Google DeepMind发布Genie 4实时世界模型,原生支持音频
> Genie 4 is Google DeepMind’s first real-time world model with native audio, ge…
Genie 4是首个原生支持音频的实时世界模型,结合Gemini实现动态场景编辑与人机互动,代表了视频生成与物理模拟的重要范式突破,值得开发者关注。
> Genie 4 is Google DeepMind’s first real-time world model with native audio, generating ambient sound, music and live dialogue from characters who react to users and in-world events.
> Genie 4 是 Google DeepMind 首个原生支持音频的实时世界模型,能够根据对用户和虚拟世界中事件做出反应的角色,生成环境音、音乐和实时对话。
> Users can rewrite a running simulation by typing, changing weather, moving the camera or adding people, while Gemini fits each edit to the scene and keeps it coherent.
> 用户可以通过打字、改变天气、移动摄像机或添加人物来重写正在运行的模拟场景,而 Gemini 会适配每次编辑以符合场景并保持连贯性。
> Gemini 3.8 Flash acts as an in-loop director, splitting goals into steps and checking incoming frames, and Gemini 4 Argon used that loop to simulate Apptronik’s Apollo humanoid playing checkers.
> Gemini 3.8 Flash 充当循环内的导演角色,将目标分解为步骤并检查传入的帧,而 Gemini 4 Argon 利用该循环模拟了 Apptronik 的 Apollo 人形机器人玩跳棋的过程。
> access starts with trusted testers before Google AI Ultra subscribers and early Gemini API partners. https://x.com/sundarpichai/status/2115115252690145519/video/1
> 访问权限首先向受信任的测试人员开放,随后才是 Google AI Ultra 订阅者和早期 Gemini API 合作伙伴。https://x.com/sundarpichai/status/2115115252690145519/video/1
更进一步:量化金融体系
看懂新闻只是起点——沿量化金融路径,把它变成能交付的工程能力