A novel implementation of fusing ViT with Mamba into a fast, agile, and high performance Multi-Modal Model. Powered by Zeta, the simplest AI framework ever.
Implementation of Vision Mamba from the paper: "Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model" It's 2.8x faster than DeiT and saves 86.8% GPU memory when performing batch inference to extract features on high-res images
Mambular is a Python package that simplifies tabular deep learning by providing a suite of models for regression, classification, and distributional regression tasks. It includes models such as Mambular, TabM, FT-Transformer, TabulaRNN, TabTransformer, and tabular ResNets.
Integrating Mamba/SSMs with Transformer for Enhanced Long Context and High-Quality Sequence Modeling
Minimal Mamba-2 implementation in PyTorch
PyTorch Implementation of Jamba: "Jamba: A Hybrid Transformer-Mamba Language Model"
A hierarchical yaml config in Python
[CVPR'24 Spotlight] The official implementation of "State Space Models for Event Cameras"
Official implementation of I2I-Mamba, an image-to-image translation model based on selective state spaces
Implementation of PyTorch: "GAMBA: MARRY GAUSSIAN SPLATTING WITH MAMBA FOR SINGLE-VIEW 3D RECONSTRUCTION"
Recall to Imagine, a model-based RL algorithm with superhuman memory. Oral (1.2%) @ ICLR 2024
Some toy examples of score matching algorithms written in PyTorch
A human-friendly way of managing parameters in AWS SSM
Neural State-Space Models and Latent Dynamics Functions in PyTorch for High-Dimensional Forecasting
[PRCV-2024] State Space Model based Frame-Event Tracking
Implementation of a modular, high-performance, and simplistic mamba for high-speed applications
A simpler Pytorch + Zeta Implementation of the paper: "SiMBA: Simplified Mamba-based Architecture for Vision and Multivariate Time series"
Add a description, image, and links to the ssm topic page so that developers can more easily learn about it.
To associate your repository with the ssm topic, visit your repo's landing page and select "manage topics."