LeituraPesquisaRadarFramework de investimento
Entrar / Cadastrar
← Voltar para a leitura
NotíciasTópico · 谷歌Genie 4模型Estrutural2 min de leituraEditorial DisconfirmAI

Google DeepMind Announces Genie 4: A New Generation of Natively Multimodal World Simulation

Google DeepMind has unveiled Genie 4, a new world model enabling real-time interactive simulation with native audio and dialogue generation, currently in research preview.

2026-10-28 00:13 GMT+8

On October 27, 2026, Google DeepMind officially announced the launch of Genie 4, its new generation world model designed to unlock unprecedented realism and improve real-time interactive simulation. Unlike previous models focused primarily on visual generation, Genie 4 is natively multimodal, capable of simultaneously generating audio-like music, ambient noises, and interactive dialogue that match the simulated world.

The Genie 4 model builds on capabilities from the Gemini family. Specifically, Gemini Omni anchors the simulations in real-world appearance and behavior, while other Gemini models provide the complex reasoning needed to maintain the simulation's coherence and continuity. Users can set an event in motion, and Genie 4 simulates what happens next: how the world responds, how it sounds, and how the people in it move, react, and speak.

Google DeepMind stated that understanding and simulating the world is a crucial aspect of building AGI. Genie 4 advances the ability to create safe, infinitely variable simulations that can help with everything from developing training environments for robots and agents to unlocking the creation of new interactive experiences. The model introduces a new standard of realism in physics and human action, simulating scenarios like aerodynamics and collisions, and creating characters that move naturally, respond organically to their environments, and can be interactively steered in real-time.

Currently, Genie 4 is being rolled out as a research preview for trusted testers to gather feedback before a wider release to consumers and developers. Early access is starting with Google AI Ultra subscribers in Project Genie and early access partners of the Gemini API and Google AI Studio.

Entrar / Cadastrar
LeituraPesquisaRadarFramework de investimento

Fontes

  • deepmind.googleGoogle DeepMind↗
Tópico

谷歌Genie 4模型

美国谷歌公司旗下DeepMind部门于2026年10月27日正式发布新一代世界模型Genie 4。该模型实现了原生多模态生成,支持在实时交互模拟中同步生成音频(包括环境音、音乐和对话),并将单次模拟时长从上一代Genie 3的一分钟延长至两…

3 etapas3 peçasAtualizado 2026-10-28 13:10

Como chegamos aqui

  1. 2025-08-01谷歌发布前代模型Genie 3的研究预览版,当时模拟时长限制为60秒。techcrunch.com ↗
  2. 2026-08-01AI视频初创公司Runway发布其第二代世界模型GWM Worlds 2,具备动态响应和音频生成功能,加剧了世界模型领域的竞争。techcrunch.com ↗
  3. 2026-10-27谷歌DeepMind正式宣布推出Genie 4,支持原生音频生成、实时自然语言交互及两分钟模拟时长,面向受信任测试者开放。deepmind.google ↗

O que ainda está indefinido

  • Genie 4何时正式向公众全面开放,而非仅限于AI Ultra订阅者和API合作伙伴?
  • 谷歌如何解决长时间模拟中的物体持久性漂移和音频准确性问题?
  • 在世界模型领域并购潮(如AMD收购World Labs)背景下,Genie 4的商业化路径将如何调整?

Também nesta thread

  • Google DeepMind Launches Genie 4 World Model with Native Audio and Real-Time Steering2026-10-28
  • Google Announces Genie 4 World Model: Adds Audio, Real-Time Prompt Updates, Doubles Simulation Length to Two Minutes2026-10-28
Ler o tópico completo →
Continuar pesquisando →