Reproduce “AIDE: Automated Instruction via Distilled Expertise for Reference-Free Motor Skill Coaching” 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
Yoshiki Ito
AIDE trains a teacher on paired learner–expert pose sequences, then uses a learner-only student at inference to generate coaching feedback through privileged information. On basketball, it improves over Learner-Only on all seven metrics, including ROUGE-L of 22.3±1.0 versus 20.7±0.9. It is not uniformly better than reference-required methods; evidence concerns feedback generation on ExpertAF, not improved athletic performance.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.