SOURCE-LINKED INTELLIGENCE

Off-Manifold Refinement: Guiding Video Generators with a Frozen World Model

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

Modern video generators routinely fail at physical dynamics: objects float, trajectories violate gravity, contacts vanish. Standard denoising and flow-matching objectives fit visual data distributions but do not explicitly penalize such physical violations. Existing remedies can improve physical consistency, but typically add substantial inference or training cost. Candidate-selection methods generate and score multiple videos, while gradient-based world-model guidance repeatedly decodes and re-encodes intermediate estimates. Generator-internal refinement adds perturbation and re-denoising loo

Read original source ↗ Open in workspace

recordType

paper

region

Global