News

Johns Hopkins researchers used betting strategies to help clarify AI models’ decision-making processes.

A recent innovation from Johns Hopkins researchers enables deeper insights into gene function and disease-linked mutations.

A new JHU targeted training approach can make up for a lack of natural spatial ability in robot teleoperation tasks.

New research reveals that AI can’t perceive humans’ unspoken desires and goals as easily as we do.

Johns Hopkins researchers partnered with a local imaging device company to develop an efficient, real-time lumbar puncture guidance system.

A research team including Ziang Xiao has found that popular large language models like GPT-4 cannot yet accurately simulate the real world.

A Johns Hopkins-led interinstitutional research team will develop a novel photoacoustic endoscope and fluorescent contrast agent to ensure total tumor removal and preservation of healthy tissue.

Inspired by human learning patterns, Johns Hopkins computer scientists have developed a new technique to train AI models on massive amounts of medical data without forgetting what they’ve already learned.

Ilya Shpitser fixes common problems found in datasets so that researchers can use them to draw accurate conclusions.

Johns Hopkins researchers determine that explanations and examples improve clinicians’ trust in an AI system that assists with remote strep diagnosis.

Researchers unveil a groundbreaking method to protect question-answering systems from disinformation.

A Johns Hopkins study finds that large language models are more likely to generate irrelevant or harmful responses when operating in underrepresented languages.