Muse, the first world and human action model, could facilitate interdisciplinary collaboration, for example when exploring gameplay ideas.
Today released Microsoft MUSE, a first-in-the-in-stroke generative AI model that we are applying for games. But that’s so much more than that. What we share today is a big step forward for gameplay idation. And what is even more exciting is what this breakthrough represents in our journey with the building and use of generative AI, and which industries, developers and creators of all interests will be able to do next.
The impressive abilities we first witnessed with chatgpt and GPT-4 to learn human language are now matched by AI’s ability to learn the mechanics of how things work actually develop a practical understanding of interactions in the world. As a computer scientist, this ability to understand and model a 3D world is something that I and many other good researchers have been pursuing for over 10 years, and personally I was not sure that it could be made possible with such speed and quality.
In the case of muse, just from observing human gameplay, this model develops a deep understanding of the environment, including its dynamics, and how it develops over time in response to actions. This locks the opportunity to quickly iterate, remix and cabinets in video games so that developers can eventually create immersive environments and free up their full creativity.
In addition to games, I am excited about the potential of this capacity to enable AI assistants who understand and help visualize things, from configuring the kitchen in your home to redesign a retail space to build a digital twin of a factory floor to test and explore different scenarios. All of these things are now becoming possible with AI. Seen from computer science research, it’s pretty amazing and the future uses of this are probably transformative to creators.
–
At Microsoft we have a long history of collaboration between research and engineering. Today, when we release Muse, we also advertise Azure AI Foundry Labs, where the AI ​​community can explore the latest from Microsoft Research. Azure AI Foundry Labs will help speed up the transition from research to solutions, bringing new ideas to the wider community to help shape AI’s future. Learn more.