---
title: "Knowledge Graph | AI World Model Relationships | world-models.io"
canonical: "https://world-models.io/en/graph/"
description: "Explore a crawlable knowledge graph of AI world models, research labs, and categories, with direct links to every represented entity."
author: "Bernard Grenat"
generated: "2026-10-30"
---

New: the Timeline is live. Track world model releases, papers, and benchmark updates in real time.

The Knowledge Hub for AI World Models

# World Models Relationship Graph

A relationship map connecting AI world models to their research labs and technical categories, with a static entity directory available before JavaScript runs.

robotics

model-based-rl

simulation

embodied-ai

## What is a world model?

A world model is an AI system that learns a predictive representation of how an environment changes over time. It can use observations, actions, or language to estimate future states and possible outcomes before an agent acts. World models support planning in model-based reinforcement learning, robotics, embodied AI, autonomous driving, and interactive simulation. This site catalogs these systems with model records, research papers, benchmark context, and source links. Start with the [world models database](https://world-models.io/en/world-models-database/), compare systems on the [leaderboard](https://world-models.io/en/leaderboard/), or read the [Performance Index methodology](https://world-models.io/en/methodology/performance-index/).

## Quick Answer

Short extractable summary preserved directly in static HTML.

- The knowledge graph connects 63 model records with 38 labs and 8 technical categories.
- The interactive canvas is an enhancement; the complete linked entity directories below are delivered in the initial HTML for crawlers, assistive technology, and no-JavaScript readers.

## Model Nodes

| Model | Lab or company | Category |
| --- | --- | --- |
| [DreamerV3](https://world-models.io/en/models/dreamer-v3/) | Google DeepMind | Model-Based RL |
| [DreamerV2](https://world-models.io/en/models/dreamer-v2/) | Google | Model-Based RL |
| [PlaNet](https://world-models.io/en/models/planet/) | Google | Model-Based RL |
| [RSSM](https://world-models.io/en/models/rssm/) | Google | Latent Dynamics |
| [NVIDIA Cosmos](https://world-models.io/en/models/nvidia-cosmos/) | NVIDIA | Foundation World Model |
| [Genie 2](https://world-models.io/en/models/genie-2/) | Google DeepMind | Generative World Model |
| [MuZero](https://world-models.io/en/models/muzero/) | Google DeepMind | Model-Based RL |
| [Predictron](https://world-models.io/en/models/predictron/) | Google DeepMind | Model-Based RL |
| [UniSim](https://world-models.io/en/models/unisim/) | Google DeepMind | Generative World Model |
| [TD-MPC2](https://world-models.io/en/models/td-mpc2/) | MIT / Meta | Model-Based RL |
| [World Models (Ha & Schmidhuber)](https://world-models.io/en/models/ha-world-model/) | Google Brain / IDSIA | Model-Based RL |
| [V-JEPA](https://world-models.io/en/models/v-jepa/) | Meta | Self-Supervised World Model |
| [IRIS](https://world-models.io/en/models/iris/) | Microsoft Research | Model-Based RL |
| [GAIA-1](https://world-models.io/en/models/gaia-1/) | Wayve | Foundation World Model |
| [Imagination-Augmented Agents (I2A)](https://world-models.io/en/models/imagination-augmented-agents/) | Google DeepMind | Model-Based RL |
| [Value Prediction Network (VPN)](https://world-models.io/en/models/value-prediction-network/) | University of Michigan / Google Brain | Model-Based RL |
| [AMI World Model](https://world-models.io/en/models/ami-world-model/) | AMI Labs | Foundation World Model |
| [Sora](https://world-models.io/en/models/sora/) | OpenAI | Generative World Model |
| [DIAMOND](https://world-models.io/en/models/diamond/) | Microsoft Research / University of Geneva | Model-Based RL |
| [Pandora](https://world-models.io/en/models/pandora/) | Tsinghua University / ByteDance | Generative World Model |
| [OASIS](https://world-models.io/en/models/oasis/) | Decart / Etched | Generative World Model |
| [Copilot4D](https://world-models.io/en/models/copilot4d/) | Waabi | Foundation World Model |
| [Genie](https://world-models.io/en/models/genie-1/) | Google DeepMind | Generative World Model |
| [I-JEPA](https://world-models.io/en/models/i-jepa/) | Meta | Self-Supervised World Model |
| [GameNGen](https://world-models.io/en/models/gamengen/) | Google Research | Generative World Model |
| [Emu Video](https://world-models.io/en/models/emu-video/) | Meta | Generative World Model |
| [3D-VLA](https://world-models.io/en/models/3d-vla/) | MIT / Tsinghua | Foundation World Model |
| [RT-2](https://world-models.io/en/models/rt-2/) | Google DeepMind | Foundation World Model |
| [Large World Model (LWM)](https://world-models.io/en/models/lwm/) | UC Berkeley | Foundation World Model |
| [Stable Video Diffusion](https://world-models.io/en/models/stable-video-diffusion/) | Stability AI | Generative World Model |
| [MILE](https://world-models.io/en/models/mile/) | Wayve | Foundation World Model |
| [STEVE-1](https://world-models.io/en/models/steve-1/) | UT Austin | Generative World Model |
| [Gen-3 Alpha](https://world-models.io/en/models/gen-3-alpha/) | Runway | Generative World Model |
| [Genie 3](https://world-models.io/en/models/genie-3/) | Google DeepMind | Generative World Model |
| [V-JEPA 2](https://world-models.io/en/models/v-jepa-2/) | Meta | Self-Supervised World Model |
| [LeWorldModel](https://world-models.io/en/models/leworldmodel/) | Mila / NYU / Samsung SAIL | Self-Supervised World Model |
| [PixVerse R1](https://world-models.io/en/models/pixverse-r1/) | PixVerse | Generative World Model |
| [Marble](https://world-models.io/en/models/marble/) | World Labs | Foundation World Model |
| [1X World Model](https://world-models.io/en/models/1x-world-model/) | 1X | Foundation World Model |
| [PlayWorld](https://world-models.io/en/models/playworld/) | Princeton University | Generative World Model |
| [WHAM](https://world-models.io/en/models/wham/) | Microsoft Research / Ninja Theory | Generative World Model |
| [WHAM-RT](https://world-models.io/en/models/wham-rt/) | Microsoft Research / Ninja Theory | Generative World Model |
| [GAIA-2](https://world-models.io/en/models/gaia-2/) | Wayve | Generative World Model |
| [Waabi World](https://world-models.io/en/models/waabi-world/) | Waabi | Generative World Model |
| [Odyssey-2](https://world-models.io/en/models/odyssey-2/) | Odyssey | Foundation World Model |
| [HY-World 2.0](https://world-models.io/en/models/hy-world-2/) | Tencent Hunyuan | Foundation World Model |
| [RELIC](https://world-models.io/en/models/relic/) | Adobe Research | Generative World Model |
| [Matrix-Game 2.0](https://world-models.io/en/models/matrix-game-2/) | Skywork AI | Generative World Model |
| [HY-World 1.5](https://world-models.io/en/models/hy-world-1-5/) | Tencent Hunyuan | Generative World Model |
| [LingBot-World](https://world-models.io/en/models/lingbot-world/) | Ant Group | Generative World Model |
| [HiDream-O1-World](https://world-models.io/en/models/hidream-o1-world/) | HiDream.ai | Generative World Model |
| [Alaya-EVOKE](https://world-models.io/en/models/alaya-evoke/) | Alaya Lab | Generative World Model |
| [AlayaWorld](https://world-models.io/en/models/alaya-world/) | Alaya Lab | Generative World Model |
| [Lyra 2.0](https://world-models.io/en/models/lyra-2/) | NVIDIA | Generative World Model |
| [SANA-WM](https://world-models.io/en/models/sana-wm/) | NVIDIA | Generative World Model |
| [DreamX-World](https://world-models.io/en/models/dreamx-world/) | Amap | Generative World Model |
| [ABot-World](https://world-models.io/en/models/abot-world/) | Amap | Generative World Model |
| [InSpatio-World](https://world-models.io/en/models/inspatio-world/) | InSpatio | Generative World Model |
| [Fantasy-World](https://world-models.io/en/models/fantasy-world/) | Amap | Generative World Model |
| [Infinite-World](https://world-models.io/en/models/infinite-world/) | Meituan | Generative World Model |
| [MatrixGame3](https://world-models.io/en/models/matrix-game-3/) | Skywork AI | Generative World Model |
| [HY-GameCraft](https://world-models.io/en/models/hy-gamecraft/) | Tencent Hunyuan | Generative World Model |
| [Astra](https://world-models.io/en/models/astra-world-model/) | Tsinghua University | Generative World Model |

## Lab Nodes

| Lab | Type | Focus |
| --- | --- | --- |
| [Google DeepMind](https://world-models.io/en/labs/deepmind/) | industry | model-based-rl, generative-world-models, planning, games, robotics |
| [NVIDIA Research](https://world-models.io/en/labs/nvidia/) | industry | foundation-world-models, physical-ai, autonomous-driving, robotics, video-generation |
| [Meta FAIR](https://world-models.io/en/labs/meta-fair/) | industry | self-supervised-learning, jepa, embodied-ai, autonomous-intelligence |
| [Mila / NYU / Samsung SAIL](https://world-models.io/en/labs/mila-nyu-samsung-sail/) | academic | self-supervised-learning, jepa, physical-reasoning, embodied-ai |
| [AMI Labs](https://world-models.io/en/labs/ami-labs/) | industry | multimodal-world-models, embodied-ai, language-conditioned-robotics, foundation-models |
| [UC Berkeley](https://world-models.io/en/labs/uc-berkeley/) | academic | model-based-rl, robotics, visual-rl, sim-to-real |
| [Stanford University](https://world-models.io/en/labs/stanford/) | academic | robotics, embodied-ai, manipulation, simulation |
| [Carnegie Mellon University](https://world-models.io/en/labs/cmu/) | academic | robotics, autonomous-systems, model-based-learning |
| [Toyota Research Institute](https://world-models.io/en/labs/toyota-research/) | industry | autonomous-driving, robotics, physical-ai |
| [MIT CSAIL](https://world-models.io/en/labs/mit/) | academic | model-based-rl, planning, embodied-ai, scalable-agents |
| [OpenAI](https://world-models.io/en/labs/openai/) | industry | video-generation, world-simulation, foundation-models, generative-ai |
| [Wayve](https://world-models.io/en/labs/wayve/) | industry | autonomous-driving, generative-world-models, end-to-end-driving, scenario-generation |
| [PixVerse Research](https://world-models.io/en/labs/pixverse/) | industry | real-time-world-models, interactive-generation, multiplayer-experiences, video-generation |
| [Decart](https://world-models.io/en/labs/decart/) | industry | real-time-world-models, interactive-generation, neural-game-engines |
| [Waabi](https://world-models.io/en/labs/waabi/) | industry | autonomous-driving, lidar-world-models, 4d-prediction, closed-loop-simulation |
| [Microsoft Research](https://world-models.io/en/labs/microsoft-research/) | industry | autoregressive-world-models, diffusion-rl, sample-efficient-rl |
| [Google Research](https://world-models.io/en/labs/google-research/) | industry | neural-game-engines, world-simulation, video-understanding |
| [Stability AI](https://world-models.io/en/labs/stability-ai/) | industry | video-generation, diffusion-models, open-source-ai |
| [Runway](https://world-models.io/en/labs/runway/) | industry | video-generation, creative-ai, controllable-generation |
| [UT Austin](https://world-models.io/en/labs/ut-austin/) | academic | instruction-following, open-world-agents, video-pretraining |
| [World Labs](https://world-models.io/en/labs/world-labs/) | industry | 3d-generation, multimodal-world-models, persistent-worlds, spatial-reasoning |
| [1X](https://world-models.io/en/labs/1x/) | industry | humanoid-robotics, physical-ai, video-world-models, embodied-ai |
| [Princeton University](https://world-models.io/en/labs/princeton/) | academic | robotics, world-models, manipulation, autonomous-data-collection |
| [Tsinghua University](https://world-models.io/en/labs/tsinghua/) | academic | embodied-ai, generative-world-models, robotics, 3d-reasoning |
| [ByteDance Research](https://world-models.io/en/labs/bytedance/) | industry | generative-world-models, video-generation, embodied-ai |
| [University of Geneva](https://world-models.io/en/labs/university-of-geneva/) | academic | model-based-rl, diffusion-models, world-models |
| [IDSIA](https://world-models.io/en/labs/idsia/) | academic | foundational-world-models, model-based-rl, generative-world-models |
| [Etched](https://world-models.io/en/labs/etched/) | industry | real-time-world-models, interactive-generation, neural-game-engines |
| [Odyssey](https://world-models.io/en/labs/odyssey/) | industry | interactive-world-models, causal-video, real-time-generation |
| [Tencent Hunyuan](https://world-models.io/en/labs/tencent-hunyuan/) | industry | 3d-world-models, multimodal-generation, world-reconstruction |
| [Adobe Research](https://world-models.io/en/labs/adobe-research/) | industry | interactive-world-models, long-horizon-memory, video-generation |
| [Skywork AI](https://world-models.io/en/labs/skywork-ai/) | industry | interactive-world-models, real-time-generation, open-source |
| [Ant Group](https://world-models.io/en/labs/ant-group/) | industry | interactive-world-models, video-generation, embodied-simulation |
| [HiDream.ai](https://world-models.io/en/labs/hidream-ai/) | industry | interactive-world-models, video-generation |
| [Alaya Lab](https://world-models.io/en/labs/alaya-lab/) | industry | persistent-world-models, interactive-video, world-state-memory |
| [Amap](https://world-models.io/en/labs/amap/) | industry | interactive-world-models, action-conditioned-video, camera-control |
| [InSpatio](https://world-models.io/en/labs/inspatio/) | industry | spatial-world-models, interactive-video, camera-control |
| [Meituan](https://world-models.io/en/labs/meituan/) | industry | interactive-world-models, evaluation, action-conditioning |

## Category Nodes

| Category | Definition |
| --- | --- |
| [Model-Based RL](https://world-models.io/en/categories/model-based-rl/) | Model-based reinforcement learning is an approach where agents learn a predictive model of the environment (a world model) and use it to simulate outcomes, plan ahead, and learn from imagined experience. |
| [Embodied AI](https://world-models.io/en/categories/embodied-ai/) | Embodied AI concerns AI systems that interact with and learn from the physical world through a body, whether a robot, an autonomous vehicle, or a virtual agent with physical constraints. |
| [Generative World Models](https://world-models.io/en/categories/generative-world-models/) | Generative world models are AI systems that learn to generate realistic simulated environments, replacing or augmenting hand-crafted simulators with learned models of world dynamics. |
| [Latent Dynamics](https://world-models.io/en/categories/latent-dynamics/) | Latent dynamics models learn compressed representations of environment dynamics in a latent (hidden) space, enabling efficient prediction and planning without operating in pixel space. |
| [Autonomous Agents](https://world-models.io/en/categories/autonomous-agents/) | Autonomous agents use world models to make independent decisions in complex, open-ended environments by predicting consequences and planning actions. |
| [Video World Models](https://world-models.io/en/categories/video-world-models/) | Video world models understand and generate video as a representation of world dynamics and physics, learning temporal structure, object permanence, and physical interactions from video data. |
| [Foundation World Models](https://world-models.io/en/categories/foundation-world-models/) | Foundation world models are large-scale, general-purpose models trained on massive datasets to learn broad representations of world dynamics. They aim to serve as versatile base models for diverse downstream tasks, from robotics to autonomous driving to video generation. |
| [Self-Supervised World Models](https://world-models.io/en/categories/self-supervised-world-models/) | Self-supervised world models learn representations of environment dynamics without explicit labels or reward signals. They leverage prediction in abstract representation space, predicting future states, video frames, or embeddings, to build internal models of how the world works. |