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, compare systems on the leaderboard, or read the Performance Index methodology.
Static HTML snapshot of the model record for crawlers and no-JS readers.
| Attribute | Value |
|---|---|
| Model | UniSim |
| Lab / Organization | DeepMind |
| Category | Generative World Model |
| Subtype | Universal Simulator |
| World Model Type | Action-conditioned video simulator |
| Primary Domain | Robotics / Simulation |
| Architecture | Video diffusion model with action conditioning |
| Modality | Video + Actions |
| Training Method | Multi-domain video pre-training with action-conditioned generation |
| Status | active |
| Year | 2023 |
| Performance Index | 72/100 (medium confidence, v1.1) |
Main editorial body preserved directly in static HTML.
UniSim is a generative model that acts as a universal simulator of real-world interaction. Unlike standard video generators, UniSim is action-conditioned: it simulates what would happen given a specific action, making it a true interactive simulator. It can simulate visual outcomes of actions across domains, from robot manipulation to human activities.
UniSim is an action-conditioned video simulator developed by Google DeepMind in 2023 for robotics / simulation.
Short extractable facts for answer engines and no-JS readers.
| Signal | Value |
|---|---|
| Definition | UniSim is an action-conditioned video simulator developed by Google DeepMind in 2023 for robotics / simulation. |
| Short Description | A universal simulator that learns to simulate real-world interactions from diverse data sources. |
| Benchmark Rows | 1 |
| FAQ Entries | 1 |
| Related Models | 2 |
| Related Guides | 1 |
| Related Research Topics | 4 |
| Last Updated | 2026-03-08 |
Key capabilities associated with this model.
Representative applications attached to this model record.
Balanced assessment surfaced in static HTML.
Published benchmark evidence attached to this model record.
| Benchmark | Metric | Result | Source |
|---|---|---|---|
| Robot Policy Training | Success Rate 78 % | Significant improvement over baselines | Source |
Primary references preserved in static HTML for citation extraction.
| Reference | Link |
|---|---|
| Yang et al., 2023. Learning Interactive Real-World Simulators. arXiv:2310.06680 | Open source |
Nearby models linked from the current editorial record.
| Model | Category | World Model Type | Index v1.1 |
|---|---|---|---|
| NVIDIA Cosmos | Foundation World Model | Video world foundation model | 87/100 |
| Genie 2 | Generative World Model | Generative environment model | 79/100 |
Side-by-side comparisons already connected to this model.
| Comparison | Matchup | Summary |
|---|---|---|
| NVIDIA Cosmos vs DreamerV3 | NVIDIA Cosmos vs DreamerV3 | Cosmos and DreamerV3 represent two different scales and approaches to world modeling: Cosmos is a foundation-scale video world model platform for physical AI, while DreamerV3 is a sample-efficient RL agent with learned dynamics. |
| Genie 2 vs UniSim | Genie 2 vs UniSim | Both are generative world models that create interactive environments, but Genie 2 generates 3D worlds from single images while UniSim learns a universal action-conditioned simulator from diverse real-world data. |
| NVIDIA Cosmos vs Genie 2 | NVIDIA Cosmos vs Genie 2 | Two foundation-scale world models with different strategies: Cosmos is an open industrial platform for physical AI training, while Genie 2 is a DeepMind research system that generates interactive 3D environments from images. |
| UniSim vs Genie 2 | UniSim vs Genie 2 | Both are large-scale generative world simulators, but UniSim focuses on unified simulation across real-world domains while Genie 2 generates persistent, explorable 3D environments from single images. |
| UniSim vs Genie 2 | UniSim vs Genie 2 | Two DeepMind generative world models targeting interactive simulation. UniSim uses a diffusion-based approach for universal simulation, while Genie 2 generates playable 3D environments from a single image. |
Crawler-readable guide links tied to this model.
| Guide | Summary |
|---|---|
| How to Apply World Models in Robotics | How to use world models for robot learning: from simulation-based training to real-world deployment and sim-to-real transfer. |
Connected research areas surfaced directly in static HTML.
| Topic | Summary |
|---|---|
| Self-Supervised World Models | How self-supervised world models learn environment dynamics without rewards, from JEPA and V-JEPA to predictive latent representations. |
| World Models for Robotics | How world models improve robot learning, learned simulation, safe exploration, and sim-to-real transfer across manipulation, navigation, and control. |
| AI Simulation Systems | How AI simulation systems and learned simulators reduce the reality gap and extend or replace hand-crafted engines for autonomous agents. |
| Video World Models | How video world models and video generation transformers learn physics, temporal consistency, and interactive simulation from large-scale video, from OpenAI Sora and Google DeepMind Genie to NVIDIA Cosmos and V-JEPA. |
FAQ answers rendered directly into static HTML for extractable responses.
UniSim is action-conditioned: it simulates what would happen given a specific action, making it a true interactive simulator rather than just a video generation model.
Short extractable summary preserved directly in static HTML.
Editorial provenance and refresh policy preserved directly in static HTML.
Published by world-models.io editorial board.
Lead editor Tyler D. - Technical editor, methodology and benchmark analysis.
This model page synthesizes primary papers, official model pages, benchmark evidence, and related world-models.io context into a reference resource.
Each editorial page is assembled from primary sources, normalized into extractable summaries, checked for factual drift, and reviewed before publication or major refreshes. Last reviewed: 2026-03-08.
Pages are refreshed when a new paper, benchmark, release, architecture update, or stronger primary source materially changes the answer a reader or AI system should retrieve.
Each page links back to relevant primary sources and keeps a stable canonical URL so readers can verify claims, trace context, and reference the most up-to-date version. See the editorial policy.
Primary model and lab sources embedded in static HTML.