AI RESEARCH
General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal Decoupling
arXiv CS.CV
•
ArXi:2606.00110v1 Announce Type: new Achieving robust generalization from limited data is a central challenge in embodied intelligence. Prevailing methods fail by regressing absolute coordinates, which violates the principle of general covariance. Fundamentally, this conflates the intrinsic task geometry with rigid execution patterns, binding policies to specific motion styles and fixed speeds. To resolve this, we propose the Generalized Action Manifold (GAM) framework that enforces general covariance through structural disentanglement.