SOURCE-LINKED INTELLIGENCE

Kernel Reboot: Breaking the Boundaries of Neural Tangent Kernels for Neural Fields

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

Neural fields (NFs) map continuous coordinates to signals such as color or density, but fast high-quality reconstruction from sparse observations remains difficult. Classical Neural Tangent Kernel (NTK) regression gives closed-form fits, yet it is fundamentally linear and cannot accumulate reusable task priors. We develop three algorithms that address these gaps. NTK-KIP learns a distilled support set of coordinates (and optional labels) so that a finite NTK can inpaint large missing regions from little observed data, yielding a compact non-linear representation instead of a raw kernel solve.

Read original source ↗ Open in workspace

recordType

paper

region

Global