Generalist reports up to 10–20× gains in GEN-1 actuator adaptation
Generalist disclosed a GEN-1 learning improvement for adapting to unfamiliar actuators and robot hardware, reporting gains of up to 10–20× on internal benchmarks and stronger performance on precision manipulation.
Evidence notes
- The update targets low-level adaptation to new actuators and robot embodiments rather than a new GEN-1 model release.
- Generalist reports gains of up to 10–20 times on internal benchmarks, without publishing the benchmark protocol or absolute scores.
- The company showed the improvement on high-precision disassembly of parts from a NIST board.
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.