Disentangled Skill Representations for Predictive Human Modeling

The paper introduces Skill Abstraction with Interpretable Latents (SAIL), a method that models human skill as a persistent, multi‑dimensional construct inferred from naturalistic behavior over time. SAIL produces a robust skill embedding that blends expert and novice bases, learns transferable subskills through counterfactual subskill swaps, and supports skill‑informed behavior prediction across various in‑domain contexts. Experiments on racing and baseball demonstrate that SAIL achieves strong predictive performance, improves behaviorally grounded disentanglement compared to baselines, and enhances downstream AI coaching outcomes.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• rag
• safety