DeepVerse: 4D Autoregressive Video Generation as a World Model
-
Updated
Aug 11, 2025 - Python
DeepVerse: 4D Autoregressive Video Generation as a World Model
MaineCoon: Pursuing a Real-Time Audio-Visual Social World Model — technical report & project links. 🌐 https://mainecoon.tech/
Tiny local text-to-24x24 pixel art model, trained on roughly 200K samples in 30 minutes on an RTX 5090.
[ICLR 2025] Where Am I and What Will I See : An Auto-Regressive Model for Spatial Localization and View Prediction
[TPAMI] The official implementation of our paper "Improved and Accelerated Text-to-Image Generation with Collect, Reflect, and Refine".
Sequence-to-Sequence Generative Model for Sequential Recommender System
This repository contains Python functions for predicting time series.
Conditional Latent Autoregressive Recurrent Model (CLARM) for learning spatiotemporal dynamics
Autoregressive Inverse Design of Disordered Metamaterials for Target Nonlinear Response
Teaching material for "Introduction to temporal neural data analysis"
Blood pressure estimation using AR model
Solving the Knight's Tour puzzle using an Autoregressive Transformer
An attempt on using blockwise frequency prediction on AR image generation
Interactive S&P 500 stock price prediction app using machine learning and Streamlit. Visualise trends, forecast prices, and explore data insights.
Interactive video generation with online 4D control
GPT-style decoder-only Transformer built from scratch using TensorFlow with custom Multi-Head Attention, Positional Encoding, Hyperparameter Tuning, Text Generation, and Attention Visualization.
Generative modeling for JAX/Flax NNX: VAEs, GANs, DDPM/DDIM/score/DiT/latent diffusion, normalizing flows, energy-based, autoregressive and geometric (SE(3), protein, point cloud, mesh) models; image, text, audio, molecular, protein, tabular and time-series modalities; a shared Trainer with callbacks and extensions; evaluation through calibrax.
Three-stage forecasting study of daily COVID-19 cases and deaths in Germany using AR/ARX models, seasonal lags, regression trees, random forests, rolling-origin evaluation, and Diebold–Mariano tests.
Time Series Analysis using an autoregressive model to predict the temperature for Svalbard, Norway based on ECAD datasets
System in C++ for weather data management with interface with language Python. The python part is responsable to do predicitions of the weather of the next day.
To associate your repository with the autoregressive-model topic, visit your repo's landing page and select "manage topics."