Taking race into account when developing tools to predict a patient’s risk of colorectal cancer leads to more accurate predictions when compared with race-blind algorithms, researchers find.
“Cultural prompting” – asking an AI model to perform a task like someone from another part of the world – resulted in reduced bias in responses for the vast majority of the more than 100 countries tested by a Cornell-led research group.
An internationally recognized leader in social networks and algorithmic fairness, the Bowers CIS professor won the award for his foundational contributions in computer science and social science.
The Fall 2024 Scientific Computing Training Series begins October 2, featuring five webinars on Python, JupyterLab, and R, aimed at enhancing research services and scientific collaboration across all Cornell campuses.
The Communal eXtended-Reality (CXR) system is a cutting-edge blend of the physical and digital worlds in which virtual scenes are overlaid onto the real world, designed to engage communities in new ways.
A Cornell-led collaboration developed machine-learning models that use cell-free molecular RNA to diagnose pediatric inflammatory conditions that are difficult to differentiate.
A new computational system called Schemonic, developed by Cornell researchers, cuts the costs of using large language models such as ChatGPT and Google Bard by combing large datasets and generating what amounts to “CliffsNotes” versions of data.
