AI RESEARCH

RHYME-XT: A Neural Operator for Spatiotemporal Control Systems

arXiv CS.LG

ArXi:2603.17867v1 Announce Type: new We propose RHYME-XT, an operator-learning framework for surrogate modeling of spatiotemporal control systems governed by input-affine nonlinear partial integro-differential equations (PIDEs) with localized rhythmic behavior. RHYME-XT uses a Galerkin projection to approximate the infinite-dimensional PIDE on a learned finite-dimensional subspace with spatial basis functions parameterized by a neural network. This yields a projected system of ODEs driven by projected inputs.