This defense addresses generalization under distribution shift with limited data. It introduces (1) diffusion-based inverse task inference that recovers a task embedding from a few demonstrations, enabling compositional generation without fine-tuning; and (2) bilinear transduction that converts out-of-support inputs into out-of-combination problems, yielding zero-shot extrapolation in robotics and property prediction.

This research develops an objective, data-driven approach to return-to-sport decisions after pediatric knee surgery. Using motion capture and advanced data analysis, it identifies hidden movement patterns linked to re-injury risk. The goal is to improve clinical decision-making, reduce repeat injuries, and make injury prevention more accessible beyond specialist clinics.