Generalist AI releases GEN-1, a general-purpose robotics AI model achieving 99% success rates on physical tasks
Generalist published its GEN-1 technical release, reporting high-reliability, faster physical-task execution and recovery behaviour from a real-time multimodal robotics model.
Evidence notes
- Generalist introduced GEN-1 as its latest milestone in scaling robot learning and positioned it as a general-purpose AI model for simple physical tasks.
- The company said GEN-1 reached 99 percent success rates on the showcased tasks, ran roughly 3 times faster, and adapted in real time to unexpected scenarios.
- Generalist also said the displayed results used only about one hour of robot data, presenting GEN-1 as a step down in task-specific data requirements.
Company context
Generalist builds embodied foundation models for robots, initially focused on dexterous manipulation. Its work combines real-world robot interaction data, in-house data-collection hardware and models intended to generalize across tasks.