Researchers teach LLMs to solve complex planning challenges
This new framework leverages a model’s reasoning abilities to create a “smart assistant” that finds the optimal solution to multistep problems.
This new framework leverages a model’s reasoning abilities to create a “smart assistant” that finds the optimal solution to multistep problems.
A new international collaboration unites MIT and maritime industry leaders to develop nuclear propulsion technologies, alternative fuels, data-powered strategies for operation, and more.
Researchers fuse the best of two popular methods to create an image generator that uses less energy and can run locally on a laptop or smartphone.
New research could allow a person to correct a robot’s actions in real-time, using the kind of feedback they’d give another human.
Agreement between MIT Microsystems Technology Laboratories and GlobalFoundries aims to deliver power efficiencies for data centers and ultra-low power consumption for intelligent devices at the edge.
The programmable proteins are compact, modular, and can be directed to modify DNA in human cells.
FragFold, developed by MIT Biology researchers, is a computational method with potential for impact on biological research and therapeutic applications.
A new study shows LLMs represent different data types based on their underlying meaning and reason about data in their dominant language.
Whitehead Institute and CSAIL researchers created a machine-learning model to predict and generate protein localization, with implications for understanding and remedying disease.
A deep neural network called CHAIS may soon replace invasive procedures like catheterization as the new gold standard for monitoring heart health.