Google DeepMind releases Genie 3 interactive world model

According to the DeepMind blog, Google DeepMind announced today the launch of the universal world model Genie 3. This model can generate diverse interactive virtual environments in real-time based on text prompts, support dynamic world navigation at 24 frames per second at 720p resolution, and maintain environmental consistency for several minutes. Genie 3 not only excels in physical attribute modeling, geographic and historical scene restoration, but also achieves controllable generation of complex world events. As a key step towards general artificial intelligence (AGI), Genie 3 provides a broader simulation space for the training and evaluation of AI somatosensory agents. At present, the model is open to some scholars and creators in the form of limited research preview, and is expected to be expanded to more testers in the future.