Search papers, labs, and topics across Lattice.
Hangzhou Dianzi University
2
0
4
SCALPEL redefines medical vision-language representation by eliminating hallucinations and enhancing context understanding, achieving state-of-the-art results across multiple benchmarks.
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.
