David A. Clifton

LLMs systematically favor text over numbers in evidence arbitration, revealing a critical failure mode in decision-making systems that rely on heterogeneous data sources.

Scaling up pathology foundation models doesn't guarantee better survival prediction—a distilled model with 8% of the parameters can outperform its larger teacher.

Dataset condensation, previously limited to neural networks, can now democratize access to clinical data by enabling privacy-preserving training of classical models like decision trees and Cox regression.