# Skild AI's S1 Learns Robot Tasks From One Video Without Weight Updates

The model reports 66 percent success on unseen tasks against 9 percent for an equivalent language-prompted policy, on jobs running up to ten minutes.

- Published: 2026-09-11T06:22:22.078Z
- Canonical: https://polylog.news/ai/2026-09-11/skild-ai-s-s1-learns-robot-tasks-from-one-video-without-weig
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [NVIDIA Blog](https://blogs.nvidia.com/blog/skild-ai-s1-physical-ai/), [Skild AI](https://skild.ai/blogs/s1), [The Robot Report](https://www.therobotreport.com/skild-ai-unveils-s1-flagship-robot-foundation-model/)

Skild AI's S1 robot foundation model takes a single human video of a task and executes it, without task-specific post-training and without updating weights. That is in-context learning applied to physical action, and it changes the unit of…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-09-11/skild-ai-s-s1-learns-robot-tasks-from-one-video-without-weig (subscription information: https://polylog.news/pricing).