OneWorld: Learning Consistent Physics Across Actions in World Models

OneWorld introduces a shared‑mechanism counterfactual generation framework that jointly models multiple action‑conditioned futures using a common latent physical mechanism. By inferring distributions over latent mechanisms for each action‑outcome branch and aggregating them into shared‑world evidence, the model enforces consistency across interventions while preserving distinct action outcomes. Experiments in controlled environments demonstrate that OneWorld improves cross‑intervention physical consistency without sacrificing single‑rollout prediction quality.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.