[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

Generative Models Tutorial with Demo: Bayesian Classifier Sampling, Variational Auto Encoder (VAE), Generative Adversial Networks (GANs), Popular GANs Architectures, Auto-Regressive Models, Important Generative Model Papers, Courses, etc..

OmniTokenizer: one model and one weight for image-video joint tokenization.

Phase-amplitude coupling (PAC) toolbox

Heart rate variability (HRV) analysis tool to detect autonomic nerve state

Covid-19 India's statewide analysis with census data 2011 and Kaggle data

Auto-regressive causal language model for molecule (SMILES) and reaction template (SMARTS) generation based on the Hugging Face implementation of OpenAI's GPT-2 transformer decoder model

Implementing Time Series Auto Regressive Model (AR Model) from Scratch in Python

About Code for the paper "NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models" (EMNLP 2023 Findings)

Graph neural network models to perform link prediction on the nba and ncaa point differential graph on seasons 2013-2019, 2021.

📈 Application of neural networks in the prediction of PETR4.SA shares, compared with statistical models

Learned time series analysis from Quantstart

Forecast the Airline Flight Demand Using ARIMA and AR

Full Stack Machine Learning

This project demonstrates text summarization using the BART (Bidirectional and Auto-Regressive Transformers) model. BART is a transformer model trained as a denoising autoencoder and is effective for text generation tasks such as summarization.

This repository focuses on predicting Apple Inc.'s stock prices using time series analysis from 2013 to 2018. The project involves data exploration, stationarity analysis, time series decomposition, model development, and generating insights to assist investors.

Predicting the monthly electricity consumption for 3248 households in the coming year (January to December), provided with historical half-hourly energy readings for the 3248 smart meters.