Agora-1
Agora-1 is a multi-agent world model released by the AI lab Odyssey on 18 May 2026.
World Models
Explore World Models through related topics and the articles other pages reference most.
Most linked
The World Models articles that other AI Wiki pages link to most.
- NVIDIA CosmosNVIDIA Cosmos is a world foundation model platform developed by NVIDIA for physical AI applications, including autonomous vehicles and…
- Genie 3Genie 3 is a general-purpose foundation world model developed by Google DeepMind and announced on August 5, 2025, that generates…
- World LabsWorld Labs is an American spatial-intelligence company, headquartered in San Francisco, that builds "Large World Models" (LWMs), generative…
- V-JEPA 2V-JEPA 2 (Video Joint Embedding Predictive Architecture 2) is an open-source video world model released by Meta AI on June 11, 2025 that…
- Odyssey (AI lab)Odyssey is an artificial intelligence lab that builds what it calls foundation world models: causal, action-conditioned systems trained to…
- Jeff HawkeJeff Hawke (published as Jeffrey Hawke) is a New Zealand robotics and machine learning engineer who is the co-founder and chief technology…
- World action modelA world action model (WAM) is a robot policy design that builds action generation on a video world model backbone rather than on a…
- Odyssey-3Odyssey-3 is a foundation world model announced on September 15, 2026 by Odyssey, an AI lab founded in 2023 by Oliver Cameron and Jeff…
Explore articles
Browse subtopics (28)
Articles that also belong to these categories. Counts cover all of World Models.
All articles (32)AI Models (12)Generative AI (11)Computer Vision (8)Video Generation (8)Robotics (7)AI Research (5)Embodied AI (5)AI Benchmarks (4)AI Companies (4)Autonomous Vehicles (4)Google DeepMind (4)Reinforcement Learning (4)AI Agents (2)AI Tools & Products (2)Machine Learning (2)Model Evaluation (2)Multimodal AI (2)NVIDIA (2)Open Source AI (2)Physical AI (2)AI in Gaming (1)Artificial Intelligence (1)Chinese AI (1)People (1)Research Organizations (1)Robot Hardware (1)Robotics Companies (1)Training & Optimization (1)
Showing 1-32 of 32 articles
Atlas (World Labs)
Atlas is an early-access world model announced by World Labs on September 1, 2026.
CaliBench
CaliBench is a benchmark for image-to-video generative models that asks whether a model reproduces the correct distribution of physical outcomes across many generations from the same starting frame
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 "imagining" sequences of future outcomes inside that…
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 company Wayve on 26 March 2025.
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 family.
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 2026 as the latest generation of its GAIA family.
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 turns a single image, photo, or sketch into a…
Genie 2
Genie 2 is a foundation world model developed by Google DeepMind, unveiled on December 4, 2024.
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 environments from a single text prompt and runs in…
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 report and first code release published on April 16
Intrinsic Discovery (Induction Labs)
Intrinsic Discovery is an experimental training method introduced by Induction Labs in August 2026.
Inverse graphics
Inverse graphics is the problem of recovering, from one or more images, a description of the scene that produced them: the geometry, materials, lighting, camera, and in some formulations the motion and…
Jeff Hawke
Jeff Hawke (published as Jeffrey Hawke) is a New Zealand robotics and machine learning engineer who is the co-founder and chief technology officer of Odyssey
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 before acting, it predicts an action-relevant…
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.
Mimic Robotics
Mimic Robotics is a Swiss robotics company that develops dexterous robot hands, human demonstration equipment, control software, and learned manipulation policies for industrial work.
NVIDIA Cosmos
NVIDIA Cosmos is a world foundation model platform developed by NVIDIA for physical AI applications, including autonomous vehicles and robotics.
Odyssey (AI lab)
Odyssey is an artificial intelligence lab that builds what it calls foundation world models: causal, action-conditioned systems trained to predict how the world evolves from one moment to the next, and to…
Odyssey-2
Odyssey-2 is a family of real-time, interactive generative models built by the AI lab Odyssey.
Odyssey-3
Odyssey-3 is a foundation world model announced on September 15, 2026 by Odyssey, an AI lab founded in 2023 by Oliver Cameron and Jeff Hawke.
PROWL-1
PROWL-1 is a training framework from the AI lab Odyssey in which a reinforcement learning agent is paid to break a world model.
PhyGenBench
PhyGenBench (Physics Generation Benchmark) is a benchmark for testing whether text-to-video models produce videos that follow basic physical commonsense.
Physics-IQ
Physics-IQ is a benchmark that tests whether generative video models understand physical principles, by asking them to continue real videos of physical experiments and comparing the result with what actually…
Physis-Lang
Physis-Lang is a research framework from NVIDIA, the Massachusetts Institute of Technology and the University of Oxford that uses structured natural language as a representation of physical processes for video…
Project Continuum
Project Continuum is an experimental application from Runway's Runway Labs that explores real-time video in an operating-system-style interface. Runway presented an early demonstration on October 1, 2026.
RSI-Anything
RSI-Anything is a research framework for improving AI agents through world-model predictions and feedback from tests, interfaces, or experiments.
Reactor
Reactor is an American artificial-intelligence startup building developer infrastructure for real-time generative video and interactive world models.
Starchild-1
Starchild-1 is a real-time audio-video world model built by the AI lab Odyssey. It generates synchronized video and sound autoregressively, chunk by chunk, while a user streams new text, speech and action…
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, predict, and plan in the physical world by…
World Labs
World Labs is an American spatial-intelligence company, headquartered in San Francisco, that builds "Large World Models" (LWMs), generative AI systems that perceive, generate, reason about and interact with…
World action model
A world action model (WAM) is a robot policy design that builds action generation on a video world model backbone rather than on a vision-language model, so that a single network jointly predicts how a scene…