{"id":1172025,"date":"2026-05-26T08:27:21","date_gmt":"2026-05-26T15:27:21","guid":{"rendered":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/?post_type=msr-project&p=1172025"},"modified":"2026-05-26T08:47:09","modified_gmt":"2026-05-26T15:47:09","slug":"wham","status":"publish","type":"msr-project","link":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/project\/wham\/","title":{"rendered":"WHAM"},"content":{"rendered":"
\n\t
\n\t\t
\n\t\t\t\"a\t\t<\/div>\n\t\t\n\t\t
\n\t\t\t\n\t\t\t
\n\t\t\t\t\n\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\n\n

WHAM: World and Human Action Models <\/h1>\n\n\n\n

Unlocking new forms of creative expression and ushering in the future of interactive media <\/p>\n\n\n\n

\n
Play WHAM-RT in Copilot Labs<\/a><\/div>\n\n\n\n
Read the Nature publication<\/a><\/div>\n<\/div>\n\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t<\/div>\n\t\t<\/div>\n\t<\/div>\n<\/section>\n\n\n\n\n\n

World and Human Action Models, or WHAM for short, are a family of generative AI models that capture both the environment (\u201cworld\u201d) 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. <\/p>\n\n\n\n

The family currently includes two models: <\/p>\n\n\n\n