Frozen Flows Forget: Diagnosing and Restoring Lost Motion in a Latent-flow World Model
[Widzenie komputerowe] Autorzy: Xiwen Chen, Rigaudiere Z. Li, Zhiruo Zhou i 2 więcej
Latent world models that integrate a flow in a frozen self supervised latent space train stably and cheaply, yet silently lose the property manipulation depends on most: motion. The pretrained flow never moves the manipulated object; retraining it with latent-only losses only trades stillness for teleport-like motion. We trace the failure to the training signal, not the representation: anchor-sparse, latent-only supervision never says where along the horizon change belongs. Decode-augmented rollout training (DART) repairs this while keeping the representation frozen, retraining only the flow with decode-path supervision. DART outperforms its latent only parent on the full protocol, restores the temporal structure of motion, and re-couples predicted motion to the scene; at larger scale it further improves prediction quality, closing nearly half the remaining gap to an oracle-informed int…
- Kategoria arxiv
- cs.CV
- Kategoria
- Widzenie komputerowe