Dandan Zhu

Current image quality metrics struggle to articulate *why* one high-quality image is better than another, but this challenge shows MLLMs are closing the gap by providing expert-level explanations.

A new dataset, SeIQA, offers a benchmark to evaluate how humans perceive semantic loss in degraded images, pushing beyond traditional quality metrics.

Achieve state-of-the-art medical lesion segmentation across diverse modalities and lesion types with a single, unified model that outperforms specialized approaches.