To excel at engineering design, generative AI must learn to innovate, study finds
AI models that prioritize similarity falter when asked to design something completely new.
“Pangea” study aims to modernize national test and training infrastructure
Lincoln Laboratory is developing a roadmap to streamline system acquisitions and facilitate connectivity across the Southwestern test ranges.
Teachers embrace hands-on learning in Materials Genome Camp
Educators in weeklong MIT workshop mold self-healing metal, bridging materials science and classroom engagement.
How to help high schoolers prepare for the rise of artificial intelligence
A one-week summer program aims to foster a deeper understanding of machine-learning approaches in health among curious young minds.
MIT researchers combine deep learning and physics to fix motion-corrupted MRI scans
The challenge involves more than just a blurry JPEG. Fixing motion artifacts in medical imaging requires a more sophisticated approach.
New method simplifies the construction process for complex materials
With a new, user-friendly interface, researchers can quickly design many cellular metamaterial structures that have unique mechanical properties.
Making sense of cell fate
MIT researchers find timing and dosage of DNA-damaging drugs are key to whether a cancer cell dies or enters senescence.
New quantum magnet unleashes electronics potential
Researchers discover how to control the anomalous Hall effect and Berry curvature to create flexible quantum magnets for use in computers, robotics, and sensors.
Armando Solar-Lezama named inaugural Distinguished Professor of Computing
EECS professor appointed to new professorship in the MIT Schwarzman College of Computing.
Cutting urban carbon emissions by retrofitting buildings
Study shows that cities’ plans often won’t achieve their goals, but decarbonizing the local grid could make the difference.
Learning the language of molecules to predict their properties
This AI system only needs a small amount of data to predict molecular properties, which could speed up drug discovery and material development.
When computer vision works more like a brain, it sees more like people do
Training artificial neural networks with data from real brains can make computer vision more robust.
A new mathematical “blueprint” is accelerating fusion device development
New research explores how Dyson maps are putting quantum computers to work in designing fusion energy devices.
Helping robots handle fluids
Researchers create a new simulation tool for robots to manipulate complex fluids in a step toward helping them more effortlessly assist with daily tasks.
A better way to match 3D volumes
By mapping the volumes of objects, rather than their surfaces, a new technique could yield solutions to computer graphics problems in animation and CAD.