Depth Beats Breadth: Scaling Wearable World Models of Human Physiology

Anonymous (ICLR 2027 double-blind submission)

Summary

Action-conditioned wearable world model forecasting physiological trajectories from personal history and specified future behaviour. Corpus: 5.4M users, ~2B user-days. Scaling study over population size, training context, model capacity and inference context: longer personal histories beat more users, much of it from longer inference context; larger models benefit more from long context.