SmartApe AI
Nov 3, 2026 · Artificial Intelligence
SimpleICL: Robots Learn New Tasks from One Demo Video Without Retraining
Researchers from Chinese Academy of Sciences and Alibaba propose SimpleICL, a robot in-context learning framework enabling zero-shot generalization to unseen manipulation tasks by watching a single human demonstration video, using semantic discriminative data and cross-group pairing to resolve prompt ambiguity, achieving 66% success in simulation and up to 81% on real robots.
Cross-group PairingEmbodied AIHuman Demonstration
0 likes · 10 min read
