VLA models
GAIA-2
United Kingdom
Europe's flagship driving world model: generates controllable, spatiotemporally consistent multi-camera video, including rare and safety-critical scenarios for training and validating Wayve's driving AI. Succeeded in December 2025 by GAIA-3 (15B parameters, double GAIA-2's size), offered for AV validation.
OrganizationWayve
CountryGB
Release2025-03
Open weightsno
Architecturelatent-diffusion multi-camera generative world model conditioned on ego-vehicle dynamics, agent configurations, environmental factors and road semantics
Modalitiesvision, action
Embodimentsautonomous-vehicle
Training dataReal-world driving data from geographically diverse environments (UK, US, Germany)
Sources : Wayve (2025-03-26)arXiv (2025-03-26)ADAS & Autonomous Vehicle International (2025-12-03)
← Back to comparator · VLA models