Reproduce “Instant-Fold: In-Context Imitation Learning for Deformable Object Manipulation” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yilong Wang, Cheng Qian, Edward Johns
Instant-Fold guides a robot through a demonstrated clothes-folding procedure on held-out folds. It learns visual features that track cloth through deformation and conditions a closed-loop dual-arm policy on demonstration keyframes and the current scene. The fully pretrained policy achieved 58.3 ± 5.0% C-SR@95 and 95.8 ± 2.0% context-following accuracy; evaluation covers garment tops and one quantitatively tested real-world fold mode.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.