AI-generated sensors open new paths for early cancer detection
Nanoparticles coated with molecular sensors could be used to develop at-home tests for many types of cancer.
Sean Luk: Addressing the urgent need for better immunotherapy
The MIT senior helps design proteins that spur the immune system to fight cancer and other diseases.
MIT scientists investigate memorization risk in the age of clinical AI
New research demonstrates how AI models can be tested to ensure they don’t cause harm by revealing anonymized patient health data.
One pull of a string is all it takes to deploy these complex structures
A new method could enable users to design portable medical devices, like a splint, that can be rapidly converted from flat panels to a 3D object without any tools.
MIT community in 2025: A year in review
Top stories highlighted the Institute’s leading positions in world and national rankings; new collaboratives tackling manufacturing, generative AI, and quantum; how one professor influenced hundreds of thousands of students around the world; and more.
MIT’s top research stories of 2025
Concrete batteries, AI-developed antibiotics, the ozone’s recovery, and a more natural bionic knee were some of the most popular topics on MIT News.
Study: High-fat diets make liver cells more likely to become cancerous
New research suggests liver cells exposed to too much fat revert to an immature state that is more susceptible to cancer-causing mutations.
Study: More eyes on the skies will help planes reduce climate-warming contrails
Images from geostationary satellites alone aren’t enough to help planes avoid contrail-prone regions, MIT researchers report.
“Wait, we have the tech skills to build that”
From robotics to apps like “NerdXing,” senior Julianna Schneider is building technologies to solve problems in her community.
Building reuse into the materials around us
At MIT, metallurgist Diran Apelian ScD ’73 urges engineers and researchers to rethink design, recycling, and the life cycle of modern materials.
Guided learning lets “untrainable” neural networks realize their potential
CSAIL researchers find even “untrainable” neural nets can learn effectively when guided by another network’s built-in biases using their guidance method.
A new way to increase the capabilities of large language models
MIT-IBM Watson AI Lab researchers developed an expressive architecture that provides better state tracking and sequential reasoning in LLMs over long texts.
Post-COP30, more aggressive policies needed to cap global warming at 1.5 C
Global Change Outlook report for 2025 shows how accelerated action can reduce climate risks and improve sustainability outcomes, while highlighting potential geopolitical hurdles.
Student Spotlight: Diego Temkin
The senior, who is involved in Dormitory Council, Hydrant, the Student Information Processing Board, and SuperUROP, is double majoring in computer science and engineering and in urban planning.
MIT-Hood Pediatric Innovation Hub convenes leaders to advance pediatric health
The Hood Pediatric Innovation Hub brings together clinicians, researchers, and industry to bridge the gap between discovery and care.