Zero-Shot Synthetic-to-Real Handwritten Text Recognition via Task Analogies

ArXi:2604.09713v1 Announce Type: new Handwritten Text Recognition (HTR) models trained on synthetic handwriting often struggle to generalize to real text, and existing adaptation methods still require real samples from the target domain. In this work, we tackle the fully zero-shot synthetic-to-real generalization setting, where no real data from the target language is available. Our approach learns how model parameters change when moving from synthetic to real handwriting in one or source languages and transfers this learned correction to new target languages.