Ctrl-World: A Controllable Generative World Model for Robot Manipualtion

A minimal implementation of DeepMind's Genie world model

Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

[CVPR 2025] The offical Implementation of "Universal Actions for Enhanced Embodied Foundation Models"

Cosmos-Curate is a powerful video curation system that processes, analyzes, and organizes video content using advanced AI models and distributed computing.

Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control inputs.

Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.

HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo

Official repository for LTX-Video

Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.

This code corresponds to simulation environments used as part of the DexMimicGen project.

Examples for the course [real world robotics](https://rwr.ethz.ch/)

Unified framework for robot learning built on NVIDIA Isaac Sim

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.

Allegro is a powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple text input.

Flyability Autonomy Test Game