深慢Shimmer 深慢Shimmer arXiv:2606.25056v1 Announce Type: new Abstract: Behavioral Foundation Models (BFMs) offer a promising path toward universal physics-based character control by organizing a rich repertoire of physically plausible behaviors into a latent space, guided by a large-scale motion dataset. While these models excel at time-invariant tasks, such as goal-reaching and state-based reward optimization, their latent space does not directly support time-varying objectives, such as tracking a motion sequence. Fo
This research addresses a critical gap in Behavioral Foundation Models by enabling time-varying motion tracking through latent optimization instead of heuristics.