AI RESEARCH
CRAFT: Clinical Reward-Aligned Finetuning for Medical Image Synthesis
arXiv CS.CV
•
ArXi:2605.12650v1 Announce Type: new Foundation diffusion models can generate photorealistic natural images, but adapting them to medical imaging remains challenging. In medical adaptation, limited labeled data can exacerbate hallucination-like and clinically implausible synthesis, while existing metrics such as FID or Inception Score do not quantify per-image alignment with pathology-relevant criteria. We