World Models
18 AI Wiki articles on World Models. The most referenced are NVIDIA Cosmos, Genie 3 and World Labs.
18 articlesRSS
Showing 1-18 of 18 articles
Atlas (World Labs)
Atlas is an early-access world model announced by World Labs on September 1, 2026. World Labs describes it as an "omni model" for camera-controlled image and...
Computer VisionGenerative AI
Dreamer (reinforcement learning)
Dreamer is a family of model-based reinforcement learning agents that learn a compact world model of their environment and then improve their behavior by...
Reinforcement Learning
GAIA-2 (Wayve)
GAIA-2 (Generative AI for Autonomy 2) is a controllable, multi-camera generative world model for autonomous driving, announced by the British self-driving...
AI ModelsAutonomous Vehicles
GAIA-3 (Wayve)
GAIA-3 is a 15-billion-parameter generative world model for autonomous driving released by Wayve on 2 December 2025, the third generation in the company's GAIA...
AI ModelsAutonomous Vehicles
GAIA-4 (Wayve)
GAIA-4 is a multimodal generative world model for closed-loop autonomous driving simulation, announced by the British self-driving company Wayve on 3 August...
AI ModelsAutonomous Vehicles
Genie (DeepMind)
Genie is an 11-billion-parameter generative interactive environment from Google DeepMind, described by its creators as the first foundation world model: it...
Generative AIGoogle DeepMind
Genie 2
Genie 2 is a foundation world model developed by Google DeepMind, unveiled on December 4, 2024. It generates action-controllable, interactive three-dimensional...
Generative AIGoogle DeepMind
Genie 3
Genie 3 is a general-purpose foundation world model developed by Google DeepMind and announced on August 5, 2025, that generates interactive, navigable 3D...
AI ModelsGenerative AI
HY-World 2.0
HY-World 2.0 (also written HunyuanWorld 2.0 or Hunyuan World Model 2.0) is an open multimodal 3D world model from Tencent's Hunyuan team, with a technical...
Chinese AIMultimodal AI
Intrinsic Discovery (Induction Labs)
Intrinsic Discovery is an experimental training method introduced by Induction Labs in August 2026. It uses an intrinsically rewarded reinforcement learning...
AI AgentsAI Benchmarks
Lumo-2
Lumo-2 is a 4B-scale robot-learning model developed by Astribot. Astribot describes it as a latent world-action model: instead of rendering a future video...
AI ModelsEmbodied AI
Marble (World Labs)
Marble is a multimodal generative world model developed by World Labs, the spatial intelligence startup co-founded by Stanford computer scientist Fei-Fei Li....
AI Tools & ProductsComputer Vision
Mimic Robotics
Mimic Robotics is a Swiss robotics company that develops dexterous robot hands, human demonstration equipment, control software, and learned manipulation...
AI CompaniesEmbodied AI
NVIDIA Cosmos
NVIDIA Cosmos is a world foundation model platform developed by NVIDIA for physical AI applications, including autonomous vehicles and robotics. Announced by...
AI ModelsEmbodied AI
Reactor
Reactor is an American artificial-intelligence startup building developer infrastructure for real-time generative video and interactive world models. The...
AI CompaniesVideo Generation
V-JEPA 2
V-JEPA 2 (Video Joint Embedding Predictive Architecture 2) is an open-source video world model released by Meta AI on June 11, 2025 that learns to understand,...
AI ModelsComputer Vision
World Labs
World Labs is an American spatial-intelligence company, headquartered in San Francisco, that builds "Large World Models" (LWMs), generative AI systems that...
AI CompaniesComputer Vision
World action model
Value --- World action model (WAM); also written "world-action model" Field Build a robot policy on a video world-model backbone so one network jointly...
AI ModelsEmbodied AI