Skild AI: S1 step-change over VLAs, exponential on novel tasks
Compared to conventional VLAs, S1 is a step-change improvement.
For known tasks, S1 can match the performance of language-prompted VLAs.
For novel tasks, S1 exponentially outperforms any existing language-prompted VLAs as pre-training scales.
Skild AI believes this is a promising direction towards establishing scaling laws for robotics.
▶
✓ Verified
2026-08-25