DeepMind releases Gemini Robotics 2.5 and ASIMOV-jailbreak
Get up to speed
DeepMind has released Gemini Robotics 2.5, an enhanced visual-language-action (VLA) model that can improve the breadth and speed of robot learning skills, enabling robots to assist humans in completing more tasks in more realistic environments.
From Google DeepMind
Developments
2 developments
- Nov 11 01:11 · 1 reportsGoogle DeepMind 发布 Gemini Robotics 2.5,在梅赛德斯-奔驰生产线试点中金属部件排序成The Decoder:Google DeepMind Releases Gemini Robotics 2.5, Achieving 96% Success Rate in Metal Part Sorting on Mercedes-Benz Production Line
- Nov 10 03:51 · 2 reportsDeepMind 发布 Gemini Robotics 2.5 和开源安全基准 ASIMOV-jailbreakGoogle DeepMind:DeepMind Releases Gemini Robotics 2.5, Accelerating Real-World General Dexterity
Report timeline
Follow the reporting to see the story from different angles.
- The DecoderFeaturedGoogle DeepMind Releases Gemini Robotics 2.5, Achieving 96% Success Rate in Metal Part Sorting on Mercedes-Benz Production Line
Google DeepMind has launched a new robotic control AI model, Gemini Robotics 2.5, which has been piloted on the Mercedes-Benz production line and achieved a 96% success rate in sorting metal parts. The model is based on the Visual-Language-Action (VLA) model, capable of processing visual information, understanding language instructions, and converting them into robotic actions. Compared to previous versions, Gemini Robotics 2.5 has significantly improved in task success rate and speed.
- Ars Technica · AIFeaturedDeepMind Releases Gemini Robotics 2.5 and Open Source Security Benchmark ASIMOV-jailbreak
DeepMind has released the next-generation AI-driven Gemini Robotics platform, where the robot AI in version 2.5 is nearly at human level in completing real tasks, with some robots already working in Mercedes-Benz factories. DeepMind has also launched the open-source security benchmark ASIMOV-jailbreak.
- Google DeepMindFeaturedDeepMind Releases Gemini Robotics 2.5, Accelerating Real-World General Dexterity
DeepMind has released Gemini Robotics 2.5, an enhanced visual-language-action (VLA) model that can improve the breadth and speed of robot learning skills, enabling robots to assist humans in completing more tasks in more realistic environments.