Google DeepMind Unveils Gemini Robotics 2.5 Vision-Language-Action Model

Written by

in

Google DeepMind has introduced Gemini Robotics 2.5, its most capable vision-language-action model to date. It achieves success rates 30% to 100% higher than previous baselines across 200 different tasks and completes tasks 20% to 30% faster.

Source:Google DeepMind 研究博客 · Read Original

Comments

Leave a Reply

Your email address will not be published. Required fields are marked *