Two new preprints released on arXiv!

We are excited to share two new preprints released on arXiv:

STORM: A Multimodal Foundation Model of Spatial Transcriptomics and Histology for Biological Discovery and Clinical Prediction

STORM bridges spatial transcriptomics and histology imaging, trained on ~1.2 million transcriptomic profiles across 18 organs. Tested across 23 independent patient cohorts, it achieves improved predictions for immunotherapy response and clinical outcomes.

Read on arXiv


MUPAD: A Generative Foundation Model for Multimodal Histopathology

MUPAD is a generative foundation model trained on 100 million histology image patches, 1.6 million text-histology pairs, and 10.8 million RNA-histology pairs spanning 34 human organs. It enables cross-modal translation and substantially outperforms specialized alternatives.

Read on arXiv

Jinxi Xiang
Jinxi Xiang
Postdoctoral Fellow in Medical AI

My research interests include computer vision and medical image analysis.