Listening in on neural activity is a promising way of restoring the ability to communicate for people whose bodies no longer can. Artificial neural networks are the key middleman in the process.

The software tool NeuroTrALE is designed to quickly and efficiently process large amounts of brain imaging data semi-automatically.

In controlled experiments, MIT CSAIL researchers discover simulations of reality developing deep within LLMs, indicating an understanding of language beyond simple mimicry.

The approach can detect anomalies in data recorded over time, without the need for any training.

New algorithm helps robots practice skills like sweeping and placing objects, potentially helping them improve at important tasks in houses, hospitals, and factories.

More efficient than other approaches, the “Thermometer” technique could help someone know when they should trust a large language model.

Introducing structured randomization into decisions based on machine-learning model predictions can address inherent uncertainties while maintaining efficiency.

MAIA is a multimodal agent that can iteratively design experiments to better understand various components of AI systems.

New research suggest the secret to learning new motor skills quickly lies not in our muscles, but in our eyes.

Analysis and materials identified by MIT engineers could lead to more energy-efficient fuel cells, electrolyzers, batteries, or computing devices.