AI RESEARCH
HamVision: Hamiltonian Dynamics as Inductive Bias for Medical Image Analysis
arXiv CS.LG
•
ArXi:2603.21377v1 Announce Type: cross We present HamVision, a framework for medical image analysis that uses the damped harmonic oscillator, a fundamental building block of signal processing, as a structured inductive bias for both segmentation and classification tasks. The oscillator's phase-space decomposition yields three functionally distinct representations: position~$q$ (feature content), momentum~$p$ (spatial gradients that encode boundary and texture information), and energy $H = \tfrac{1}{2}|z|^2$ (a parameter-free saliency map.