Understanding the visual knowledge of language models | MIT News

You’ve possible heard {that a} image is price a thousand phrases, however can a big language mannequin (LLM) get the image if it’s by no means seen pictures earlier than? Because it seems, language fashions which might be skilled purely on textual content have a stable understanding of the visible world. They’ll write image-rendering code … Read more

New algorithm discovers language just by watching videos | MIT News

Mark Hamilton, an MIT PhD pupil in electrical engineering and laptop science and affiliate of MIT’s Pc Science and Synthetic Intelligence Laboratory (CSAIL), needs to make use of machines to grasp how animals talk. To try this, he set out first to create a system that may be taught human language “from scratch.” “Humorous sufficient, … Read more

Synthetic imagery sets new bar in AI training efficiency | MIT News

Information is the brand new soil, and on this fertile new floor, MIT researchers are planting extra than simply pixels. By utilizing artificial photos to coach machine studying fashions, a workforce of scientists just lately surpassed outcomes obtained from conventional “real-image” coaching strategies.  On the core of the method is a system known as StableRep, … Read more

New model offers a way to speed up drug discovery | MIT News

Enormous libraries of drug compounds could maintain potential remedies for quite a lot of illnesses, resembling most cancers or coronary heart illness. Ideally, scientists wish to experimentally check every of those compounds towards all potential targets, however doing that sort of display is prohibitively time-consuming. Lately, researchers have begun utilizing computational strategies to display these … Read more

Scaling audio-visual learning without labels | MIT News

Researchers from MIT, the MIT-IBM Watson AI Lab, IBM Analysis, and elsewhere have developed a brand new approach for analyzing unlabeled audio and visible information that would enhance the efficiency of machine-learning fashions utilized in functions like speech recognition and object detection. The work, for the primary time, combines two architectures of self-supervised studying, contrastive … Read more