According to a report from BiJie Network, Google DeepMind has announced the release of Genie 3, a universal world model. This model generates diverse interactive virtual environments in real-time based on text prompts, supporting dynamic world navigation at 24 frames per second and 720p resolution, while maintaining environmental consistency for several minutes. Genie 3 is not only skilled in modeling physical properties and reconstructing geographical and historical scenes, but it can also perform controllable generation of complex world events. As a key step toward Artificial General Intelligence (AGI), Genie 3 provides a broader simulation space for the training and evaluation of AI sensory agents. Currently, the model is available in a limited research preview version to selected scholars and creators, with the aim of expanding to more testers in the future.

AGI3.1%
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
0/400
No comments
Trade Crypto Anywhere Anytime
qrCode
Scan to download Gate app
Community
English
  • 简体中文
  • English
  • Tiếng Việt
  • 繁體中文
  • Español
  • Русский
  • Français (Afrique)
  • Português (Portugal)
  • Bahasa Indonesia
  • 日本語
  • بالعربية
  • Українська
  • Português (Brasil)