SOURCE-LINKED INTELLIGENCE

TailProp: content-adaptive light- and heavy-tailed propagation for vision

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Science-inspired vision models show that explicit propagation dynamics can provide structured and interpretable alternatives to conventional token mixing. Existing formulations, however, typically construct and adapt visual propagation within a particular dynamical family, while visual representations can require substantially different spatial interactions across samples, channels, and network stages. We explore cross-regime adaptive propagation and introduce TailProp, a hierarchical vision backbone built upon the Tail Propagation Operator (TPO). TPO uses Gaussian and Cauchy stable-process pr

Read original source ↗ Open in workspace

recordType

paper

region

Global