Paolo Muratore

open-genie. Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).

x-lstm. Pytorch implementation of the xLSTM model by Beck et al. (2024)

mamba. Pytorch (Lightning) implementation of the Mamba model

modular-diffusion. Modular PyTorch (Lightning) implementation of Diffusion Probabilistic Models

retnet-pytorch. Implementation of Retention-Network in PyTorch

variational-diffusion. Unofficial implementation of Variational Diffusion Models in PyTorch (Lightning)

LTTS. This is the repository for code associated to the paper: "Target spiking patterns enable efficient and biologicallyplausible learning for complex temporal tasks" (published in PlosONE at: https://doi.org/10.1371/journal.pone.0247014).

goal. Generalized Optimal Apprentiship Learning (GOAL): Unifying Error-Based and Target-Based Learning via Feedback Control

bayesian-flow. Unofficial Implementation of Bayesian Flow Network in easy PyTorch for didactic purposes

py-fluid. Just another Fluid Simulation, this time with Art!

FLIP2D. PIC/FLIP 2D Fluid Simulator based on Robert Bridson book

SNN. This is the first attempt to write a simple Spiking Neural Network with the aim to test it against MNIST dataset and obtein an error score lower than 5%

jamba. Pytorch (Lightning) Implementation of the Jamba Language Model

hierarchy-flow. Unofficial implementation of Hierarchical Flow (image-to-image) for didactic purposes

denoising-diffusion-pytorch. Implementation of Denoising Diffusion Probabilistic Model in Pytorch

statlearn-read. Repository for the Statistical Learning of Reading project where (borrowing from Visual Neuroscience literature) ANN architectures are used to gain insight on how brain learns to read.

video-to-piano. Python

git-playground. Playground repository, to teach git to SISSA PhD students

torch-zoo. Collection of deep models in PyTorch as learning exercises

LTTS-BC. Repository for implementing Behavioural Cloning in a Target-Based Biologically Plausible way

Fluid-Dynamics. Fluids are fun. But man, are they hard to simulate

Slow_Students. Python