HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

[ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, Slurm, 20+ clouds, on-prem).

Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals

[CVPR '26] SceneTok: A Compressed, Diffusable Token Space for 3D Scenes

Simulating embodied sensorimotor control with NeuroMechFly v2

NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.

Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

Two AI agents. One filesystem. Zero humans. We ran this experiment twice.

A markup-based typesetting system that is powerful and easy to learn.

Official Codebase for "DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos"

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots

Distributed Robot Interaction Dataset.

PyTorch code and models for V-JEPA self-supervised learning from video.

Scalable Option Learning

Masked Depth Modeling for Spatial Perception

Causal video-action world model for generalist robot control

Advancing Open-source World Models

World Model Inference Engine

OnlyFlow: Optical Flow based Motion Conditioning for Video Diffusion Models

A Large-scale Video Action Dataset

Vector (and Scalar) Quantization, in Pytorch

Sharp Monocular View Synthesis in Less Than a Second

PyTorch media decoding and encoding

Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition

Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos

JAX reimplementation of the DeepMind paper "Genie: Generative Interactive Environments"