Inference-time Physics Alignment of Video Generative Models with Latent World Models

Understand

State-of-the-art video generative models produce promising visual content yet often violate basic physics principles, limiting their utility.

• While some attribute this deficiency to insufficient physics understanding from pre-training, we find that the shortfall in physics plausibility also stems from suboptimal inference strategies.
• We therefore introduce WMReward and treat improving physics plausibility of video generation as an inference-time alignment problem.
• In particular, we leverage the strong physics prior of a latent world model (here, VJEPA-2) as a reward to search and steer multiple candidate denoising trajectories, enabling scaling test-time compute for better generation performance.