WHAM: World and Human Action Models 

World and Human Action Models, or WHAM for short, are a family of generative AI models that capture both the environment (“world”) and human actions to produce interactive, coherent sequences of visuals and controller actions. Developed as part of the Muse research program, WHAM presents a new design material, unlocking new forms of creative expression and ushering in the future of interactive media. 

The family currently includes two models: 

• WHAM — our first World and Human Action Model, published in Nature (2025). 

• WHAM-RT — our real-time World and Human Action Model, playable now in Copilot Labs. 

The project is a close collaboration between the People-Centric AI group at Microsoft Research and Xbox Game Studios’ Ninja Theory.