Reading or Guessing? Visual Grounding Failures of Vision-Language Models for OCR in Ancient Greek Editions 文章

ArXiv CS.CV2026-05-28NEWSen作者: Antonia Karamolegkou, Nicolas Angleraud, Beno\^it Sagot, Thibault Cl\'erice
查看原文 →
关系图谱

Reading or Guessing? Visual Grounding Failures of Vision-Language Models for OCR in Ancient Greek Editions · 相关技术

相关技术

Optical Character Recognition (OCR)Vision-Language Models