Simpler models can outperform deep learning at climate prediction
New research shows the natural variability in climate data can cause AI models to struggle at predicting local temperature and rainfall.
Search Stories
At convocation, President Kornbluth greets the Class of 2029
“We believe in all of you,” MIT’s president said at the welcoming ceremony for new undergraduates.
Materials Research Laboratory: Driving interdisciplinary materials research at MIT
The MRL helps bring together academia, government, and industry to accelerate innovation in sustainability, energy, and advanced materials.
New laser “comb” can enable rapid identification of chemicals with extreme precision
The ultrabroadband infrared frequency comb could be used for chemical detection in portable spectrometers or high-resolution remote sensors.
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.
A shape-changing antenna for more versatile sensing and communication
You can adjust the frequency range of this durable, inexpensive antenna by squeezing or stretching its structure.
MIT gears up to transform manufacturing
The Initiative for New Manufacturing is convening experts across the Institute to drive a transformation of production across the U.S. and the world.
Jessika Trancik named director of the Sociotechnical Systems Research Center
Trancik will lead multidisciplinary research center focused on the high-impact, complex, sociotechnical systems that shape our world.
Better public service with data
MIT master’s student and Brazilian diplomat Davi Augusto Oliveira Pinto wants to help policymakers make informed choices to improve people’s lives.
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.
Helping data storage keep up with the AI revolution
Storage systems from Cloudian, co-founded by an MIT alumnus, are helping businesses feed data-hungry AI models and agents at scale.
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.
Ultrasmall optical devices rewrite the rules of light manipulation
Nanophotonic devices developed at MIT are compact, efficient, reprogrammable, adaptive, and able to dynamically respond to external inputs.
Ushering in a new era of suture-free tissue reconstruction for better healing
MIT spinout Tissium recently secured FDA marketing authorization of a biopolymer platform for nerve repair.
New algorithms enable efficient machine learning with symmetric data
This new approach could lead to enhanced AI models for drug and materials discovery.