A reference catalog for embodied AI
The reference catalog of world models and simulation environments.
Browse, search, and compare the world model ecosystem — the models, the simulation environments they run in, and the relationships between them.
Genie 2
Google DeepMind
Foundation world model that generates playable, action-controllable 3D environments from a single image.
1 relationships
NVIDIA Cosmos
NVIDIA
World foundation model platform for physical AI, with open diffusion and autoregressive video world models.
3 relationships
V-JEPA 2
Meta AI (FAIR)
Self-supervised video joint-embedding predictive world model for understanding and planning.
1 relationships
DreamerV3
Google DeepMind / Danijar Hafner
General model-based RL agent that learns a world model (RSSM) and plans in imagination across domains.
2 relationships
World Labs
World Labs
Large World Models that generate persistent, explorable 3D worlds from a single image or prompt.
1 relationships
GAIA-2
Wayve
Controllable video generative world model for autonomous driving scenario synthesis.
2 relationships
Oasis
Decart / Etched
Real-time, fully generated playable world model — an interactive game rendered frame-by-frame by a transformer.
SpAItial
SpAItial
Spatial Foundation Models that generate interactive, photorealistic 3D environments from a text prompt or image.
1 relationships
Pantograph Pan-1
Pantograph
Interactive world model pretrained on internet-scale video that achieves diverse goals in Minecraft via RL-based pretraining.
2 relationships
MuJoCo
Google DeepMind
Fast, accurate rigid-body physics engine for robotics and RL; MJX adds GPU-batched, differentiable simulation.
4 relationships
NVIDIA Isaac Sim
NVIDIA
Omniverse/USD robotics simulator with photorealistic RTX rendering and physically accurate sensor simulation.
4 relationships
Genesis (World 1.0)
Genesis AI
Generative, GPU-accelerated simulation platform for robotics; World 1.0 pairs the multi-physics engine with the Nyx photorealistic renderer and the Quadrants compiler.
2 relationships
AI Habitat
Meta AI (FAIR)
High-performance simulator for embodied AI in photorealistic 3D scans, with human-robot interaction (Habitat 3.0).
ManiSkill
UC San Diego (Hao Su Lab)
GPU-parallelized robotic manipulation simulation and benchmark built on SAPIEN.
1 relationships
Antioch
Antioch
Full-stack cloud simulation platform to test and deploy autonomous systems, with parallel cloud runs and an agent.
1 relationships
NVIDIA Newton
NVIDIA / Google DeepMind / Disney Research
Open-source, GPU-accelerated, differentiable physics engine for robot learning; built on Warp + OpenUSD and governed by the Linux Foundation.
2 relationships
MuJoCo Playground
Google DeepMind
Open-source suite of 50+ GPU-accelerated robot-learning environments built on MuJoCo MJX for sim-to-real research.
2 relationships
Brax
JAX-based, massively-parallel differentiable physics engine for reinforcement learning on GPU/TPU.
1 relationships
NVIDIA Isaac Lab
NVIDIA
Open GPU-accelerated robot-learning framework built on Isaac Sim; standardizes massively-parallel RL and imitation training environments.
2 relationships
Genie 3
Google DeepMind
Real-time interactive general-purpose world model generating playable 3D environments from a prompt.