ActionParty: Multi-Subject Action Binding in Generative Video Games

ArXi:2604.02330v1 Announce Type: cross Recent advances in video diffusion have enabled the development of "world models" capable of simulating interactive environments. However, these models are largely restricted to single-agent settings, failing to control multiple agents simultaneously in a scene. In this work, we tackle a fundamental issue of action binding in existing video diffusion models, which struggle to associate specific actions with their corresponding subjects.