<ul><li>Researchers introduce Gen-C, a generative model for authoring high-level crowd behaviors in virtual environments.</li><li>Gen-C leverages a large language model to generate crowd scenarios which are expanded and generalized through simulations.</li><li>The method employs Variational Graph Auto-Encoders to learn graph structures and node features, enabling flexible generation of dynamic crowd interactions.</li><li>Gen-C showcases its potential for populating diverse virtual environments with agents exhibiting varied and dynamic behaviors.</li></ul>

Gen-C: Populating Virtual Worlds with Generative Crowds

Discover more