Research

Filter Options

Tuesday, July 23, 2024

alt="The automated, multimodal approach developed by MIT researchers interprets artificial vision models that evaluate the properties of images (Credits: iStock)."

CSAIL article

MIT researchers advance automated interpretability in AI models

As artificial intelligence models become increasingly prevalent and are integrated into diverse sectors like health care, finance, education, transportation, and entertainment, understanding how they work under the hood is critical. Interpreting the mechanisms underlying AI models enables us to audit them for safety and biases, with the potential to deepen our understanding of the science behind intelligence itself.

Tuesday, July 16, 2024

alt="MIT CSAIL researchers helped design a new technique that can guarantee the stability of robots controlled by neural networks. This development could eventually lead to safer autonomous vehicles and industrial robots (Credits: Alex Shipps/MIT CSAIL)."

CSAIL article

Creating and verifying stable AI-controlled systems in a rigorous and flexible way

Neural networks have made a seismic impact on how engineers design controllers for robots, catalyzing more adaptive and efficient machines. Still, these brain-like machine-learning systems are a double-edged sword: Their complexity makes them powerful, but it also makes it difficult to guarantee that a robot powered by a neural network will safely accomplish its task.

Tuesday, July 16, 2024

alt="A new method could help models predict a material's thermal properties, such as by revealing the dynamics of atoms in crystals, as illustrated here (Credits: Image courtesy of the researchers)."

CSAIL article

AI method radically speeds predictions of materials’ thermal properties

It is estimated that about 70 percent of the energy generated worldwide ends up as waste heat.

Thursday, July 11, 2024

alt="MIT researchers examined how LLMs fare with variations of different tasks, putting their memorization and reasoning skills to the test. The result: Their reasoning abilities are often overestimated (Image: Alex Shipps/MIT CSAIL)."

CSAIL article

Reasoning skills of large language models are often overestimated

When it comes to artificial intelligence, appearances can be deceiving. The mystery surrounding the inner workings of large language models (LLMs) stems from their vast size, complex training methods, hard-to-predict behaviors, and elusive interpretability.