Skild AI unveils S1: Robot model learns tasks from one video demo
deepakpathak · x · 2026-08-27
Skild AI released S1, a foundation model for robots enabling in-context learning. A robot can watch a single video demo and attempt the task in real-time without fine-tuning.
Key Capabilities:
- Learns long-horizon tasks (>10 mins) like making coffee or flipping pancakes, absent from pretraining data.
- Handles perturbations, recovers from mistakes, and improvises beyond the demo.
This approach acts as "prompting for robotics," significantly lowering the data barrier for robot training.
More from Embodied
- Viral meme nails AI's irony: it can write symphonies but can't do the dishes — briannekimmel · 2026-10-16
- WEDGE turns navigation agents' own failures into targeted training worlds — mohitban47 · 2026-10-16
- Knödel Watch: animated vocabulary cards on ESP32-S3, open-sourced 4 days after unboxing — alexcovo_eth · 2026-10-16
- NVIDIA RTX Spark PC launches tomorrow with global events and strong early reviews — NVIDIA Blog · 2026-10-16
- SlipSense fuses pressure and vibration for 23ms zero-shot robotic slip detection — micoolcho · 2026-10-16
- Stanford's Fei-Fei Li team open-sources OpenWAM, a unified world-action model framework for robots — jiqizhixin · 2026-10-16