Search papers, labs, and topics across Lattice.
Department of Biomedical Informatics and Data Science , Yale School of Medicine , New Haven , US, Affiliation:
5
0
5
Fusing volumetric and surface brain MRI data in a self-supervised autoencoder uncovers substantially more heritable genetic loci than unimodal approaches.
Clinical MLLMs can be significantly improved by optimizing for AUROC via pairwise instance rankings, reversing accuracy-based prompt evolution's performance degradation.
A single model can now achieve state-of-the-art performance in both word and sentence alignment across multiple languages, simplifying the alignment process significantly.
HA-DLC reveals that effectively modeling intra-tumoural heterogeneity can dramatically improve tumour classification accuracy from multiparametric MRI.
