Research
Research

A smarter way for large language models to think about hard problems

This new technique enables LLMs to dynamically adjust the amount of computation they use for reasoning, based on the difficulty of the question.

MIT engineers design an aerial microrobot that can fly as fast as a bumblebee

With insect-like speed and agility, the tiny robot could someday aid in search-and-rescue missions.

Helping power-system planners prepare for an unknown future

Macro, a modeling tool developed by the MIT Energy Initiative, enables energy-system planners to explore options for developing infrastructure to support decarbonized, reliable, and low-cost power grids.

New control system teaches soft robots the art of staying safe

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.

Researchers discover a shortcoming that makes LLMs less reliable

Large language models can learn to mistakenly link certain sentence patterns with specific topics — and may then repeat these patterns instead of reasoning.

MIT scientists debut a generative AI model that could create molecules addressing hard-to-treat diseases

BoltzGen generates protein binders for any biological target from scratch, expanding AI’s reach from understanding biology toward engineering it.

How artificial intelligence can help achieve a clean energy future

AI supports the clean energy transition as it manages power grid operations, helps plan infrastructure investments, guides development of novel materials, and more.

The cost of thinking

MIT neuroscientists find a surprising parallel in the ways humans and new AI models solve complex problems.

New AI agent learns to use CAD to create 3D objects from sketches

The virtual VideoCAD tool could boost designers’ productivity and help train engineers learning computer-aided design.

MIT Energy Initiative launches Data Center Power Forum

MIT faculty and MITEI member company experts address power demand from data centers.