SIMA 2 Uses Gemini and Self-Improvement to Generalize Across Unseen 3D and Photorealistic Worlds

Wait 5 sec.

Google DeepMind researchers introduced SIMA 2 (Scalable Instructable Multiworld Agent), a generalist agent built on the Gemini foundation model that can understand and act across multiple 3D virtual game environments. The SIMA 2 architecture uses a Gemini Flash-Lite model trained on a mixture of gameplay and Gemini pretraining data. By Vinod Goje