A faster way to estimate AI power consumption
The “EnergAIzer” method generates reliable results in seconds, enabling data center operators to efficiently allocate resources and reduce wasted energy.
Data
MIT scientists build the world’s largest collection of Olympiad-level math problems, and open it to everyone
New dataset of 30,000-plus competition math problems from 47 countries gives AI researchers a harder test — and students worldwide a better training ground.
Teaching AI models to say “I’m not sure”
A new training method improves the reliability of AI confidence estimates without sacrificing performance, addressing a root cause of hallucination in reasoning models.
New technique makes AI models leaner and faster while they’re still learning
Researchers use control theory to shed unnecessary complexity from AI models during training, cutting compute costs without sacrificing performance.
Helping data centers deliver higher performance with less hardware
Researchers developed a system that intelligently balances workloads to improve the efficiency of flash storage hardware in a data center.
Augmenting citizen science with computer vision for fish monitoring
MIT Sea Grant works with the Woodwell Climate Research Center and other collaborators to demonstrate a deep learning-based system for fish monitoring.
How to create “humble” AI
An MIT-led team is designing artificial intelligence systems for medical diagnosis that are more collaborative and forthcoming about uncertainty.
On algorithms, life, and learning
Operations research expert Dimitris Bertsimas delivered the annual Killian Lecture, providing a look at the past and future of his work.
Generative AI improves a wireless vision system that sees through obstructions
With this new technique, a robot could more accurately detect hidden objects or understand an indoor scene using reflected Wi-Fi signals.
Can AI help predict which heart-failure patients will worsen within a year?
Researchers at MIT, Mass General Brigham, and Harvard Medical School developed a deep-learning model to forecast a patient’s heart failure prognosis up to a year in advance.