Med-Banana: Learning Quality-Controlled Medical Image Editing from Success-and-Failure Trajectories

ArXi:2511.00801v4 Announce Type: replace Text-guided medical image editing must satisfy the requested pathology while preserving anatomy, modality-specific appearance, and clinical plausibility. However, existing datasets largely supervise editors with final accepted edits and discard the failed attempts produced during generation. We argue that these failures provide essential supervision for quality control: they specify what should be rejected, why an edit is medically or visually invalid, and how the instruction should be revised.