AI RESEARCH
Let There Be Light: Reflection, Refraction and Scattering for Neural Operators
arXiv CS.LG
•
ArXi:2606.03262v1 Announce Type: new Neural operators learn mappings between infinite-dimensional function spaces and provide a data-driven surrogate modeling paradigm for parametric partial differential equations (PDEs). Existing architectures typically obtain expressivity by parameterizing integral kernels in prescribed transform domains or by applying attention-like interactions over discretized spatial points.