A new framework to efficiently screen drugs
Novel method to scale phenotypic drug screening drastically reduces the number of input samples, costs, and labor required to execute a screen.
Search Stories
Using spatial learning to transform math and science education
PrismsVR, founded by Anurupa Ganguly ’07, MNG ’09, takes students to virtual worlds to learn through experiences and movement.
Combining next-token prediction and video diffusion in computer vision and robotics
A new method can train a neural network to sort corrupted data while anticipating next steps. It can make flexible plans for robots, generate high-quality video, and help AI agents navigate digital environments.
MIT economists Daron Acemoglu and Simon Johnson share Nobel Prize
Along with James Robinson, the professors are honored for work on the relationship between economic growth and political institutions.
MIT Energy and Climate Club mobilizes future leaders to address global climate issues
One of the largest MIT clubs sees itself as “the umbrella of all things related to energy and climate on campus.”
Teen uses pharmacology learned through MIT OpenCourseWare to extract and study medicinal properties of plants
Inspired by traditional medicine, 17-year-old Tomás Orellana is on a mission to identify plants that can help treat students’ health issues.
On technology in schools, think evolution, not revolution
Associate Professor Justin Reich’s work shows high-tech tools infuse into education one step at a time, as schools keep adapting and changing.
Modeling relationships to solve complex problems efficiently
Associate Professor Julian Shun develops high-performance algorithms and frameworks for large-scale graph processing.
How AI is improving simulations with smarter sampling techniques
MIT CSAIL researchers created an AI-powered method for low-discrepancy sampling, which uniformly distributes data points to boost simulation accuracy.
Accelerating particle size distribution estimation
MIT researchers speed up a novel AI-based estimator for medication manufacturing by 60 times.
AI model can reveal the structures of crystalline materials
By analyzing X-ray crystallography data, the model could help researchers develop new materials for many applications, including batteries and magnets.
Liftoff: The Climate Project at MIT takes flight
The major effort to accelerate practical climate change solutions launches as its mission directors meet the Institute community.
Enhancing LLM collaboration for smarter, more efficient solutions
“Co-LLM” algorithm helps a general-purpose AI model collaborate with an expert large language model by combining the best parts of both answers, leading to more factual responses.
Protecting the rights of internet users, in Mexico and worldwide
PhD student Mariel García-Montes researches the internet’s far-reaching impact on society, especially regarding privacy and young people.
Study: Early dark energy could resolve cosmology’s two biggest puzzles
In the universe’s first billion years, this brief and mysterious force could have produced more bright galaxies than theory predicts.