Yong-Hong He

Complex graph networks are overkill for histology-to-gene inference: factorizing tissue microenvironments into low-rank latent gene programs beats heavy architectures across five cohorts while slashing computational overhead.

Morphology-derived tumor states reveal critical progression information that traditional diagnostic labels overlook, linking spatial histopathology to multi-omics insights.

ConRub-Med achieves unprecedented accuracy in open-ended medical question answering by leveraging scalable, model-generated rubrics that outperform traditional expert-driven methods.