Mingxuan Liu

Achieve verifiable clinical interpretation by grounding radiology reports to 3D CT volumes with a novel graph-guided lesion grounding framework that outperforms existing multimodal foundation models.

Frozen vision-language models can dramatically improve abnormality grounding in rare disease imaging by iteratively refining decisions through optimized instructions and visual perturbations.

PReD leaps ahead by creating the first foundation model to close the loop on perception, recognition, and decision-making for electromagnetic signals.

Achieve state-of-the-art pansharpening of thin-cloud contaminated remote sensing images with a unified model that disentangles frequency components and leverages NIR and PAN bands for robust restoration.

FetalAgents leapfrogs existing fetal ultrasound analysis tools by dynamically orchestrating specialized AI agents, outperforming monolithic models across diverse clinical tasks and delivering structured clinical reports from video streams.