Generated video plans are then grounded to visual-motor control, through an inverse dynamics model that infers actions from generated videos.

Filter pruning has been widely used for neural network compression because of its enabled practical acceleration.

We build such explanations and counterfactuals iteratively using constraint solving techniques and a heuristic based on feature-level sensitivity ranking.

The problem is challenging as it requires not only the reconstruction of visible parts but also the hallucination of invisible regions. Consequently, this problem is often ill-posed and corresponds to multiple plausible solutions because of insufficient evidence from a single image.