Skild AI Unveils S1: Robot Model Learning Tasks from One Video Demo
DeryaTR_ · x · 2026-08-26
Skild AI introduced S1, a robot foundation model designed to learn new manipulation tasks via in-context prompting. It can execute 10-minute tasks it has never seen before using just a single video prompt without any fine-tuning. In internal benchmarks, S1 achieved a 66% step-success rate on unseen tasks compared to 9% for a language-prompted model, with one video demonstration providing roughly the benefit of 380 post-training examples.
More from Embodied
- Niantic Spatial's places library ships robot-ready Gaussian splat warehouse scenes for policy training — RexDouglass · 2026-10-16
- Volvo and NVIDIA expand partnership to bring safe automated driving to next-gen cars — nvidia · 2026-10-16
- Tevel's robotic system harvests fruit around the clock using computer vision — LexiLove · 2026-10-16
- SHOES: 10 minutes of real-robot RL lets quadrupeds walk in shoes, CoRL 2026 paper — kscottz · 2026-10-16
- Tesla Cybercab robotaxis logged zero crashes in first two weeks of public rides, NHTSA data shows — elonmusk · 2026-10-16
- Robotics LLMs tested on 16 tasks: GPT-6 Astra hits 17.2% success vs Fable's 9.1% — pabbeel · 2026-10-16