News

Researchers seek optimal choices at the ski lodge and inside the operating system.

Johns Hopkins computer scientists introduce a new method to reduce the size of multilingual language models.

Johns Hopkins researchers harness the power of machine learning to develop a first approach to X-ray-guided surgical phase recognition.

New safety tests by Johns Hopkins researchers reveal vulnerabilities of popular systems like DALL-E 2.

In collaboration with NIH and Lumo Imaging, Hopkins researchers demonstrate a computer vision framework to track the evolution of skin lesions over time in total-body photography.

Hopkins researchers unveil new uncertainty quantification methods in an effort to promote appropriate trust in AI use.

Misha Kazhdan's new Distributed Poisson Surface Reconstruction algorithm shares its computational load across PCs to deliver fast, accurate, and watertight reconstructions.

Concerned by recent trends in natural language processing research, Hopkins computer scientists emphasize the importance of user-centric evaluation methods and contextual awareness.

Johns Hopkins researchers demonstrate the promise of “augmented endoscopy,” a real-time neurosurgical guidance method that uses advanced computer vision techniques.

The achievement could provide a clearer picture of the role the chromosome plays in male-specific development, fertility, and genetically triggered diseases like cancer.

Inspired by journalists, Hopkins researchers discover a new technique to ground a large language model’s answers in reality.

Hopkins computer scientists propose a simple solution for a common multilingual language model pitfall.