arXiv cs.CV: handwriting/OCR
Learning to Look Again: Loss-Gap Supervision for Free-form Crop Routing in Vision-Language Models
다시 보는 법 배우기: 비전-언어 모델에서 자유형 크롭 라우팅을 위한 손실-갭 감독
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.