Speeding up drug discovery with diffusion generative models
MIT researchers built DiffDock, a model that may one day be able to find new drugs faster than traditional methods and reduce the potential for adverse side effects.
A method for designing neural networks optimally suited for certain tasks
With the right building blocks, machine-learning models can more accurately perform tasks like fraud detection or spam filtering.
Strengthening trust in machine-learning models
Associate Professor Tamara Broderick and colleagues build a “taxonomy of trust” to identify where confidence in the results of a data analysis might break down.
Learning to grow machine-learning models
New LiGO technique accelerates training of large machine-learning models, reducing the monetary and environmental cost of developing AI applications.
Detailed images from space offer clearer picture of drought effects on plants
J-WAFS researchers are using remote sensing observations to build high-resolution systems to monitor drought.
Peter Baddoo, Department of Mathematics instructor, dies at 29
Baddoo was a respected and admired scholar, teacher, mentor, and colleague.
Mining the right transition metals in a vast chemical space
Computational chemists design better ways of discovering and designing materials for energy applications.
New method accelerates data retrieval in huge databases
Researchers used machine learning to build faster and more efficient hash functions, which are a key component of databases.
MIT professor to Congress: “We are at an inflection point” with AI
Aleksander Mądry urges lawmakers to ask rigorous questions about how AI tools are being used by corporations.
Creating a versatile vaccine to take on Covid-19 in its many guises
Aided by machine learning, scientists are working to develop a vaccine that would be effective against all SARS-CoV-2 strains.
New insights into training dynamics of deep classifiers
MIT researchers uncover the structural properties and dynamics of deep classifiers, offering novel explanations for optimization, generalization, and approximation in deep networks.
Large language models are biased. Can logic help save them?
MIT researchers trained logic-aware language models to reduce harmful stereotypes like gender and racial biases.
Robot armies duke it out in Battlecode’s epic on-screen battles
The long-running programming competition encourages skills and friendships that last a lifetime.
Phiala Shanahan is seeking fundamental answers about our physical world
With supercomputers and machine learning, the physicist aims to illuminate the structure of everyday particles and uncover signs of dark matter.
MIT-Takeda Program heads into fourth year with crop of 10 new projects
The program leverages MIT’s research expertise and Takeda’s industrial know-how for research in artificial intelligence and medicine.