Semigroup-JEPA: Latent Dynamics Consistency for Zero-Shot Physics Generalization
[Uczenie maszynowe] Autorzy: Andy Zeyi Liu, Haoran Sun, Lucas Baker i 2 więcej
Joint-Embedding Predictive Architecture (JEPA) world models learn a compact latent representation of the world that supports prediction and planning, but their capability to learn physics and generate physically realistic dynamics remains hitherto untested. In this work, we introduce SemiGroup-JEPA (SG-JEPA), which extends the LeWorldModel framework by supplying the parameter governing the physics to the temporal model via action-conditioning and jointly training an encoder and predictor through an autoregressive latent rollout. To evaluate the model's ability to generalize out of distribution, we design dynamical tasks under different gravitational fields that, despite obeying the same physical law, exhibit qualitatively different dynamics, ranging from floating motion in weak gravitational fields to rapid bouncing in strong ones. In contrast to DINO-WM, SG-JEPA reduces open-loop predi…
- Kategoria arxiv
- cs.LG
- Kategoria
- Uczenie maszynowe