Helping computer vision and language models understand what they see
Researchers use synthetic data to improve a model’s ability to grasp conceptual information, which could enhance automatic captioning and question-answering systems.
Researchers use synthetic data to improve a model’s ability to grasp conceptual information, which could enhance automatic captioning and question-answering systems.
MIT Plasma Science and Fusion Center will receive DoE support to improve access to fusion data and increase workforce diversity.
The MIT and Accenture Convergence Initiative for Industry and Technology selects three new research projects to support.
The MIT Schwarzman College of Computing awards seed grants to seven interdisciplinary projects exploring AI-augmented management.
MIT researchers investigate the causes of health-care disparities among underrepresented groups.
Researchers develop a machine-learning technique that can efficiently learn to control a robot, leading to better performance with fewer data.
The dataset, being collected as part of a US Coast Guard science mission, will be released open source to help advance naval mission planning and climate change studies.
A new technique helps a nontechnical user understand why a robot failed, and then fine-tune it with minimal effort to perform a task effectively.
Author and African American studies scholar Ruha Benjamin urges MIT Libraries staff to “re-imagine the default settings” of technology for a more just future.
Researchers create a privacy technique that protects sensitive data while maintaining a machine-learning model’s performance.