Frozen Flows Forget: Diagnosing and Restoring Lost Motion in a Latent-flow World Model
Read the original on arXiv AI →The paper investigates why latent‑flow world models that use a frozen self‑supervised latent space lose the ability to manipulate motion. It shows that the pretrained flow does not move the manipulated object and that training with latent‑only losses only produces stillness or teleport‑like motion. The authors introduce Decode‑Augmented Rollout Training (DART), which keeps the representation frozen but retrains the flow using decode‑path supervision, restoring temporal motion structure and improving prediction quality, even closing much of the gap to an oracle‑informed reference. The study also notes that pixel error alone can favor frozen predictions.
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.