Microsoft-Backed Pathology Foundation Model PRISM2 Published in Nature
anshulkundaje · x · 2026-08-05
PRISM2, a multimodal slide-level pathology foundation model developed by Tempus AI in collaboration with Microsoft researchers, has been published in Nature.
By combining large vision models built from pathology images with large language models, PRISM2 achieves best-in-class performance across various diagnostic applications, including cancer detection, biomarker identification, and prognosis prediction. It is the largest model trained on the most comprehensive dataset to date, featuring nearly 700,000 specimens and clinical reports, covering over 2.3 million slides and 14 million question-answer pairs.
More from Research
- Explained: Why Chain of Thought (CoT) Actually Works in LLMs — NaveenGRao · 2026-08-05
- Independently trained models develop 'universal' attention heads? New research shows predictable neuron scaling — CSProfKGD · 2026-08-05
- Connito Introduces Decentralized MoE Training Network on Bittensor — shibshib89 · 2026-08-05
- Improving Animal Welfare with Tech: Hyperspectral Imaging and E-Beam Vaccines in Poultry — NikoMcCarty · 2026-08-05
- Ex-Citadel Quant Releases Deep Guide on AI Power Pricing and Data Centers — PandaAshwinee · 2026-08-05
- NeurIPS Review Reflections: Compute Barriers and Score Calibration Issues — chhaviyadav_ · 2026-08-05