---
title: "World Models Timeline | Latest Releases & Updates | world-models.io"
canonical: "https://world-models.io/en/timeline/"
description: "Track the latest world model releases, research papers, benchmark updates, and lab announcements in real time."
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 Timeline

A chronological feed of world model releases, research breakthroughs, and industry updates.

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 timeline tracks published world model papers, product releases, benchmark updates, and lab announcements in chronological order.
- Use it to monitor what changed recently and connect each event back to the relevant models, labs, and sources.

## Editorial Trust Signals

Editorial provenance and refresh policy preserved directly in static HTML.

**Published by** world-models.io editorial board.

**Lead editor** world-models.io editorial board - Event review and source normalization.

This hub monitors verified primary sources, normalizes event data, and publishes reviewed summaries linked to the broader knowledge graph.

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: 2026-09-27.

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.](https://world-models.io/en/editorial-policy/)

Primary sources only

Last reviewed date visible

Methodology documented

Source links included

Correction channel published

Review date visible

## Timeline Snapshot

Static overview of the release archive.

The timeline tracks published world model papers, product releases, benchmark updates, and lab announcements in chronological order.

This static snapshot exposes 21 timeline events before JavaScript runs, so crawlers can discover the event archive and detail pages directly from HTML.

## Latest Timeline Events

Most recent events rendered directly in static HTML.

| Event | Source | Type | Published | Summary |
| --- | --- | --- | --- | --- |
| [World-models.io launches a read-only MCP connector for AI clients](https://world-models.io/en/timeline/world-models-mcp-connector-launch/) | world-models.io Editorial | editorial_publish | 2026-10-30T15:00:00Z | World-models. io launches a read-only MCP connector for AI clients. |
| [Runway introduces Praxis-1, an open-weight world action model for robotics](https://world-models.io/en/timeline/runway-praxis-1-world-action-model/) | Runway Research | model_release | 2026-09-30T00:00:00Z | Runway introduces Praxis-1, a world action model that transfers large-scale video pretraining into robot control. |
| [GAVEL proposes graph world models for verified long-horizon LLM planning](https://world-models.io/en/timeline/gavel-graph-world-models-llm-planning/) | arXiv | paper_published | 2026-09-16T18:25:58Z | GAVEL presents an explicit graph world model for checking and repairing long-horizon plans proposed by language models. |
| [PSG-JEPA asks whether forward prediction is enough for physically grounded world models](https://world-models.io/en/timeline/psg-jepa-physical-state-grounding/) | arXiv | paper_published | 2026-08-07T04:44:16Z | PSG-JEPA studies whether forward prediction alone gives a JEPA world model the physically meaningful state needed for control. |
| [A practical taxonomy for AI world models, published by the editorial team](https://world-models.io/en/timeline/practical-taxonomy-ai-world-models/) | world-models.io Editorial | editorial_publish | 2026-07-14T10:00:00Z | A new editorial taxonomy compares AI world models across domain, function, internal representation, temporal horizon, action conditioning, evaluation type, availability. |
| [Physically Viable World Models make the case for query-conditioned embodied AI](https://world-models.io/en/timeline/physically-viable-world-models-query-conditioned-ai/) | arXiv | paper_published | 2026-05-28T20:18:22Z | This position paper argues that embodied world models should answer intervention queries about the consequences of actions, not merely generate visually plausible future. |
| [Google DeepMind unveils Genie 3: real-time interactive world model at 720p/24fps](https://world-models.io/en/timeline/deepmind-genie-3-release/) | Google DeepMind | model_release | 2026-04-22T14:00:00Z | DeepMind announces Genie 3, a real-time foundation world model generating interactive 3D environments at 720p and 24 fps from text prompts. |
| [NVIDIA Cosmos-Predict2 released: improved physical consistency for robotics simulation](https://world-models.io/en/timeline/nvidia-cosmos-predict2/) | NVIDIA Research | model_release | 2026-04-18T16:00:00Z | NVIDIA Research releases Cosmos-Predict2, a second-generation diffusion world model with stronger physical consistency for robot policy pretraining. |
| [Wayve publishes GAIA-2 technical report: scalable driving world model](https://world-models.io/en/timeline/wayve-gaia2-technical-report/) | arXiv | paper_published | 2026-04-12T09:00:00Z | Wayve releases the GAIA-2 technical report detailing a multi-camera, multi-condition driving world model trained on 4,700 hours of urban driving. |
| [Meta FAIR releases V-JEPA 2 checkpoints under non-commercial license](https://world-models.io/en/timeline/meta-vjepa2-checkpoints/) | Meta FAIR | model_release | 2026-04-08T15:00:00Z | Meta FAIR publishes V-JEPA 2 model checkpoints (ViT-L, ViT-H, ViT-g) on Hugging Face under a research-only license. |
| [world-models.io launches 'Frontier World Models 2026' editorial collection](https://world-models.io/en/timeline/editorial-frontier-collection-2026/) | world-models.io Editorial | collection_update | 2026-04-05T10:00:00Z | A new curated collection on world-models. |
| [1X Technologies and DeepMind announce joint NEO world model for humanoid manipulation](https://world-models.io/en/timeline/1x-deepmind-neo-world-model/) | Google DeepMind | model_release | 2026-03-28T13:00:00Z | 1X Technologies and Google DeepMind announce a joint research effort on NEO, a world model for humanoid manipulation trained on teleoperation data. Initial results show 2. |

## Timeline Event Directory

Canonical crawlable directory of timeline events. JavaScript filters can enhance this same archive for interactive readers.

| Event | Source | Type | Published | Related Models |
| --- | --- | --- | --- | --- |
| [World-models.io launches a read-only MCP connector for AI clients](https://world-models.io/en/timeline/world-models-mcp-connector-launch/) | world-models.io Editorial | editorial_publish | 2026-10-30T15:00:00Z | 0 |
| [Runway introduces Praxis-1, an open-weight world action model for robotics](https://world-models.io/en/timeline/runway-praxis-1-world-action-model/) | Runway Research | model_release | 2026-09-30T00:00:00Z | 0 |
| [GAVEL proposes graph world models for verified long-horizon LLM planning](https://world-models.io/en/timeline/gavel-graph-world-models-llm-planning/) | arXiv | paper_published | 2026-09-16T18:25:58Z | 0 |
| [PSG-JEPA asks whether forward prediction is enough for physically grounded world models](https://world-models.io/en/timeline/psg-jepa-physical-state-grounding/) | arXiv | paper_published | 2026-08-07T04:44:16Z | 1 |
| [A practical taxonomy for AI world models, published by the editorial team](https://world-models.io/en/timeline/practical-taxonomy-ai-world-models/) | world-models.io Editorial | editorial_publish | 2026-07-14T10:00:00Z | 0 |
| [Physically Viable World Models make the case for query-conditioned embodied AI](https://world-models.io/en/timeline/physically-viable-world-models-query-conditioned-ai/) | arXiv | paper_published | 2026-05-28T20:18:22Z | 0 |
| [Google DeepMind unveils Genie 3: real-time interactive world model at 720p/24fps](https://world-models.io/en/timeline/deepmind-genie-3-release/) | Google DeepMind | model_release | 2026-04-22T14:00:00Z | 1 |
| [NVIDIA Cosmos-Predict2 released: improved physical consistency for robotics simulation](https://world-models.io/en/timeline/nvidia-cosmos-predict2/) | NVIDIA Research | model_release | 2026-04-18T16:00:00Z | 1 |
| [Wayve publishes GAIA-2 technical report: scalable driving world model](https://world-models.io/en/timeline/wayve-gaia2-technical-report/) | arXiv | paper_published | 2026-04-12T09:00:00Z | 0 |
| [Meta FAIR releases V-JEPA 2 checkpoints under non-commercial license](https://world-models.io/en/timeline/meta-vjepa2-checkpoints/) | Meta FAIR | model_release | 2026-04-08T15:00:00Z | 1 |
| [world-models.io launches 'Frontier World Models 2026' editorial collection](https://world-models.io/en/timeline/editorial-frontier-collection-2026/) | world-models.io Editorial | collection_update | 2026-04-05T10:00:00Z | 0 |
| [1X Technologies and DeepMind announce joint NEO world model for humanoid manipulation](https://world-models.io/en/timeline/1x-deepmind-neo-world-model/) | Google DeepMind | model_release | 2026-03-28T13:00:00Z | 0 |
| [Google DeepMind releases Genie 2: a foundation world model for 3D environments](https://world-models.io/en/timeline/deepmind-genie-2-release/) | Google DeepMind | model_release | 2026-03-14T14:00:00Z | 1 |
| [NVIDIA Cosmos World Foundation Models open-sourced on Hugging Face](https://world-models.io/en/timeline/nvidia-cosmos-open-source/) | NVIDIA Research | model_release | 2026-03-12T16:00:00Z | 1 |
| [Meta FAIR publishes V-JEPA 2: understanding, prediction, and planning from video](https://world-models.io/en/timeline/meta-vjepa2-paper/) | arXiv | paper_published | 2026-03-10T09:00:00Z | 1 |
| [A comprehensive survey organizes world models for embodied AI](https://world-models.io/en/timeline/stanford-survey-world-models-embodied/) | arXiv | paper_published | 2026-03-08T11:00:00Z | 0 |
| [world-models.io adds interactive Model Comparator and Performance Index methodology page](https://world-models.io/en/timeline/editorial-comparator-methodology/) | world-models.io Editorial | editorial_publish | 2026-03-06T15:00:00Z | 0 |
| [UC Berkeley releases UniPi: Universal World Model for Robot Policy Learning](https://world-models.io/en/timeline/berkeley-unipi-release/) | UC Berkeley | model_release | 2026-03-04T13:00:00Z | 1 |
| [Leaderboard update: Performance Index recalculated with March 2026 benchmark data](https://world-models.io/en/timeline/leaderboard-march-2026-update/) | world-models.io Editorial | leaderboard_update | 2026-03-02T10:00:00Z | 2 |
| [New collection: 'World Models for Autonomous Driving' curated with 12 key models](https://world-models.io/en/timeline/collection-autonomous-driving/) | world-models.io Editorial | collection_update | 2026-02-28T14:00:00Z | 0 |
| [DiffuseBot uses physics-augmented diffusion to design soft robots](https://world-models.io/en/timeline/toyota-diffusebot/) | arXiv | paper_published | 2026-02-25T09:30:00Z | 0 |

## External Sources

Primary references and official sources surfaced directly in static HTML for crawlers and no-JS readers.

- [Google DeepMind research](https://deepmind.google/research/) Primary lab source
- [NVIDIA Research](https://research.nvidia.com) Primary lab source
- [arXiv](https://arxiv.org) Primary paper source