Computation-Efficient Era: A Comprehensive Survey of State Space Models in Medical Image Analysis

[ACM MM'24 Oral] RainMamba: Enhanced Locality Learning with State Space Models for Video Deraining

Official implementation of I2I-Mamba, an image-to-image translation model based on selective state spaces

[WACV2025 Oral] SUM: Saliency Unification through Mamba for Visual Attention Modeling

CVPR 2025 (Highlight)

A Comprehensive Survey of Mamba Architectures for Medical Image Analysis: Classification, Segmentation, Restoration, and Beyond

[NeurIPS 2024] Official implementation of the paper "MambaLRP: Explaining Selective State Space Sequence Models".

Official repository for Mamba-based Segmentation Model for Speaker Diarization

[AAAI 2025] SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks

DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation (NeurIPS 2024)

[MedIA'25] MambaMIM: Pre-training Mamba with State Space Token Interpolation and its Application to Medical Image Segmentation

Welcome to the world of Mamba! This repository is a curated collection of papers, tutorials, videos, and other valuable resources related to Mamba.

LC-PLM: long-context protein language model based on BiMamba-S architecture

Library for Federated Emergence & Foundation Models

Brainwave is a state-of-the-art neural decoder that transforms electroencephalogram (EEG) and brain signals into multimodal outputs including images, videos, and text.

Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Honorable Mention]

Code for paper: Revealing and Mitigating the Local Pattern Shortcuts of Mamba

Mamba SSM implementation with support for macOS Apple Silicon, enabling efficient inference and training without CUDA dependencies.

Segmentation of cancerous tumors using Mamba. Code, resources, and paper provided. We manage to make a small (42k param) model that can segment pretty well.

Official Implementation of XYScanNet (NTIRE 2025 @ CVPR)