arXiv cs.CV: handwriting/OCR
Found but Not Read: When Extracted Text Closes the Retrieval-Reading Gap in Document Vision-Language Models
발견은 했지만 읽지는 않은 것: 추출된 텍스트가 문서 시각-언어 모델에서 검색-독해 격차를 해소할 때
No write-up yet — this entry is still just the auto-fetched hook. Aaron's own summary (200–500 words) will replace this note once he's written it.