Learning to Generate Rigid Body Interactions with Video Diffusion Models

ArXi:2510.02284v3 Announce Type: replace-cross Recent video generation models have achieved remarkable progress and are now deployed in film, social media production, and advertising. Beyond their creative potential, such models also hold promise as world simulators for robotics and embodied decision making. Despite strong advances, current approaches still struggle to generate physically plausible object interactions and lack object-level control mechanisms. To address these limitations, we.