Yousef Azizi's Projects
This repository contains implementations and illustrative code to accompany DeepMind publications
Universal neural differential equations with O(1) backprop, GPUs, and stiff+non-stiff DE solvers, demonstrating scientific machine learning (SciML) and physics-informed machine learning methods
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
Denoising Diffusion Probabilistic Models
A simple integration between Django API and React App
PyTorch implementation of the TIP2017 paper "Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising"
Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.
An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).
A Streamlit app to show how you can easily empower viewers to comment and collaborate on your app using a commenting component. The comments are hosted on a Google Sheets.
fabric is an open-source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.
FastKAN: Very Fast Implementation of Kolmogorov-Arnold Networks (KAN)
The code implements a novel method for converting random forest into a single decision tree
Code for the paper: Augmenting genetic algorithms with deep neural networks for exploring the chemical space
GAN(TK)Ā²: GAN Neural Tangent Kernel ToolKit
Code for ICCV Paper "GAN-Tree: An Incrementally Learned Hierarchical Generative Framework for Multi-Modal Data Distributions"
Code for paper "Which Training Methods for GANs do actually Converge? (ICML 2018)"
Graph Attention Networks (https://arxiv.org/abs/1710.10903)
12 Lessons, Get Started Building with Generative AI š https://microsoft.github.io/generative-ai-for-beginners/
Code release for the paper Generative Modeling With Inverse Heat Dissipation
Generative Agents: Interactive Simulacra of Human Behavior
Code for the paper "Language Models are Unsupervised Multitask Learners"
An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
Python library for digesting Persian text.
The all-in-one AI library for Persian, supporting a wide variety of tasks and modalities!