arXiv cs.CV: handwriting/OCR
FlowCPO: A Unified Divergence View of Preference Alignment for Flow Models
FlowCPO: 플로우 모델의 선호 정렬에 대한 통합 발산 관점
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.