Explainable Artificial Intelligence (XAI)

AI summary · may contain errors

EVLF-FM, a multimodal vision-language foundation model for medicine, achieves highest internal disease-diagnostic average accuracy of 0.895 across 18 global datasets spanning 10 imaging modalities.

AI summary · may contain errors

In central Taiwan, explainable machine learning linked PM 2.5 oxidative potential to nonlinear interactions among transition metals, water-soluble organic carbon, and aerosol liquid water, enabling source-specific mitigation leverage estimates.

AI summary · may contain errors

Agentic AI systems like Co-Scientist, Robin, and Biomni can generate hypotheses, design experiments, run computational analyses, and refine reasoning using experimental feedback.

AI summary · may contain errors

In TCGA RNA-seq tumour samples, GO-constrained biologically-informed neural networks add little to reconstruction or latent-space organization, with performance often matched by randomized or unconstrained models.

AI summary · may contain errors

StratCP is a stratified conformal prediction method that controls false discovery rate for selected patients and achieves target coverage for deferred prediction sets across medical foundation model tasks.