谷歌Deepmind的Genie 4为交互式世界模型带来实时音频和对话
谷歌Deepmind推出Genie 4，一种实时生成背景音频和角色对话的交互式世界模型，由Gemini模型驱动。这影响了人工智能的研究和开发。
google deepmind has introduced genie 4, an interactive world model that calculates environments frame by frame in real time and, for the first time, directly generates matching background audio and character dialogue. genie 4 is powered by gemini models that plan multistep tasks and continuously adapt the simulated world to user text prompts and changing conditions. the model is still experimental and has limitations in longer sessions and complex physics, but it has potential applications in robotics and training environments. genie 4 is currently available to select testers and will later expand to google ai ultra subscribers. this development signals progress in ai research and potential advancements in hybrid world models.