOv5_mamba: unmanned aerial vehicle object detection based on bidirectional dense feedback network and adaptive gate feature fusionLinkCodeObject Detection
ECML/PKDD 2024 WorkshopA Deep Learning-Based Approach for Mangrove MonitoringLinkCodeSemantic Segmentation
IEEE TGRS 2024HyperMamba: A Spectral-Spatial Adaptive Mamba for Hyperspectral Image ClassificationLinkCodeHyperspectral Image Classification
ACM MM 2024VmambaSCI: Dynamic Deep Unfolding Network with Mamba for Compressive Spectral ImagingLinkSpectral Compressive Imaging
IEEE TGRS 2024ConMamba: CNN and SSM High-Performance Hybrid Network for Remote Sensing Change DetectionLinkChange Detection
IEEE TGRS 2024A Novel Remote Sensing Image Change Detection Approach Based on Multi-level State Space ModelLinkCodeChange Detection
IEEE TGRS 2024Dynamic Token Augmentation Mamba for Cross-Scene Classification of Hyperspectral ImageLinkCodeHyperspectral Image Classification
IEEE GRSL 2024PPMamba:Enhancing Semantic Segmentation in Remote Sensing Imagery by SS2DLinkCodeSemantic Segmentation
AAAI 2025Detail Matters: Mamba-Inspired Joint Unfolding Network for Snapshot Spectral Compressive ImagingLinkCodeSpectral Compressive Imaging
IGARSS 2025Mamba-MOC: A Multicategory Remote Object Counting via State Space ModelLinkCodeObject Counting
IEEE TGRS 2025S2Mamba: A Spatial-spectral State Space Model for Hyperspectral Image ClassificationLinkHyperspectral Image Classification
Remote Sensing 2024Spectral-Spatial Mamba for Hyperspectral Image ClassificationLinkHyperspectral Image Classification
WACV 2025A Mamba-based Siamese Network for Remote Sensing Change DetectionLinkChange Detection
IEEE TGRS 2025MSFMamba: Multi-Scale Feature Fusion State Space Model for Multi-Source Remote Sensing Image ClassificationLinkRemote Sensing Image Classification
IEEE TGRS 2025IGroupSS-Mamba: Interval Group Spatial–Spectral Mamba for Hyperspectral Image ClassificationLinkHyperspectral Image Classification
IGARSS 2025SITSMamba for Crop Classification based on Satellite Image Time SeriesLinkCodeRemote Sensing Image Classification
ICASSP 2025UV-Mamba: A DCN-Enhanced State Space Model for Urban Village Boundary Identification in High-Resolution Remote Sensing ImagesLinkSemantic Segmentation
ICASSP 2026RemoteDet-Mamba: A Hybrid Mamba-CNN Network for Multi-modal Object Detection in Remote Sensing ImagesLinkObject Detection
IGARSS 2025WSSM: Geographic-enhanced hierarchical state-space model for global station weather forecastLinkWeather Forecasting
IEEE GRSL 2025CDxLSTM: Boosting Remote Sensing Change Detection With Extended Long Short-Term MemoryLinkCodeChange Detection
IEEE TGRS 2025IRSRMamba: Infrared Image Super-Resolution via Mamba-based Wavelet Transform Feature Modulation ModelLinkCodeSuper-Resolution
AAAI 2025DehazeMamba: SAR-guided Optical Remote Sensing Image Dehazing with Adaptive State SpaceLinkCodeDehazing
IJCAI 2025HSRMamba: Contextual Spatial-Spectral State Space Model for Single Hyperspectral Image Super-ResolutionLinkCodeSuper-Resolution
NeurIPS 2025RoMA: Scaling up Mamba-based Foundation Models for Remote SensingLinkRemote Sensing Foundation Model
IEEE TGRS 2025Wavelet-Assisted Mamba for Satellite-Derived Sea Surface Temperature Super-ResolutionLinkSuper-Resolution
IJCAI 2025VimGeo: Efficient Cross-View Geo-Localization with Vision Mamba ArchitectureLinkCodeGeo-Localization
IJCAI 2025DPMamba: Distillation Prompt Mamba for Multimodal Remote Sensing Image Classification with Missing ModalitiesLinkRemote Sensing Image Classification
ICASSP 2025SSRMamba: Efficient Visual State Space Model for Spectral Super-ResolutionLinkSuper-Resolution
ICASSP 2025SSFMamba: Spatial-Spectral Fusion State Space Model for PansharpeningLinkPansharpening
AAAI 2026MFmamba: A Multi-function Network for Panchromatic Image Resolution Restoration Based on State-Space ModelLinkPansharpening
AAAI 2026M3SR: Multi-Scale Multi-Perceptual Mamba for Efficient Spectral ReconstructionLinkHyperspectral Reconstruction
AAAI 2026MMMamba: A Versatile Cross-Modal in Context Fusion Framework for Pan-Sharpening and Zero-Shot Image EnhancementLinkPansharpening
WACV 2026DMS2F-HAD: A Dual-branch Mamba-based Spatial-Spectral Fusion Network for Hyperspectral Anomaly DetectionLinkCodeHyperspectral Anomaly Detection
ICASSP 2026SAR Ship Wake Detection Based on Siamese Network with Mamba Cross-Domain Feature FusionLinkObject Detection

Medical Image

VenuePaperLinkCodeTask
MICCAI 2024SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image SegmentationLinkCode3D Medical Segmentation
ISBI 2025nnMamba: 3D Biomedical Image Segmentation, Classification and Landmark Detection with State Space ModelLinkCode3D Medical Segmentation
ACM TOMCCAP 2025VM-UNet: Vision Mamba UNet for Medical Image SegmentationLinkCode2D Medical Segmentation
MICCAI 2024Swin-UMamba: Mamba-based UNet with ImageNet-based pretrainingLinkCode2D Medical Segmentation
KBS 2024Semi-Mamba-UNet: Pixel-Level Contrastive Cross-Supervised Visual Mamba-based UNet for Semi-Supervised Medical Image SegmentationLinkCode2D Medical Segmentation
BIBM 2024MamMIL: Multiple Instance Learning for Whole Slide Images with State Space ModelsLinkCancer Subtyping
MICCAI 2024MambaMIL: Enhancing Long Sequence Modeling with Sequence Reordering in Computational PathologyLinkCodeCancer Subtyping/Survival Prediction
MICCAI 2024LKM-UNet: Large Kernel Vision Mamba UNet for Medical Image SegmentationLinkCode2D Medical Segmentation
BIBM 2024MD-Dose: A diffusion model based on the Mamba for radiation dose predictionLinkCodeRadiation Dose Prediction
ISBRA 2024VM-UNET-V2 Rethinking Vision Mamba UNet for Medical Image SegmentationLinkCode2D Medical Segmentation
Neurocomputing 2025H-vmunet: High-order Vision Mamba UNet for Medical Image SegmentationLinkCode2D Medical Segmentation
MIDL 2024ViM-UNet: Vision Mamba for Biomedical SegmentationLinkCode2D Medical Segmentation
MICCAI 2024nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image SegmentationLinkCode3D Medical Segmentation
CVPR 2024 WorkshopVim4Path: Self-Supervised Vision Mamba for Histopathology ImagesLinkCodeCancer Subtyping
MIPR 2024UU-Mamba: Uncertainty-aware U-Mamba for Cardiac Image SegmentationLink3D Medical Segmentation
MICCAI 2024 OralCardiovascular Disease Detection from Multi-View Chest X-rays with BI-MambaLinkCodeRisk Prediction
Scientific Reports 2025Combining Graph Neural Network and Mamba to Capture Local and Global Tissue Spatial Relationships in Whole Slide ImagesLinkCodeCancer Subtyping/Survival Prediction
WACV 2025Convolution and Attention-Free Mamba-based Cardiac Image SegmentationLinkCode2D Medical Segmentation
BMVC 2024On Evaluating Adversarial Robustness of Volumetric Medical Segmentation ModelsLinkCode3D Medical Segmentation
MICCAI 2024 WorkshopVision Mamba for Classification of Breast Ultrasound ImagesLinkMedical Image Classification
MICCAI 2024Deform-Mamba Network for MRI Super-ResolutionLinkSuper-Resolution
ICPR 2024Self-Prior Guided Mamba-UNet Networks for Medical Image Super-ResolutionLinkSuper-Resolution
KDD Workshop 2024State Space Model-based Classification of Major Depressive Disorder Across Multiple Imaging SitesLinkMedical Image Classification
MICCAI 2024ShapeMamba-EM: Fine-Tuning Foundation Model with Local Shape Descriptors and Mamba Blocks for 3D EM Image SegmentationLink3D Medical Segmentation
ICME 2025MambaMIC: An Efficient Baseline for Microscopic Image Classification with State Space ModelsLinkCodeMedical Image Classification
ICASSP 2025SX-Stitch: An Efficient VMS-UNet Based Framework for Intraoperative Scoliosis X-Ray Image StitchingLinkMedical Image Stitching
ICASSP 2025MpoxMamba: A Grouped Mamba-based Lightweight Hybrid Network for Mpox DetectionLinkCodeMedical Image Classification
Scientific Reports 2024A mixed Mamba U-net for prostate segmentation in MR imagesLink3D Medical Segmentation
IEEE TMI 2025Serp-Mamba: Advancing High-Resolution Retinal Vessel Segmentation with Selective State-Space ModelLink2D Medical Segmentation
MICCAI 2024Tri-Plane Mamba: Efficiently Adapting Segment Anything Model for 3D Medical ImagesLinkCode3D Medical Segmentation
ACCV 2024 WorkshopSkinMamba: A Precision Skin Lesion Segmentation Architecture with Cross-Scale Global State Modeling and Frequency Boundary GuidanceLinkCode2D Medical Segmentation
IEEE Sensors Journal 2025SPRMamba: Surgical Phase Recognition for Endoscopic Submucosal Dissection with MambaLinkSurgical Phase Recognition
WACV 2025MambaRecon: MRI Reconstruction with Structured State Space ModelsLinkCodeImage Reconstruction
MICCAI 2024EM-Net: Efficient Channel and Frequency Learning with Mamba for 3D Medical Image SegmentationLinkCode3D Medical Segmentation
MICCAI 2024MetaUNETR: Rethinking Token Mixer Encoding for Efficient Multi-organ SegmentationLinkCode3D Medical Segmentation
MICCAI 2024PathMamba: Weakly Supervised State Space Model for Multi-class Segmentation of Pathology ImagesLinkCode2D Medical Segmentation
MICCAI 2024Efficient and Gender-adaptive Graph Vision Mamba for Pediatric Bone Age AssessmentLinkCodeBone Age Assessment
MICCAI 2024Polyp-Mamba: Polyp Segmentation with Visual MambaLinkPolyp Segmentation
IEEE TMI 2024Unleash the Power of State Space Model for Whole Slide Image with Local Aware Scanning and Importance ResamplingLinkCodeCancer Subtyping/Survival Prediction
IEEE TMI 2024Swin-UMamba+: Adapting Mamba-based vision foundation models for medical image segmentationLinkCode2D & 3D Medical Segmentation
AAAI 2025S3Mamba: Small-Size-Sensitive Mamba for Lesion SegmentationLinkCode2D Medical Segmentation
ICME 2025HCMA-UNet: A Hybrid CNN-Mamba UNet with Axial Self-Attention for Efficient Breast Cancer SegmentationLinkCode3D Medical Segmentation
IEEE TMI 2025Merging Context Clustering with Visual State Space Models for Medical Image SegmentationLinkCode2D Medical Segmentation
ISBI 2025GLFC: Unified Global-Local Feature and Contrast Learning with Mamba-Enhanced UNet for Synthetic CT Generation from CBCTLinkCodeImage Synthesis
IEEE TCSVT 2025DH-Mamba: Exploring Dual-Domain Hierarchical State Space Models for MRI ReconstructionLinkCodeImage Reconstruction
IEEE TCSS 2025MSV-Mamba: A Multiscale Vision Mamba Network for Echocardiography SegmentationLink2D Medical Segmentation
Information Fusion 2025Polyp-Mamba: A Hybrid Multi-Frequency Perception Gated Selection Network for polyp segmentationLinkPolyp Segmentation
Patterns 2025UltraLight VM-UNet: Parallel Vision Mamba Significantly Reduces Parameters for Skin Lesion SegmentationLinkCode2D Medical Segmentation
IEEE TMM 2026T-Mamba: A Unified Framework with Long-Range Dependency in Dual-Domain for 2D & 3D Tooth SegmentationLinkCode2D & 3D Medical Segmentation
MICCAI 2025Sparse Reconstruction of Optical Doppler Tomography with Alternative State Space ModelLinkImage Reconstruction
Exploration of Medicine 2025MUCM-Net: A Mamba Powered UCM-Net for Skin Lesion SegmentationLinkCode2D Medical Segmentation
ICCV 2025TokenUnify: Scaling Up Autoregressive Pretraining for Neuron SegmentationLink3D Medical Segmentation
IEEE JBHI 2025SliceMamba with Neural Architecture Search for Medical Image SegmentationLink2D Medical Segmentation
MIA 2025MambaMIM: Pre-training Mamba with State Space Token InterpolationLinkCodeMedical Image Pre-training
RECOMB 2025Hierarchical Spatio-Temporal State-Space Modeling for fMRI AnalysisLinkfMRI Analysis
BIBM 2024MSVM-UNet: Multi-Scale Vision Mamba UNet for Medical Image SegmentationLinkCode2D Medical Segmentation
ICASSP 2025OCTAMamba: A State-Space Model Approach for Precision OCTA Vascularization SegmentationLinkVessel Segmentation
Information Fusion 2026MambaEviScrib: Mamba and Evidence-Guided Consistency Enhance CNN Robustness for Scribble-Supervised Medical Image SegmentationLink2D Medical Segmentation
CMIG 2025CT-Mamba: A Hybrid Convolutional State Space Model for Low-Dose CT DenoisingLinkDenoising
International Journal of Imaging Systems and Technology 2025Advancing Efficient Brain Tumor Multi‑Class Classification: New Insights From the Vision Mamba Model in Transfer LearningLinkMedical Image Classification
IEEE RA-L 2025MambaXCTrack: Mamba-Based Tracker With SSM Cross-Correlation and Motion Prompt for Ultrasound Needle TrackingLinkNeedle Tracking
WACV 2025SAM-Mamba: Mamba Guided SAM Architecture for Generalized Zero-Shot Polyp SegmentationLinkCodePolyp Segmentation
CVPR 2025Unsupervised Foundation Model-Agnostic Slide-Level Representation LearningLinkSlide-Level Representation Learning
CVPR 20252DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image ClassificationLinkCodeMedical Image Classification
ICCKE 2024Segmentation of Coronary Artery Stenosis in X-ray Angiography using Mamba ModelLink2D Medical Segmentation
MICCAI 2025Surface Vision Mamba: Leveraging Bidirectional State Space Model for Efficient Spherical Manifold RepresentationLinkCodeSpherical Manifold Representation
CVPR 2025M3amba: Memory Mamba is All You Need for Whole Slide Image ClassificationLinkCancer Subtyping
CVPR 2025Cross-Modal Interactive Perception Network with Mamba for Lung Tumor Segmentation in PET-CT ImagesLinkCodeTumor Segmentation
ICCV 2025 OralGMMamba: Group Masking Mamba for Whole Slide Image ClassificationLinkCancer Subtyping
ICCV 2025STDDNet: Harnessing Mamba for Video Polyp Segmentation via Spatial-aligned Temporal Modeling and Discriminative Dynamic Representation LearningLinkCodePolyp Segmentation
NeurIPS 2025Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image SegmentationLinkCode3D Medical Segmentation
MICCAI 2025HybridMamba: A Dual-domain Mamba for 3D Medical Image SegmentationLink3D Medical Segmentation
MICCAI 2025XFMamba: Cross-Fusion Mamba for Multi-View Medical Image ClassificationLinkCodeMedical Image Classification
MICCAI 2025DASMamba: Directional Adaptive Shuffle-Based Visual State-Space Models for Medical Image RestorationLinkCodeImage Restoration
MICCAI 2025PolyMamba: Spatial-prior Guided Mamba for Polyp SegmentationLinkPolyp Segmentation
MICCAI 2025CRAViM: Hybrid State-Space Models and Denoising Training for Unpaired Medical Image SynthesisLinkCodeImage Synthesis
MICCAI 2025Knowledge-guided Multi-scale Graph Mamba for Whole Slide Image ClassificationLinkCancer Subtyping
MICCAI 2025IM-Fuse: A Mamba-based Fusion Block for Brain Tumor Segmentation with Incomplete ModalitiesLinkCode3D Medical Segmentation
MICCAI 2025A New Paradigm for Low-dose PET/CT Reconstruction with Mamba-powered Progressive NetworkLinkImage Reconstruction
MICCAI 2025BrainMT: A Hybrid Mamba-Transformer Architecture for Modeling Long-Range Dependencies in Functional MRI DataLinkfMRI Analysis
MICCAI 2025Dual Correlation-aware Mamba for Microvascular Obstruction Identification in Non-contrast Cine Cardiac Magnetic ResonanceLinkCodeMedical Image Analysis
MICCAI 2025EndoMamba: An Efficient Foundation Model for Endoscopic Videos via Hierarchical Pre-trainingLinkMedical Image Analysis
IEEE TMI 2025Diversity-enhanced Collaborative Mamba for Semi-supervised Medical Image SegmentationLink2D & 3D Medical Segmentation
ACM MM 2025Unified Medical Image Segmentation with State Space Modeling SnakeLink2D Medical Segmentation
IEEE TIP 2025COMMA: Coordinate-aware Modulated Mamba Network for 3D Dispersed Vessel SegmentationLinkVessel Segmentation
IEEE TMI 2025Mamba-Sea: A Mamba-based Framework with Global-to-Local Sequence Augmentation for Generalizable Medical Image SegmentationLinkCode2D Medical Segmentation
MICCAI 2025MrTrack: Register Mamba for Needle Tracking with Rapid Reciprocating Motion during Ultrasound-Guided Aspiration BiopsyLinkNeedle Tracking
MICCAI 2025U-Mamba2: Scaling State Space Models for Dental Anatomy Segmentation in CBCTLink3D Medical Segmentation
BMVC 2025CellMamba: Adaptive Mamba for Accurate and Efficient Cell DetectionLinkCell Detection
MICCAI 2025 WorkshopAMD-Mamba: A Phenotype-Aware Multi-Modal Framework for Robust AMD PrognosisLinkRisk Prediction
MICCAI 2025 WorkshopPUUMA: Functional MRI Prediction of Gestational Age at Birth and Preterm RiskLinkfMRI Analysis
ICASSP 2025MDN: Mamba-Driven Dualstream Network for Medical Hyperspectral Image SegmentationLink2D Medical Segmentation
BIBM 2025MedMamba-YOLO: A Vision State Space Model for Medical Image DetectionLinkCodeMedical Image Analysis
BIBM 2025ConSSM-GAN: A Contrastive and State-Space Enhanced GAN for MR-to-CT Pelvic Image TranslationLinkImage Synthesis
BIBM 2025SWinMamba: Serpentine Window State Space Model for Vascular SegmentationLinkVessel Segmentation
BIBM 2025DB-MSMUNet: Dual Branch Multi-Scale Mamba UNet for Pancreatic CT Scans SegmentationLink2D Medical Segmentation
BIBM 2025Bridging the Perception-Cognition Gap: Re-Engineering SAM2 with Hilbert-Mamba for Robust VLM-Based Medical DiagnosisLinkMedical Image Analysis
BIBM 2025BC-Mamba: Boundary-Aware Contextual CNNs-Mamba for Accurate Ultrasound Image SegmentationLink2D Medical Segmentation
BIBM 2025MorphMamba: A Global Context-Aware Mamba for Volumetric Multi-Organ SegmentationLink3D Medical Segmentation
BIBM 2025Spatiotemporal Uncertainty-Aware Mamba-Transformer Synergy: Breast Cancer Detection in ABUSLinkTumor Segmentation
BIBM 2025MM-UNet: Morph Mamba U-Shaped Convolutional Networks for Retinal Vessel SegmentationLinkVessel Segmentation
BIBM 2025Wavelet Multi-Dimensional and Mamba-Guided Semantic Graph Feature Fusion Network for Glioma GradingLinkMedical Image Classification
BIBM 2025Versatile and Efficient Medical Image Super-Resolution Via Frequency-Gated MambaLinkSuper-Resolution
BIBM 2025E-ViM3: Mamba-3D as Masked Autoencoders for Accurate and Data-Efficient Analysis of Medical Ultrasound VideosLinkMedical Image Analysis
ICASSP 2025SFma-Unet: A Mamba-Based Spatial-Frequency Fusion Network for Medical Image SegmentationLink2D Medical Segmentation
ICASSP 2025MTTM: Memory-Augmented with Mamba for 3D Medical Images AnalysisLinkMedical Image Analysis
ICASSP 2025Edge-Interaction Mamba Network for MRI Brain Tumor SegmentationLinkTumor Segmentation
ICASSP 2025PHMamba: Preheating State Space Models with Context-Augmented Features for Medical Image SegmentationLink2D Medical Segmentation
ICASSP 2025Causal fMRI-Mamba: Causal State Space Model for Neural Decoding and Brain Task States RecognitionLinkfMRI Analysis
AAAI 2026EccoMamba: Enhanced Cross-hierarchical Continuity Orthogonal Mamba for Medical Image SegmentationLink2D Medical Segmentation
AAAI 2026HiFi-Mamba: Dual-Stream W-Laplacian Enhanced Mamba for High-Fidelity MRI ReconstructionLinkImage Reconstruction
AAAI 2026Δt-Mamba3D: A Time-Aware Spatio-Temporal State-Space Model for Breast Cancer Risk PredictionLinkRisk Prediction
AAAI 2026Rescind: Countering Image Misconduct in Biomedical Publications with Vision-Language and State-Space ModelingLinkMedical Image Classification
WACV 2026Hymavi: A Hybrid Mamba-Attention Network in Multi-View Framework for Volumetric Medical Image SegmentationLink3D Medical Segmentation
ICASSP 2026ConfMamba-SAM: Structured State Space Modeling with Memory-Augmented Prompting for Automatic Brain Lesion SegmentationLink3D Medical Segmentation
ICASSP 2026DDMamba: Dual-Scale Constrained Deformable Convolution with Mamba for Medical Image SegmentationLink2D & 3D Medical Segmentation
CVPR 2026MambaLiteUNet: Cross-Gated Adaptive Feature Fusion for Robust Skin Lesion SegmentationLink2D Medical Segmentation
CVPR 2026VesMamba: 3D Pulmonary Vessel Segmentation from CT images via Mamba with Structural Perception and Scale-aware FilteringLinkVessel Segmentation
CVPR 2026GeoSemba: Reconstructing State Space Model for Cross Paradigm Representation in Medical Image SegmentationLinkCode2D & 3D Medical Segmentation
CVPR 2026VEMamba: Efficient Isotropic Reconstruction of Volume Electron Microscopy with Axial-Lateral Consistent MambaLinkCodeImage Reconstruction
CVPR 2026 OralMDCS-MoAME: Multi-directional Composite Scanning with Mixture of Attention and Mamba Experts for Cancer Survival PredictionLinkCancer Subtyping/Survival Prediction
ICLR 2026BioTamperNet: Affinity-Guided State-Space Model Detecting Tampered Biomedical ImagesLinkMedical Image Classification

Video

VenuePaperLinkCodeTask
ECCV 2024VideoMamba: State Space Model for Efficient Video UnderstandingLinkCodeVideo Understanding
ICLR 2024SSM Meets Video Diffusion Models: Efficient Video Generation with Structured State SpacesLinkCodeVideo Generation
IJCV 2026Video Mamba Suite: State Space Model as a Versatile Alternative for Video UnderstandingLinkCodeVideo Understanding
CVPR 2024 WorkshopVMRNN: Integrating Vision Mamba and LSTM for Efficient and Accurate Spatiotemporal ForecastingLinkCodeSpatiotemporal Forecasting
ICCV 2025Snakes and Ladders: Two Steps Up for VideoMambaLinkCodeVideo Understanding
AAAI 2025RhythmMamba: Fast Remote Physiological Measurement with Arbitrary Length VideosLinkCodeRemote Photoplethysmography
NeurIPS 2024VFIMamba: Video Frame Interpolation with State Space ModelsLinkCodeFrame Interpolation
ECCV 2024VideoMamba: Spatio-Temporal Selective State Space ModelLinkCodeAction Recognition
ACM MM 2024 OralRainMamba: Enhanced Locality Learning with State Space Models for Video DerainingLinkCodeDeraining
ACM MM 2024 OralMambaTrack: A Simple Baseline for Multiple Object Tracking with State Space ModelLinkMulti-Object Tracking
Computers and Electronics in Agriculture 2025FMRFT: Fusion Mamba and DETR for Query Time Sequence Intersection Fish TrackingLinkMulti-Object Tracking
IEEE JSTAR 2024TrackingMamba: Visual State Space Model for Object TrackingLinkCodeObject Tracking
CCBR 2024PhysMamba: Efficient Remote Physiological Measurement with SlowFast Temporal Difference MambaLinkCodeRemote Photoplethysmography
NeurIPS 2024MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive ImagingLinkCodeSnapshot Compressive Imaging
NeurIPS 2024Toward Dynamic Non-Line-of-Sight Imaging with Mamba Enforced Temporal ConsistencyLinkDynamic Reconstruction
ACM MM 2024Object-Level Pseudo-3D Lifting for Distance-Aware TrackingLinkMulti-Object Tracking
AAAI 2025Manta: Enhancing Mamba for Few-Shot Action Recognition of Long Sub-SequenceLinkCodeAction Recognition
AAAI 2025Exploring Enhanced Contextual Information for Video-Level Object TrackingLinkCodeObject Tracking
AAAI 2025Robust Tracking via Mamba-based Context-aware Token LearningLinkCodeObject Tracking
IROS 2025MambaNUT: Nighttime UAV Tracking via Mamba-based Adaptive Curriculum LearningLinkObject Tracking
AAAI 2025Efficient Self-Supervised Video Hashing with Selective State SpacesLinkCodeHashing
IEEE TMM 2026STNMamba: Mamba-based Spatial-Temporal Normality Learning for Video Anomaly DetectionLinkAnomaly Detection
CVPR 2025MambaVO: Deep Visual Odometry Based on Sequential Matching Refinement and Training SmoothingLinkVisual Odometry
NeurIPS 2024Slot State Space ModelsLinkCodeVideo Understanding
IEEE TPAMI 2025MADiff: Motion-Aware Mamba Diffusion Models for Hand Trajectory Prediction on Egocentric VideosLinkTrajectory Prediction
CVPR 2025MANTA: Diffusion Mamba for Efficient and Effective Stochastic Long-term Dense AnticipationLinkAction Anticipation
CVPR 2025Event-based Video Super-Resolution via State Space ModelsLinkSuper-Resolution
CVPR 2025LC-Mamba: Local and Continuous Mamba with Shifted Windows for Frame InterpolationLinkFrame Interpolation
ICCV 2025Vamba: Understanding Hour-Long Videos with Hybrid Mamba-TransformersLinkVideo Understanding
ICCV 2025VSRM: A Robust Mamba-Based Framework for Video Super-ResolutionLinkSuper-Resolution
ICCV 2025EVDM: Event-based Real-World Video Deblurring with MambaLinkDeblurring
ICCV 2025EgoMusic-Driven Human Dance Motion Estimation with Skeleton MambaLinkHuman Motion Estimation
ICCV 2025PS-Mamba: Spatial-Temporal Graph Mamba for Pose Sequence RefinementLink3D Human Pose Estimation
ICML 2025MoMa: Modulating Mamba for Adapting Image Foundation Models to Video RecognitionLinkAction Recognition
ACM MM 2025UMSD: High Realism Motion Style Transfer via Unified Mamba-based DiffusionLinkMotion Style Transfer
CVPR 2025 HighlightLearning Phase Distortion with Selective State Space Models for Video Turbulence MitigationLinkVideo Restoration
CVPR 2025 OralSemi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video DerainingLinkVideo Restoration
CVPR 2025Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolutionLinkSuper-Resolution
ICCV 2025PRE-Mamba: A 4D State Space Model for Ultra-High-Frequent Event Camera DerainingLinkVideo Restoration
ICCV 2025High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose EstimationLinkHuman Pose Estimation
NeurIPS 2025MVSMamba: Multi-View Stereo with State Space ModelLinkMulti-View Stereo
ICASSP 2025MambaMOT: State-Space Model as Motion Predictor for Multi-Object TrackingLinkMulti-Object Tracking
ICASSP 2025MambaTrack: Exploiting Dual-Enhancement for Night UAV TrackingLinkObject Tracking
CVPR 2025 WorkshopSportMamba: Adaptive Non-Linear Multi-Object Tracking with State Space Models for Team SportsLinkMulti-Object Tracking
CVPR 2025 WorkshopDyadic Mamba: Long-term Dyadic Human Motion SynthesisLinkMotion Generation
ICASSP 2025Sign-Mamba: Advanced Mamba-Based Sign Language GenerationLinkMotion Generation
ICASSP 2025DSSM: Dual State Space Model for Human Motions GenerationLinkMotion Generation
AAAI 2026MambaOVSR: Multiscale Fusion with Global Motion Modeling for Chinese Opera Video Super-ResolutionLinkSuper-Resolution
AAAI 2026State-Space Hierarchical Compression with Gated Attention and Learnable Sampling for Hour-Long Video Understanding in Large Multimodal ModelsLinkCodeVideo Understanding
AAAI 2026Backtrace Mamba: Reviving Critical Temporal Contexts via Hierarchical Memory Compression for Online Action DetectionLinkAction Detection
AAAI 2026DeformTrace: A Deformable State Space Model with Relay Tokens for Temporal Forgery LocalizationLinkTemporal Forgery Localization
ICLR 2026ConvT3: Structured State Kernels for Convolutional State Space ModelsLinkVideo Generation
ICLR 2026Trajectory-aware Shifted State Space Models for Online Video Super-ResolutionLinkCodeSuper-Resolution
CVPR 2026RS-SSM: Refining Forgotten Specifics in State Space Model for Video Semantic SegmentationLinkVideo Semantic Segmentation
CVPR 2026M4V: Multimodal Mamba for Efficient Text-to-Video GenerationLinkVideo Generation
CVPR 2026HieraMamba: Video Temporal Grounding via Hierarchical Anchor-Mamba PoolingLinkTemporal Grounding
CVPR 2026MS-Temba: Multi-Scale Temporal Mamba for Understanding Long Untrimmed VideosLinkAction Recognition
CVPR 2026EgoFlow: Gradient-Guided Flow Matching for Egocentric 6DoF Object Motion GenerationLinkMotion Generation
CVPR 2026Gamba: Mamba-based Graph Convolutional Network with Dynamic Graph Topology Learning for Action RecognitionLinkAction Recognition
CVPR 2026When Transformers Meet Mamba: A Hybrid Transformer-Mamba Network for Video Object DetectionLinkVideo Object Detection
CVPR 2026 FindingsMVSSM: Motion-aware Visual State Space Model for Efficient Video DeblurringLinkCodeVideo Deblurring
ICML 2026StructMamPose: From Sequential Perception to Structural Reasoning for 3D Human Pose EstimationLink3D Human Pose Estimation
ECCV 2026MASS: Motion-Aligned Selective Scan for Refinement in Flow-Based Video Frame InterpolationLinkVideo Frame Interpolation

Point Cloud

VenuePaperLinkCodeTask
NeurIPS 2024PointMamba: A Simple State Space Model for Point Cloud AnalysisLinkCodeClassification, Part Segmentation
CVPR 2024State Space Models for Event CamerasLinkCodeObject Detection
ACM MM 2024MambaMOS: LiDAR-based 3D Moving Object Segmentation with Motion-aware State Space ModelLinkCodeObject Segmentation
ACM MM 2024Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space ModelLinkCodeClassification, Part Segmentation
NeurIPS 2024LCM: Locally Constrained Compact Point Cloud Model for Masked Point ModelingLinkCodeClassification, Part Segmentation, 3D Object Detection
NeurIPS 2024Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object DetectionLinkCode3D Object Detection
NeurIPS 20243DET-Mamba: Causal Sequence Modelling for End-to-End 3D Object DetectionLink3D Object Detection
ICIP 2024Mamba-PCGC: Mamba-Based Point Cloud Geometry CompressionLinkGeometry Compression
NeurIPS 2024LION: Linear Group RNN for 3D Object Detection in Point CloudsLinkCode3D Object Detection
AAAI 2025SMamba: Sparse Mamba for Event-based Object DetectionLinkCodeObject Detection
AAAI 2025Point Cloud Mamba: Point Cloud Learning via State Space ModelLinkCodeClassification, Segmentation
AAAI 20253DMambaIPF: A State Space Model for Iterative Point Cloud FilteringLinkPoint Cloud Filtering
IEEE TPAMI 2025Rethinking Efficient and Effective Point-based Networks for Event Camera Classification and RegressionLinkEvent Camera Classification
CVPR 2025MAMBA4D: Efficient Long-Sequence Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space ModelsLinkPoint Cloud Video Understanding
AAAI 2025Pamba: Enhancing Global Interaction in Point Clouds via State Space ModelLinkPoint Cloud Analysis
ROBIO 2024MV-MOS: Multi-View Feature Fusion for 3D Moving Object SegmentationLinkCodeObject Segmentation
IEEE TCSVT 2025MambaEVT: Event Stream-Based Visual Object Tracking Using State Space ModelLinkCodeObject Tracking
IEEE RA-L 2025OMEGA: Efficient Occlusion-Aware Navigation for Air-Ground Robots in Dynamic Environments via State Space ModelLinkRobot Navigation
ACM MM Asia 2024SpikMamba: When SNN meets Mamba in Event-based Human Action RecognitionLinkCodeAction Recognition
Communications in Transportation Research 2025MetaSSC: Enhancing 3D Semantic Scene Completion for Autonomous Driving through Meta-Learning and Long-sequence ModelingLink3D Semantic Scene Completion
CVPR 2025WeatherGen: A Unified Diverse Weather Generator for LiDAR Point Clouds via Spider Mamba DiffusionLinkCodePoint Cloud Generation
CVPR 2025Spectral Informed Mamba for Robust Point Cloud ProcessingLinkPoint Cloud Analysis
ICCV 2025Efficient Spiking Point Mamba for Point Cloud AnalysisLinkPoint Cloud Analysis
ICCV 2025StruMamba3D: Exploring Structural Mamba for Self-supervised Point Cloud Representation LearningLinkSelf-supervised Learning
ICLR 2025MamBEV: Enabling State Space Models to Learn Birds-Eye-View RepresentationsLink3D Object Detection
ICLR 2025State Space Model Meets Transformer: A New Paradigm for 3D Object DetectionLink3D Object Detection
CVPR 2025UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object DetectionLink3D Object Detection
CVPR 2025PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba AdapterLinkPoint Cloud Analysis
ICCV 2025UST-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video ModelingLinkPoint Cloud Analysis
AAAI 2026Seeing in Double: Dual-Granularity BEV Segmentation via Mamba-Driven Alignment and Polar-Decoupled ExpertsLinkBEV Segmentation
AAAI 2026DAPointMamba: Domain Adaptive Point Mamba for Point Cloud CompletionLinkPoint Cloud Completion
AAAI 2026CloudMamba: Grouped Selective State Spaces for Point Cloud AnalysisLinkPoint Cloud Analysis
AAAI 2026BeyondSparse: Facilitating Mamba to Enhance Cross-Domain 3D Semantic Segmentation in Adverse WeatherLinkSemantic Segmentation
AAAI 2026WinMamba: Multi-Scale Shifted Windows in State Space Model for 3D Object DetectionLink3D Object Detection
WACV 2026Towards Streaming LiDAR Object Detection with Point Clouds as Egocentric SequencesLink3D Object Detection
WACV 2026MEGA-PCC: A Mamba-based Efficient Approach for Joint Geometry and Attribute Point Cloud CompressionLinkPoint Cloud Compression
WACV 2026SSMRadNet: A Sample-wise State-Space Framework for Efficient and Ultra-Light Radar Segmentation and Object DetectionLinkObject Detection
WACV 2026milliMamba: Specular-Aware Human Pose Estimation via Dual mmWave Radar with Multi-Frame Mamba FusionLink3D Human Pose Estimation
CVPR 2026GEM: Generating LiDAR World Model via Deformable MambaLinkLiDAR World Model
CVPR 2026MARSS: Radar Semantic Segmentation via Modular Attention and State Space ModelsLinkSemantic Segmentation
CVPR 2026Mamba Learns in Context: Structure-Aware Domain Generalization for Multi-Task Point Cloud UnderstandingLinkPoint Cloud Understanding
ICML 2026NeuroMamba: A Universal Spatiotemporal Module for Robust Perception in Degraded Sensory StreamsLinkPoint Cloud Analysis
ICLR 2026Fore-Mamba3D: Mamba-based Foreground-Enhanced Encoding for 3D Object DetectionLinkCode3D Object Detection
ICLR 20263DSMT: A Hybrid Spiking Mamba-Transformer for Point Cloud AnalysisLinkPoint Cloud Analysis
ICLR 2026DriveMamba: Task-Centric Scalable State Space Model for Efficient End-to-End Autonomous DrivingLinkAutonomous Driving
ICLR 2026Point-Focused Attention Meets Context-Scan State Space: Robust Biological Visual Perception for Point Cloud RepresentationLinkPoint Cloud Analysis
ICASSP 2026STNID: A Spatiotemporal Mamba-Based Neural Implicit Dynamics Model for Point Cloud ForecastingLinkPoint Cloud Forecasting

Multi-Modal

VenuePaperLinkCodeTaskModality
Information Fusion 2025Pan-Mamba: Effective pan-sharpening with State Space ModelLinkCodePansharpeningHISR Images & LRMS Images
ECCV 2024InstructGIE: Towards Generalizable Image EditingLinkCodeImage EditingImage & Text
ECCV 2024Motion Mamba: Efficient and Long Sequence Motion Generation with Hierarchical and Bidirectional Selective SSMLinkCodeText-to-Motion GenerationMotion & Text
NeurIPS 2024 WorkshopVL-Mamba: Exploring State Space Models for Multimodal LearningLinkCodeMLLM TasksImage & Text
Neural Computing and Applications 2026Music to Dance as Language Translation using Sequence ModelsLinkCodeDance GenerationMotion & Audio
NeurIPS 2024MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space ModelsLinkGesture GenerationMotion & Audio
ECCV 2024ReMamber: Referring Image Segmentation with Mamba TwisterLinkCodeReferring Image SegmentationImage & Text
BIBM 2025SurvMamba: State Space Model with Multi-grained Multi-modal Interaction for Survival PredictionLinkCancer Subtyping/Survival PredictionWSIs & Gene
WACV 2025Sigma: Siamese Mamba Network for Multi-Modal Semantic SegmentationLinkCodeSemantic SegmentationRGB Images & Depth Images / Thermal Images
IEEE TGRS 2024Efficient Remote Sensing Image Fusion With State Space ModelLinkCodePansharpeningHISR Images & LRMS Images
PRCV 2024Mamba-FETrack: Frame-Event Tracking via State Space ModelLinkCodeRGB-Event TrackingRGB Frames & Event Data
IEEE GRSL 2024RSCaMa: Remote Sensing Image Change Captioning with State Space ModelLinkCodeImage CaptioningRemote Sensing Images & Text
MIA 2025MMR-Mamba: Multi-modal MRI reconstruction with Mamba and spatial-frequency information fusionLinkImage FusionMulti-Contrast MRI
IEEE TIP 2025S4Fusion: Saliency-Aware Selective State Space Model for Infrared and Visible Image FusionLinkImage FusionRGB Images & Infrared Images
NeurIPS 2024Meteor: Mamba-based Traversal of Rationale for Large Language and Vision ModelsLinkCodeMLLM TasksImage & Text
NeurIPS 2024Coupled Mamba: Enhanced Multi-modal Fusion with Coupled State Space ModelLinkMulti-modal Sentiment AnalysisVideo & Text & Audio
NeurIPS 2024RoboMamba: Multimodal State Space Model for Efficient Robot Reasoning and ManipulationLinkCodeRobot Reasoning and ManipulationImage & Text
ACM MM 2024MambaGesture: Enhancing Co-Speech Gesture Generation with Mamba and Disentangled Multi-Modality FusionLinkGesture GenerationMotion & Audio
ITSC 2024MambaST: A Plug-and-Play Cross-Spectral Spatial-Temporal Fuser for Efficient Pedestrian DetectionLinkCodePedestrian DetectionRGB Images & Thermal Images
ACML 2024ColorMamba: Towards High-quality NIR-to-RGB Spectral Translation with MambaLinkCodeNIR-to-RGB TranslationRGB Images & NIR Images
ACM TOMCCAP 2025JambaTalk: Speech-driven 3D Talking Head Generation based on a Hybrid Transformer-Mamba ModelLink3D Talking Head GenerationMotion & Audio
IEEE TGRS 2024Mask-Guided Mamba Fusion for Drone-based Visible-Infrared Vehicle DetectionLinkObject DetectionRGB Images & Infrared Images
IEEE TGRS 2024Joint Classification of Hyperspectral and LiDAR Data Based on MambaLinkCodeClassificationHSI & LiDAR Points
MICCAI 2024LM-UNet: Whole-Body PET-CT Lesion Segmentation with Dual-Modality-Based Annotations Driven by Latent Mamba U-NetLinkCode3D Medical SegmentationPET Images & CT Images
ICLR 2025EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical AlignmentLinkMLLM TasksImage & Text
ISBI 2025R2Gen-Mamba: A Selective State Space Model for Radiology Report GenerationLinkCodeRadiology Report GenerationImage & Text
BDAI 2025MSCrackMamba: Leveraging Vision Mamba for Crack Detection in Fused Multispectral ImageryLinkCrack DetectionRGB Images & Infrared Images
CVIP 2025DiM-Gestor: Co-Speech Gesture Generation with Adaptive Layer Normalization Mamba-2LinkCodeGesture GenerationMotion & Audio
IEEE GRSL 2024A Mamba-Diffusion Framework for Multimodal Remote Sensing Image Semantic SegmentationLinkCodeSemantic SegmentationRGB Images & SAR Images
IEEE TIV 2024SeqMamba-MPR: A Spatial-Temporal Mamba Network for Place Recognition Using Sequential Multi-Modal DataLinkPlace RecognitionRGB Images & LiDAR Points
IEEE GRSL 2024S2CrossMamba: Spatial–Spectral Cross-Mamba for Multimodal Remote Sensing Image ClassificationLinkCodeClassificationHISR Images & LRMS Images
Scientific Reports 2024ReMamba: a hybrid CNN-Mamba aggregation network for visible-infrared person re-identificationLinkVisible-infrared Re-identificationRGB Images & Infrared Images
IEEE TCSVT 2024MDNet: Mamba-Effective Diffusion-Distillation Network for RGB-Thermal Urban Dense PredictionLinkCodeDense PredictionRGB Images & Thermal Images
CVPR 2025AlignMamba: Enhancing Multimodal Mamba with Local and Global Cross-modal AlignmentLinkMulti-Modality FusionVideo & Text & Audio
AAAI 2025LOMA: Language-assisted Semantic Occupancy Network via Triplane MambaLinkOccupancy PredictionImage & Text
AAAI 2025MambaPro: Multi-Modal Object Re-Identification with Mamba Aggregation and Synergistic PromptLinkCodeObject Re-IdentificationRGB Images & Near Infrared Images & Thermal Infrared Images
AAAI 2025Light-T2M: A Lightweight and Fast Model for Text-to-motion GenerationLinkCodeText-to-Motion GenerationMotion & Text
AAAI 2025Exploiting Multimodal Spatial-temporal Patterns for Video Object TrackingLinkCodeObject TrackingRGB Videos & TIR/Depth/Event
ICASSP 2025Trusted Mamba Contrastive Network for Multi-View ClusteringLinkMulti-View ClusteringImage & Text
AAAI 2025H-MBA: Hierarchical MamBa Adaptation for Multi-Modal Video Understanding in Autonomous DrivingLinkVideo UnderstandingVideo & Text
AAAI 2025Skip Mamba Diffusion for Monocular 3D Semantic Scene CompletionLinkCode3D Semantic Scene CompletionRGB Images & LiDAR Points
IEEE TMM 2025AVS-Mamba: Exploring Temporal and Multi-modal Mamba for Audio-Visual SegmentationLinkCodeAudio-Visual SegmentationVideo & Audio
ICCV 2025LiT: Delving into a Simplified Linear Diffusion Transformer for Image GenerationLinkCodeImage GenerationImage & Text
Information Fusion 2025An efficient cross-view image fusion method based on selected state space and hashing for promoting urban perceptionLinkGeo-LocalizationStreet-view Images & Aerial-view Images
AAAI 2025Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient InferenceLinkCodeMLLM TasksImage & Text
IEEE TMM 2025Fusion-Mamba for Cross-modality Object DetectionLinkObject DetectionRGB Images & Infrared Images
Visual Intelligence 2025FusionMamba: Dynamic Feature Enhancement for Multimodal Image Fusion with MambaLinkCodeImage FusionMulti-Modal Images
IEEE TIP 2025Text-controlled Motion Mamba: Text-Instructed Temporal Grounding of Human MotionLinkTemporal GroundingMotion & Text
IEEE TCSVT 2025CFMW: Cross-modality Fusion Mamba for Robust Object Detection under Adverse Weather with Multimodal CameraLinkCodeObject DetectionRGB Images & Infrared Images
AAAI 2025RGBT Tracking via All-layer Multimodal Interactions with Progressive Fusion MambaLinkRGB-T TrackingRGB Images & Thermal Images
IEEE TCSVT 2025MambaVT: Spatio-Temporal Contextual Modeling for robust RGB-T TrackingLinkRGB-T TrackingRGB Images & Thermal Images
IEEE JBHI 2026R2GenCSR: Mining Contextual and Residual Information for LLMs-based Radiology Report GenerationLinkRadiology Report GenerationImage & Text
CVPR 2025OccMamba: Semantic Occupancy Prediction with State Space ModelsLinkSemantic Occupancy PredictionRGB Images & LiDAR Points
AAAI 2025MUSE: Mamba is Efficient Multi-scale Learner for Text-video RetrievalLinkText-Video RetrievalVideo & Text
IEEE TETCI 2026DualKanbaFormer: An Efficient Selective Sparse Framework for Multimodal Aspect-Based Sentiment AnalysisLinkMulti-modal Sentiment AnalysisImage & Text
IROS 2025MambaPlace:Text-to-Point-Cloud Cross-Modal Place Recognition with Attention Mamba MechanismsLinkCodePlace Recognition3D Point Cloud & Text
IEEE TCSVT 2025Shuffle Mamba: State Space Models with Random Shuffle for Multi-Modal Image FusionLinkImage FusionRGB Images & Infrared Images
ICASSP 2025Mamba Fusion: Learning Actions Through QuestioningLinkCodeAction AnticipationVideo & Text
ICASSP 2025Mamba-YOLO-World: Marrying YOLO-World with Mamba for Open-Vocabulary DetectionLinkCodeOpen-Vocabulary DetectionImage & Text
ADMA 2025Mamba-Enhanced Text-Audio-Video Alignment Network for Emotion Recognition in ConversationsLinkCodeEmotion RecognitionVideo & Text & Audio
IROS 2025GraspMamba: A Mamba-based Language-driven Grasp Detection Framework with Hierarchical Feature LearningLinkCodeGrasp DetectionImage & Text
ACM MM Asia 2024LMHaze: Intensity-aware Image Dehazing with a Large-scale Multi-intensity Real Haze DatasetLinkDehazingImage & Text
Neurocomputing 2025MambaSOD: Dual Mamba-Driven Cross-Modal Fusion Network for RGB-D Salient Object DetectionLinkCodeSalient Object DetectionRGB Images & Depth Images
ACM MM Workshop 2024Moyun: A Diffusion-Based Model for Style-Specific Chinese Calligraphy GenerationLinkStyle-Specific Chinese Calligraphy GenerationImage & Text
ICASSP 2025DepMamba: Progressive Fusion Mamba for Multimodal Depression DetectionLinkCodeMulti-modal Depression DetectionVideo & Audio
CVPR 2025CXPMRG-Bench: Pre-training and Benchmarking for X-ray Medical Report Generation on CheXpert Plus DatasetLinkCodeMedical Report GenerationImage & Text
EMNLP 2024Shaking Up VLMs: Comparing Transformers and Structured State Space Models for Vision & Language ModelingLinkCodeMLLM TasksImage & Text
EMNLP 2025 FindingsLongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Mamba-Transformer ModelLinkCodeMLLM TasksImage & Text
IROS 2025Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State ModelsLinkCodeRobot Manipulation3D Point Cloud & Text
CVPR 2025MambaVLT: Time-Evolving Multimodal State Space Model for Vision-Language TrackingLinkVision-Language TrackingRGB Images & Text
CVPR 2025LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational ComplexityLinkText-to-Video GenerationVideo & Text
IEEE TPAMI 2025OccScene: Semantic Occupancy-based Cross-task Mutual Learning for 3D Scene GenerationLink3D Scene GenerationRGB Images & Occupancy Grids
CVPR 2025Completion as Enhancement: A Degradation-Aware Selective Image Guided Mamba Fusion Network for Depth CompletionLinkDepth CompletionRGB Images & Depth Images
CVPR 2025Exploring Historical Information for RGBE Visual Tracking with MambaLinkRGB-Event TrackingRGB Frames & Event Data
ICCV 2025Mamba-3VL: Taming State Space Model for 3D Vision Language LearningLink3D Vision-Language Learning3D Point Cloud & Text
IJCAI 2025RRG-Mamba: Efficient Radiology Report Generation with State Space ModelLinkRadiology Report GenerationImage & Text
CVPR 2025BIMBA: Selective-Scan Compression for Long-Range Video Question AnsweringLinkVideo QAVideo & Text
ICCV 2025MUG: Pseudo Labeling Augmented Audio-Visual Mamba Network for Audio-Visual Video ParsingLinkAudio-Visual ParsingVideo & Audio
ICCV 2025End-to-End Multi-Modal Diffusion MambaLinkMulti-modal GenerationImage & Text
ACM MM 2025LEAF-Mamba: Local Emphatic and Adaptive Fusion State Space Model for RGB-D Salient Object DetectionLinkSalient Object DetectionRGB Images & Depth Images
ACM MM 2025LIDAR: Lightweight Adaptive Cue-Aware Fusion Vision Mamba for Multimodal Segmentation of Structural CracksLinkCrack SegmentationMulti-Modal
NeurIPS 2025SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image SegmentationLinkReferring Image SegmentationImage & Text
ICCV 2025MambaFusion: Height-Fidelity Dense Global Fusion for Multi-modal 3D Object DetectionLink3D Object DetectionRGB Images & LiDAR Points
ICCV 2025WaveMamba: Wavelet-Driven Mamba Fusion for RGB-Infrared Object DetectionLinkObject DetectionRGB Images & Infrared Images
AAAI 2026MambaSeg: Harnessing Mamba for Accurate and Efficient Image-Event Semantic SegmentationLinkSemantic SegmentationRGB Frames & Event Data
AAAI 2026Self-supervised Multiplex Consensus Mamba for General Image FusionLinkImage FusionMulti-Modal Images
AAAI 2026Exploiting All Mamba Fusion for Efficient RGB-D TrackingLinkObject TrackingRGB Images & Depth Images
AAAI 2026KineST: A Kinematics-guided Spatiotemporal State Space Model for Human Motion Tracking from Sparse SignalsLinkMotion TrackingMotion & Sparse Signals
WACV 2026Not Like Transformers: Drop the Beat Representation for Dance Generation with Mamba-Based Diffusion ModelLinkDance GenerationMotion & Audio
CVPR 2026TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video UnderstandingLinkVideo UnderstandingVideo & Text
CVPR 2026Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation ModelsLinkVideo-to-Audio GenerationVideo & Audio
CVPR 2026RI-Mamba: Rotation-Invariant Mamba for Robust Text-to-Shape RetrievalLinkCodeText-to-Shape Retrieval3D Point Cloud & Text
CVPR 2026VIMCAN: Visual-Inertial 3D Human Pose Estimation with Hybrid Mamba-Cross-Attention NetworkLinkCode3D Human Pose EstimationImage & IMU
CVPR 2026AIMDepth: Asymmetric Image-Event Mamba for Monocular Depth EstimationLinkDepth EstimationRGB Frames & Event Data
ICASSP 2026MAPD-Mamba: Modality-Adaptive Perception-Driven Mamba Fusion NetworkLinkMultimodal FusionMulti-Modal

Others

VenuePaperLinkCodeTask
PLOS ONE 2025Res-VMamba: Fine-Grained Food Category Visual Classification Using Selective State Space Models with Deep Residual LearningLinkCodeFood Classification
ICRA 2025Motion-Guided Dual-Camera Tracker for Low-Cost Skill Evaluation of Gastric EndoscopyLinkCodeEndoscope Tip Tracking
ICLR 2025Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in SportsLinkCodeTrajectory Generation
Sleep 2025Mamba-based deep learning approach for sleep staging on a wireless multimodal wearable system without electroencephalographyLinkSleep Staging
Scientific Reports 2025Optimising TinyML with Quantization and Distillation of Transformer and Mamba Models for Indoor Localisation on Edge DevicesLinkCodeIndoor Localization
Journal of Physics: Photonics 2025Bidirectional Mamba state-space model for anomalous diffusionLinkCodeAnomalous Diffusion Analysis
ICCC 2024ST-Mamba: Spatial-Temporal Mamba for Traffic Flow Estimation Recovery with Missing DataLinkTraffic Flow Estimation
ICCV 2025MamTiff-CAD: Multi-Scale Latent Diffusion with Mamba+ for Complex Parametric Sequence GenerationLinkCAD Sequence Generation
CVPR 2025Trajectory Mamba: Efficient Attention-Mamba Forecasting Model Based on Selective SSMLinkTrajectory Prediction
CVPR 2025 WorkshopU-Shape Mamba: State Space Model for faster diffusionLinkCodeDiffusion Acceleration
ICASSP 2025Stochastic-Aware Mamba Diffusion for Pedestrian Trajectory PredictionLinkTrajectory Prediction
AAAI 2026Mamba-Driven Multi-View Discriminative Clustering via Global-Local Cross-View Sequence ModelingLinkMulti-View Clustering
CVPR 2026FoSS: Modeling Long-Range Dependencies and Multimodal Uncertainty in Trajectory Prediction via Fourier-State Space IntegrationLinkTrajectory Prediction

Valuable Insights

VenuePaperLink
ACL 2025The Hidden Attention of Mamba ModelsLink
CVPR 2025MambaOut: Do We Really Need Mamba for Vision?Link
NeurIPS 2024Demystify Mamba in Vision: A Linear Attention PerspectiveLink
ICLR 2025A Unified Implicit Attention Formulation for Gated-Linear Recurrent Sequence ModelsLink
NeurIPS 2024MambaLRP: Explaining Selective State Space Sequence ModelsLink
NeurIPS 2025TRUST: Test-Time Refinement using Uncertainty-Guided SSM TraversesLink
CVPR 2025 WorkshopTowards Evaluating the Robustness of Visual State Space ModelsLink
ICML 2025 WorkshopState Space Models: A Naturally Robust Alternative to Transformers in Computer VisionLink
ICLR 2025 SpotlightDemystifying the Token Dynamics of Deep Selective State Space ModelsLink
ACL 2025Mamba Knockout for Unraveling Factual Information FlowLink
CVPR 2026 FindingsExemplar-Free Continual Learning for State Space ModelsLink
CVPR 2026RNN as Linear Transformer: A Closer Investigation into Representational Potentials of Visual Mamba ModelsLink

Other Domains

Reinforcement Learning

VenuePaperLinkCode
IROS 2024Proprioception Is All You Need: Terrain Classification for Boreal ForestsLinkCode
IEEE Access 2025Mamba as a motion encoder for robotic imitation learningLink
ICCMA 2024Context Aware Mamba-based Reinforcement Learning for Social Robot NavigationLink
NeurIPS 2024Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?Link
NeurIPS 2024Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RLLink
CoRL 2024MaIL: Improving Imitation Learning with Selective State Space ModelsLinkCode
IEEE TMRB 2024Visuomotor Policy Learning for Task Automation of Surgical RobotLinkCode
NeurIPS 2024Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence ModelingLink
ICRA 2026DiSPo: Diffusion-SSM based Policy Learning for Coarse-to-Fine Action AbstractionLink
ICLR 2025Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter EfficientLinkCode
AAMAS 2025Multi-Agent Reinforcement Learning with Selective State-Space ModelsLinkCode
ICML 2025A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics TasksLinkCode
AAAI 2025GLAM: Global-Local Variation Awareness in Mamba-based World ModelLinkCode
CVPR 2025FlowRAM: Grounding Flow Matching Policy with Region-Aware Mamba Framework for Robotic ManipulationLink

Graph Learning

VenuePaperLinkCode
KDD 2024Graph Mamba: Towards Learning on Graphs with State Space ModelsLinkCode
KDD 2024 WorkshopIdentifying Subphenotypes for Sepsis with Acute Kidney Injury via Multimodal Graph State Space ModelsLink
AAAI 2025DG-Mamba: Robust and Efficient Dynamic Graph Structure Learning with Selective State Space ModelsLinkCode
AAAI 2025MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic InsightsLinkCode
AAAI 2025BrainMAP: Learning Multiple Activation Pathways in Brain NetworksLinkCode
TMLR 2025DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space ModelsLink
NeurIPS 2025DyG-Mamba: Continuous State Space Modeling on Dynamic GraphsLinkCode
IJCNN 2025Topological Deep Learning with State-Space Models: A Mamba Approach for Simplicial ComplexesLink
IJCAI 2025Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing in Graph Neural NetworksLink
IJCAI 2025SourceDetMamba: A Graph-aware State Space Model for Source Detection in Sequential HypergraphsLink
ECML PKDD 2025GLADMamba: Unsupervised Graph-Level Anomaly Detection Powered by Selective State Space ModelLinkCode
AAAI 2026Dual Mamba for Node-Specific Representation Learning: Tackling Over-Smoothing with Selective State Space ModelingLinkCode

Audio

VenuePaperLinkCode
IEEE SPL 2024Multichannel Long-Term Streaming Neural Speech Enhancement for Static and Moving SpeakersLinkCode
IMWUT 2025TRAMBA: A Hybrid Transformer and Mamba Architecture for Practical Audio and Bone Conduction Speech Super Resolution and Enhancement on Mobile and Wearable PlatformsLink
Interspeech 2024Audio Mamba: Selective State Spaces for Self-Supervised Audio RepresentationsLinkCode
Interspeech 2024RawBMamba: End-to-End Bidirectional State Space Model for Audio Deepfake DetectionLinkCode
Interspeech 2024Exploring the Capability of Mamba in Speech ApplicationsLink
SLT 2024 WorkshopAn Analysis of Linear Complexity Attention Substitutes with BEST-RQLink
SLT 2024Speech-Mamba: Long-Context Speech Recognition with Selective State Spaces ModelsLinkCode
ICASSP 2025Mamba-based Segmentation Model for Speaker DiarizationLinkCode
SLT 2024Mamba-based Decoder-Only Approach with Bidirectional Speech Modeling for Speech RecognitionLinkCode
LAMIR 2024 WorkshopAEROMamba: An efficient architecture for audio super-resolution using generative adversarial networks and state space modelsLinkCode
Interspeech 2025MASV: Speaker Verification with Global and Local Context MambaLink
Expert Systems 2024A barking emotion recognition method based on Mamba and Synchrosqueezing Short-Time Fourier TransformLinkCode
ICASSP 2025Mamba-SEUNet: Mamba UNet for Monaural Speech EnhancementLink
ICASSP 2025Temporal-Frequency State Space Duality: An Efficient Paradigm for Speech Emotion RecognitionLink
APSIPA ASC 2024U-Mamba-Net: A highly efficient Mamba-based U-net style network for noisy and reverberant speech separationLink
AAAI 2025BSDB-Net: Band-Split Dual-Branch Network with Selective State Spaces Mechanism for Monaural Speech EnhancementLink
ICASSP 2025Improved Feature Extraction Network for Neuro-Oriented Target Speaker ExtractionLink
IEEE SLT 2024An Investigation of Incorporating Mamba for Speech EnhancementLink
IEEE TASLP 2025Mamba in Speech: Towards an Alternative to Self-AttentionLink
IEEE SLT 2024SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space ModelLinkCode
ICASSP 2025Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech SeparationLinkCode
CIAC 2025SELD-Mamba: Selective State-Space Model for Sound Event Localization and Detection with Source Distance EstimationLink
ICASSP 2025MusicMamba: A Dual-Feature Modeling Approach for Generating Chinese Traditional Music with SSMLink
ICASSP 2025Cross-attention Inspired Selective State Space Models for Target Sound ExtractionLink
Interspeech 2025TF-Mamba: A Time-Frequency Network for Sound Source LocalizationLink
ICASSP 2025Vector Quantized Diffusion Model Based Speech Bandwidth ExtensionLink
ICASSP 2025Rethinking Mamba in Speech Processing by Self-Supervised ModelsLink
ICASSP 2025MambaFoley: Foley Sound Generation using Selective State-Space ModelsLink
ICASSP 2025Wave-U-Mamba: An End-To-End Framework For High-Quality And Efficient Speech Super ResolutionLink
ICASSP 2025Self-supervised Learning for Acoustic Few-Shot ClassificationLink
ICASSP 2025Ultra-Low Latency Speech Enhancement - A Comprehensive StudyLink
ICASSP 2025Leveraging Joint Spectral and Spatial Learning with MAMBA for Multichannel Speech EnhancementLink
ICASSP 2025 OralDeFT-Mamba: Universal Multichannel Sound Separation and Polyphonic Audio ClassificationLink
ICASSP 2025Mamba for Streaming ASR Combined with Unimodal AggregationLink
ICLR 2025Joint Fine-tuning and Conversion of Pretrained Speech and Language Models towards Linear ComplexityLinkCode
ISCAS 2025CleanUMamba: A Compact Mamba Network for Speech Denoising using Channel PruningLink
ICASSP 2025SepMamba: State-space models for speaker separation using MambaLinkCode
IEEE JSTSP 2025SAV-SE: Scene-aware Audio-Visual Speech Enhancement with Selective State Space ModelLink
IEEE SPL 2025XLSR-Mamba: A Dual-Column Bidirectional State Space Model for Spoofing Attack DetectionLink
ICASSP 2025BEST-STD: Bidirectional Mamba-Enhanced Speech Tokenization for Spoken Term DetectionLink
ICASSP 2025TAME: Temporal Audio-based Mamba for Enhanced Drone Trajectory Estimation and ClassificationLink
Interspeech 2025xLSTM-SENet: xLSTM for Single-Channel Speech EnhancementLinkCode
ICASSP 2025MSECG: Incorporating Mamba for Robust and Efficient ECG Super-ResolutionLink
Interspeech 2025Leveraging Mamba with Full-Face Vision for Audio-Visual Speech EnhancementLink
Interspeech 2025BiCrossMamba-ST: Speech Deepfake Detection with Bidirectional Mamba Spectro-Temporal Cross-AttentionLink
Interspeech 2025Universal Speech Enhancement with Regression and Generative MambaLink
Interspeech 2025PARROT: Synergizing Mamba and Attention-based SSL Pre-Trained Models via Parallel Branch Hadamard Optimal Transport for Speech Emotion RecognitionLink
Interspeech 2025Non-Intrusive Binaural Speech Intelligibility Prediction Using Mamba for Hearing-Impaired ListenersLink
ICASSP 2026BeatMamba: Bidirectional Selective State-Space Modeling for Efficient Beat TrackingLink
ICASSP 2026CMSA-Mamba: Hierarchical State Space Modeling for Audio-Based Depression DetectionLink

Time Series

VenuePaperLinkCode
ECAI 2024TimeMachine: A Time Series is Worth 4 Mambas for Long-term ForecastingLinkCode
Information Fusion 2025TSCMamba: Mamba Meets Multi-View Learning for Time Series ClassificationLink
NeurIPS 2024Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space ModelsLink
CIKM 2025SST: Multi-Scale Hybrid Mamba-Transformer Experts for Time Series ForecastingLinkCode
IJCAI 2024 WorkshopSpoT-Mamba: Learning Long-Range Dependency on Spatio-Temporal Graphs with Selective State SpacesLinkCode
ICECCE 2024Integration of Mamba and Transformer -- MAT for Long-Short Range Time Series Forecasting with Application to Weather DynamicsLink
IEEE IOTJ 2024HARMamba: Efficient and Lightweight Wearable Sensor Human Activity Recognition Based on Bidirectional MambaLink
SLT 2024SWIM: Short-Window CNN Integrated with Mamba for EEG-Based Auditory Spatial Attention DecodingLinkCode
IEEE GRSL 2024SPPMamba: State Space Models for Seismic Phase Arrival PickingLink
NeurIPS 2024 WorkshopSequential Order-Robust Mamba for Time Series ForecastingLinkCode
Scientific Reports 2024Application of multi-modal temporal neural network based on enhanced sparrow optimization in lithium battery life predictionLink
Scientific Reports 2024Mastering seismic time series response predictions using an attention-Mamba transformer model for bridge bearings and piers across varied testing conditionsLink
ICASSP 2025SSM2Mel: State Space Model to Reconstruct Mel Spectrogram from the EEGLink
CGI 2024Mamba-Spike: Enhancing the Mamba Architecture with a Spiking Front-End for Efficient Temporal Data ProcessingLinkCode
KDD 2025SDE: A Simplified and Disentangled Dependency Encoding Framework for State Space Models in Time Series ForecastingLink
ISCAS 2025SlimSeiz: Efficient Channel-Adaptive Seizure Prediction Using a Mamba-Enhanced NetworkLinkCode
KDD 2025SSD-TS: Exploring the Potential of Linear State Space Models for Diffusion Models in Time Series ImputationLink
ICLR 2025FACTS: A Factored State-Space Framework For World ModellingLinkCode
ICASSP 2025MSEMG: Surface Electromyography Denoising with a Mamba-based Efficient NetworkLinkCode
ICBC 2025CryptoMamba: Leveraging State Space Models for Accurate Bitcoin Price PredictionLinkCode
MICCAI 2025MambaMER: Adaptive EEG-Guided Multimodal Emotion Recognition with MambaLink
ICLR 2025 OralHigh-Dynamic Radar Sequence Prediction for Weather Nowcasting Using Spatiotemporal Coherent Gaussian RepresentationLink
NeurIPS 2025RiverMamba: A State Space Model for Global River Discharge and Flood ForecastingLink

If you find this repository is useful for you, please cite our paper:

@misc{2024visual_mamba,
      title={Visual Mamba: A Survey and New Outlooks},
      author={Rui Xu and Shu Yang and Yihui Wang and Yu Cai and Bo Du and Hao Chen},
      year={2024},
      eprint={2404.18861},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Other works of HKUST SMART Lab:

@inproceedings{MambaMIL,
  author       = {Shu Yang and Yihui Wang and Hao Chen},
  title        = {MambaMIL: Enhancing Long Sequence Modeling with Sequence Reordering in Computational Pathology},
  booktitle    = {International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)},
  volume       = {15004},
  pages        = {296--306},
  publisher    = {Springer},
  year         = {2024}
}