A simpler method for learning to control a robot
Researchers develop a machine-learning technique that can efficiently learn to control a robot, leading to better performance with fewer data.
Researchers develop a machine-learning technique that can efficiently learn to control a robot, leading to better performance with fewer data.
The founders of MIT spinout Active Surfaces describe their thin-film solar technology and their experience winning this year’s $100K.
Researchers discover how to control the anomalous Hall effect and Berry curvature to create flexible quantum magnets for use in computers, robotics, and sensors.
Ultrasound research specialist and 2023 MIT Excellence Award winner Nicole Henning adapts ultrasound technology for more sensitive, less invasive imaging for disease modeling.
The device detects the same molecules that cell receptors do, and may enable routine early screening for cancers and other diseases.
PhD student Nick Caros develops tools to help transit agencies serve the public in an era of remote work.
Visolis, founded by Deepak Dugar SM ’11, MBA ’13, PhD ’13, is working to decarbonize the production of everything from rubber to jet fuel.
A new technique helps a nontechnical user understand why a robot failed, and then fine-tune it with minimal effort to perform a task effectively.
EECS professor appointed to new professorship in the MIT Schwarzman College of Computing.
Mathias Kolle’s color-changing materials take inspiration from butterflies and mollusks.
PIGINet leverages machine learning to streamline and enhance household robots' task and motion planning, by assessing and filtering feasible solutions in complex environments.
A biotech entrepreneur, Koehler will help faculty and students launch startups and bring new products to market through the MIT Deshpande Center for Technological Innovation.
Researchers create a privacy technique that protects sensitive data while maintaining a machine-learning model’s performance.
A pilot-scale system, enabled by an $82 million award from the FDA, aims to accelerate the development and production of mRNA technologies.
“FrameDiff” is a computational tool that uses generative AI to craft new protein structures, with the aim of accelerating drug development and improving gene therapy.