Action Forcing: Training World Models on Unsupervised Video by Recovering Underlying Egomotion Bases

The paper introduces Action Forcing, a method that transforms ordinary unlabeled video into action‑supervised training data by extracting egomotion bases through principal component analysis of pixel displacements. This approach yields grounded throttle–yaw control signals without requiring instrumented platforms or manual annotation, and it trains a high‑capacity video model while preventing pixel‑level overfitting via an online latent critic. The authors also critique standard video generation metrics and propose a reference‑free evaluation that measures controllability, plausibility, conjuring, and geometric integrity, showing that their model can reverse, scale, and compose actions despite limited reverse‑action data.

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.

• diffusion