Artificial intelligence that understands object relationships
Peer-Reviewed Publication
MIT researchers developed a machine learning model that understands the underlying relationships between objects in a scene and can generate accurate images of scenes from text descriptions.
A new analysis by MIT researchers could help architects and builders reduce the carbon footprint of truss structures, the crisscrossing struts that bolster bridges, towers, and buildings.
Researchers have developed a new approach to machine learning that ‘learns how to learn’ and out-performs current machine learning methods for drug design, which in turn could accelerate the search for new disease treatments.
An interdisciplinary research team from the University at Buffalo was awarded a $378,940 grant from the U.S. National Science Foundation to explore how to better utilize the social media platform Twitter for improving disaster response.
Graduate student Ben Bartlett and Shanhui Fan, professor of electrical engineering, have proposed a relatively simple quantum computer design that uses a single atom to manipulate photons and could be constructed with currently available components.
Using a new microspectroscopic technique, collaborating scientists at the University of Massachusetts Amherst and Nanjing University in China have found that steam disinfection of silicone-rubber baby bottle nipples exposes babies and the environment to micro- and nanoplastic particles.
Professor John Reynolds and Senior Postdoctoral Fellow Tom Franken have made headway into understanding how the brain decides which side of a visual border is a foreground object and which is background. The research, published on November 30, 2021 in the journal eLife, sheds light on how areas of the brain communicate to interpret sensory information and build a picture of the world around us.