Hu et al.: GAIA-1 action-conditioned driving video world model

What changed

Trained a token-sequence generative model conditioned on video, text and driving actions to synthesize controllable future driving scenarios.

Scientific scope

Trained a token-sequence generative model conditioned on video, text and driving actions to synthesize controllable future driving scenarios. Generated visual plausibility is not proof of calibrated traffic prediction, causal correctness or improved road safety. This record covers the original model and technical report, not later deployments or GAIA variants.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Generated visual plausibility is not proof of calibrated traffic prediction, causal correctness or improved road safety. This record covers the original model and technical report, not later deployments or GAIA variants.

Contributors

• Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.

• GAIA-1: A Generative World Model for Autonomous Driving
• Hu et al.: GAIA-1 action-conditioned driving video world model — author/company project record

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction