News

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.

A new machine learning framework promises to make systems more personal and ethical.

Johns Hopkins researchers are using Loop-X Mobile Imaging Robot by Brainlab to forge the future of the intelligent operating room.

The Hopkins-led team demonstrated that an AI model trained solely on synthetic tumor data works as well as models trained on real tumors.

A Johns Hopkins-led team found that chatbots reinforce our biases, providing insight into how AI could widen the public divide on controversial issues.

Johns Hopkins researchers compare GPT models to “sloppy paralegals.”