Robotics in-context learning: long tasks via one video
deepakpathak · x · 2026-08-27
Deepak Pathak shared a breakthrough in robotics "in-context learning":
- Long-horizon: Handles tasks over 10 minutes long.
- Zero-shot: Task types unseen during pre-training.
- One-shot prompt: Learns from a single demo video without fine-tuning.
This is seen as an emergent capability that could unlock many applications, emphasizing building intelligence from the ground up.
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