News

The ability to quickly and affordably survey a patient’s entire genome is expected to accelerate research, diagnostics, and precision medicine.

A Johns Hopkins study reveals how large language models fail to ignore information learned during training.

Created by a Johns Hopkins team in collaboration with the U.S. Food and Drug Administration, the work aims to improve the reliability of artificial intelligence in clinical settings.

A project headed by Johns Hopkins Computer Science faculty has been selected to receive $750,000 for its potential to accelerate AI-driven scientific discovery.

Michael Oberst, Chien-Ming Huang, and other CS faculty members recently participated in the first in-person convening of the Johns Hopkins Workgroup on AI and Healthcare.

Their work, which proves that in-context learning is not tied to language, appears in Transactions on Machine Learning Research.

The AI system detects deadly infections faster than doctors, saving thousands from a condition that claims more than 250,000 lives each year in the U.S.

Researchers at Johns Hopkins and UC San Diego used artificial intelligence to analyze comments in the public record.

Raman Arora and his students presented their latest research on computational algorithms and theory at ICML 2025.

Gene annotation has been more difficult than scientists thought.

The AstroID database allows researchers anywhere to study multiple types of cancer data in one setting.

Johns Hopkins researchers develop a novel neural network with the potential to improve sign language processing.