Can large language models figure out the real world?
New test could help determine if AI systems that make accurate predictions in one area can understand it well enough to apply that ability to a different area.
Research
A new model predicts how molecules will dissolve in different solvents
Solubility predictions could make it easier to design and synthesize new drugs, while minimizing the use of more hazardous solvents.
Researchers glimpse the inner workings of protein language models
A new approach can reveal the features AI models use to predict proteins that might make good drug or vaccine targets.
How AI could speed the development of RNA vaccines and other RNA therapies
MIT engineers used a machine-learning model to design nanoparticles that can deliver RNA to cells more efficiently.
Using generative AI, researchers design compounds that can kill drug-resistant bacteria
The team used two different AI approaches to design novel antibiotics, including one that showed promise against MRSA.
A new way to test how well AI systems classify text
As large language models increasingly dominate our everyday lives, new systems for checking their reliability are more important than ever.
Eco-driving measures could significantly reduce vehicle emissions
New research shows automatically controlling vehicle speeds to mitigate traffic at intersections can cut carbon emissions between 11 and 22 percent.
MIT tool visualizes and edits “physically impossible” objects
By visualizing Escher-like optical illusions in 2.5 dimensions, the “Meschers” tool could help scientists understand physics-defying shapes and spark new designs.
New algorithms enable efficient machine learning with symmetric data
This new approach could lead to enhanced AI models for drug and materials discovery.
Robot, know thyself: New vision-based system teaches machines to understand their bodies
Neural Jacobian Fields, developed by MIT CSAIL researchers, can learn to control any robot from a single camera, without any other sensors.