Can video generation discover physical laws from visual data?
Determine whether video generation models can discover fundamental physical laws solely from visual observations without human priors, i.e., whether observing and learning from videos alone suffices for inferring and applying classical mechanics rules to predict future frames in unseen scenarios.
References
However, it remains an open question whether video generation can discover such rules merely by observing videos, as Sora does.
— How Far is Video Generation from World Model: A Physical Law Perspective
(2411.02385 - Kang et al., 2024) in Section 1 (Introduction)
However, despite their visual realism, whether such generative models reliably capture physical laws and can consequently benefit planning remains unclear (Kang et al., 2024).
— AD-E2E-JEPA: A Joint-Embedding Predictive Architecture For End-to-End Autonomous Driving
(2609.34085 - Zhu et al., 28 Sep 2026) in Section 2.1, World Models