智东西· 杨 京丽·· 22 days agoPicksAI score65
Google releases next-generation world model Genie 4, capable of simulating physical processes such as aerodynamics and collisions.
空气动力学、碰撞都能模拟:谷歌Genie 4来了,把物理写进世界模型!
AI briefing
Google releases next-generation world model Genie 4, which can natively generate music, ambient sound, and interactive dialogue while generating worlds. Compared with the previous generation Genie 3, the new model adds native audio, real-time character dialogue, and multi-step reasoning and scene control capabilities provided by the Gemini model. It is currently being gradually opened to trusted testers in the form of a research preview.
Why it matters
Genie 4 builds on the previous generation by adding native audio, real-time dialogue, and multi-step reasoning, allowing creators to evaluate its interactive simulation capabilities accordingly.
Open original zhidx.com
Google / VeoVideo GenerationMusic & Sound EffectsModel Releases#Model release#Video generation#Music & sound#Google