EnCompass executes AI agent programs by backtracking and making multiple attempts, finding the best set of outputs generated by an LLM. It could help coders work with AI agents more efficiently.
Torralba’s research focuses on computer vision, machine learning, and human visual perception.
As AI technology advances, a new interdisciplinary course seeks to equip students with foundational critical thinking skills in computing.
New research detects hidden evidence of mistaken correlations — and provides a method to improve accuracy.
“MorphoChrome,” developed at MIT, pairs software with a handheld device to make everyday objects iridescent.
Founded by two MIT alumni, Samsara’s platform gives companies a central hub to learn from their workers, equipment, and other infrastructure.
“MechStyle” allows users to personalize 3D models, while ensuring they’re physically viable after fabrication, producing unique personal items and assistive technology.
New research demonstrates how AI models can be tested to ensure they don’t cause harm by revealing anonymized patient health data.
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.
CSAIL researchers find even “untrainable” neural nets can learn effectively when guided by another network’s built-in biases using their guidance method.
MIT-IBM Watson AI Lab researchers developed an expressive architecture that provides better state tracking and sequential reasoning in LLMs over long texts.
An AI-driven system lets users design and build simple, multicomponent objects by describing them with words.
The “self-steering” DisCIPL system directs small models to work together on tasks with constraints, like itinerary planning and budgeting.
The technique can help scientists in economics, public health, and other fields understand whether to trust the results of their experiments.
MIT CSAIL and LIDS researchers developed a mathematically grounded system that lets soft robots deform, adapt, and interact with people and objects, without violating safety limits.