A Comprehensive Survey of Mamba in Deep Learning
-
Updated
Jun 5, 2024
A Comprehensive Survey of Mamba in Deep Learning
Statecraft - Load, store and remix states for SSMs, Mamba and Stateful models
An official implementation for SSAMBA: Self-Supervised Audio Mamba
A PyTorch implementation of the paper "ZigMa: A DiT-Style Mamba-based Diffusion Model"
Official PyTorch implementation of the CVPR 2024 paper: State Space Models for Event Cameras (Spotlight).
LLM inference in Fortran
PointMamba: A Simple State Space Model for Point Cloud Analysis
Provides a streamlined and user-friendly framework for simulating data in state space models, particularly when the number of subjects/units (n) exceeds one, a scenario commonly encountered in social and behavioral sciences. For an introduction to state space models in social and behavioral sciences, refer to Chow, Ho, Hamaker, and Dolan (2010).
PyHGF: A neural network library for predictive coding
We use EM for a mixture of state space models to perform unsupervised clustering of short trajectories.
Accelerated First Order Parallel Associative Scan
Arbitrage-free Dynamic Generalized Nelson-Siegel model of interest rates following Christensen, Diebold and Rudebusch; and its estimation using the Kalman filter / maximum likelihood.
Spectral State-Space Models
ChangeMamba: Remote Sensing Change Detection Based on Spatio-Temporal State Space Model
Translating between two sets of notation for Kalman filters
Reproducible code for our paper, "On Causal Discovery with Convergent Cross Mapping"
Variational Joint Filtering
a helper package for pomp
Neural State-Space Models and Latent Dynamics Functions in PyTorch for High-Dimensional Forecasting
This repository features implementations of Mamba SSM (LLM), leveraging a parallel algorithm specifically optimized for modern hardware, with a strong focus on GPU acceleration.
Add a description, image, and links to the state-space-model topic page so that developers can more easily learn about it.
To associate your repository with the state-space-model topic, visit your repo's landing page and select "manage topics."