awesome-vision-mamba-models

DehazeMamba: SAR-guided Optical Remote Sensing Image Dehazing with Adaptive State Space

Exploring Enhanced Contextual Information for Video-Level Object Tracking

Light-T2M: A Lightweight and Fast Model for Text-to-motion Generation

Detail Matters: Mamba-Inspired Joint Unfolding Network for Snapshot Spectral Compressive Imaging

Efficient Self-Supervised Video Hashing with Selective State Spaces

RGBT Tracking via All-layer Multimodal Interactions with Progressive Fusion Mamba

DG-Mamba: Robust and Efficient Dynamic Graph Structure Learning with Selective State Space Models

GLAM: Global-Local Variation Awareness in Mamba-based World Model

BSDB-Net: Band-Split Dual-Branch Network with Selective State Spaces Mechanism for Monaural Speech Enhancement

MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights

BrainMAP: Learning Multiple Activation Pathways in Brain Networks

Dual Mamba for Node-Specific Representation Learning: Tackling Over-Smoothing with Selective State Space Modeling

SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks

EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba

2D-CrossScan Mamba: Enhancing State Space Models with Spatially Consistent Multi-Path 2D Information Propagation

PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition

MobileMamba: Lightweight Multi-Receptive Visual Mamba Network

EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality

Mamba Knockout for Unraveling Factual Information Flow

The Hidden Attention of Mamba Models

A Survey of Mamba

A Survey on Visual Mamba

Mamba: Linear-Time Sequence Modeling with Selective State Spaces