最新报道:According to Bijie.com, Google DeepMind has announced the release of Genie 3, a general-purpose world model. This model generates diverse, interactive virtual environments in real time based on text prompts, supports dynamic world navigation at 24 frames per second and 720p resolution, and maintains environmental consistency for minutes. Genie 3 excels not only in modeling physical properties and reconstructing geographical and historical scenes, but also in the 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 somatosensory agents. Currently, the model is available in a limited research preview to selected scholars and creators, with the goal of expanding to a wider audience in the future.