New: the Timeline is live. Track world model releases, papers, and benchmark updates in real time.
world-models.io
The Knowledge Hub for AI World Models

GAIA-2

GAIA-2 is Wayve's controllable multi-view generative world model for autonomous-driving scenarios.

robotics model-based-rl simulation embodied-ai

Key Attributes

Static HTML snapshot of the model record for crawlers and no-JS readers.

AttributeValue
ModelGAIA-2
Lab / OrganizationWayve
CategoryGenerative World Model
SubtypeControllable Multi-View Driving World Model
World Model TypeControllable multi-view generative world model for driving
Primary DomainAutonomous Driving
ArchitectureControllable multi-view generative world model
ModalityMulti-View Driving Video + Structured Conditions → Future Driving Video
Training MethodGenerative video world modeling with structured conditioning
Statusactive
Year2025

About GAIA-2

Main editorial body preserved directly in static HTML.

GAIA-2 is Wayve's second-generation driving world model. Its technical report explicitly defines it as a controllable multi-view generative world model, with rich conditioning for scenario generation and evaluation.

GAIA-2 is a controllable multi-view generative world model for driving developed by Wayve in 2025 for autonomous driving.

Editorial Snapshot

Short extractable facts for answer engines and no-JS readers.

SignalValue
DefinitionGAIA-2 is a controllable multi-view generative world model for driving developed by Wayve in 2025 for autonomous driving.
Short DescriptionWayve's controllable multi-view world model for generating driving scenarios from structured conditioning signals.
Benchmark Rows0
FAQ Entries1
Related Models3
Related Guides0
Related Research Topics0
Last Updated2026-07-19

Notable Features

Key capabilities associated with this model.

  • Explicit world-model objective
  • Multi-view generation
  • Fine-grained structured control

Use Cases

Representative applications attached to this model record.

Driving scenario generationAutonomous-vehicle evaluationSafety testing

Strengths and Limitations

Balanced assessment surfaced in static HTML.

Strengths

  • Direct successor to GAIA-1
  • Controllable multi-view design

Limitations

  • Technical report rather than open product
  • Closed weights

References and Citations

Primary references preserved in static HTML for citation extraction.

ReferenceLink
Wayve, 2025. GAIA-2: A Controllable Multi-View World Model.Open source

Related Models

Nearby models linked from the current editorial record.

ModelCategoryWorld Model TypeIndex v1.1
GAIA-1Foundation World ModelGenerative driving world model61/100
Waabi WorldGenerative World ModelGenerative world simulator for autonomous drivingN/A
NVIDIA CosmosFoundation World ModelVideo world foundation model87/100

Frequently Asked Questions

FAQ answers rendered directly into static HTML for extractable responses.

Why is GAIA-2 included?

Wayve's technical report explicitly describes GAIA-2 as a controllable multi-view generative world model.

Quick Answer

Short extractable summary preserved directly in static HTML.

  • GAIA-2 is a controllable multi-view generative world model for driving developed by Wayve in 2025 for autonomous driving.
  • Use this page when you need a fast read on how GAIA-2 fits into the generative world model landscape, then validate the details in the benchmarks, citations, and related pages.
  • A key strength surfaced in the editorial record is direct successor to GAIA-1.

Editorial Trust Signals

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: 2026-07-19.

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 sources onlyLast reviewed date visibleMethodology documentedSource links included

External Sources

Primary model and lab sources embedded in static HTML.

References

  1. [1] Wayve, 2025. GAIA-2: A Controllable Multi-View World Model.