AI stirs up the recipe for concrete in MIT study
With demand for cement alternatives rising, an MIT team uses machine learning to hunt for new ingredients across the scientific literature.
With demand for cement alternatives rising, an MIT team uses machine learning to hunt for new ingredients across the scientific literature.
SketchAgent, a drawing system developed by MIT CSAIL researchers, sketches up concepts stroke-by-stroke, teaching language models to visually express concepts on their own and collaborate with humans.
Courses on developing AI models for health care need to focus more on identifying and addressing bias, says Leo Anthony Celi.
Researchers redesign a compact RNA-guided enzyme from bacteria, making it an efficient editor of human DNA.
Researchers also found these effects can be reversed by treatment with an antioxidant.
Gift from the Leinweber Foundation, in addition to a $5 million commitment from the School of Science, will drive discovery, collaboration, and the next generation of physics leaders.
These devices could pack three times as much energy per pound as today’s best EV batteries, offering a lightweight option for powering trucks, planes, or ships.
MIT researchers developed a new model of memory that includes critical contributions from astrocytes, a class of brain cells.
The Institute-wide effort aims to bolster industry and create jobs by driving innovation across vital manufacturing sectors.
A large impact could have briefly amplified the moon’s weak magnetic field, creating a momentary spike that was recorded in some lunar rocks.
Led by Assistant Professor Richard Teague, a team of international astronomers has released a collection of papers and public data furthering our understanding of planet formation.
MIT researchers’ new membrane separates different types of fuel based on their molecular size, eliminating the need for energy-intensive crude oil distillation.
The “one-of-a-kind” phenomenon was observed in ordinary graphite.
Ground-level ozone in North America and Western Europe may become less sensitive to cutting NOx emissions. The opposite may occur in Northeast Asia.
This new machine-learning model can match corresponding audio and visual data, which could someday help robots interact in the real world.