Category Technology/Electronics

Agentic workflows are artificial intelligence-powered software systems that chain together multiple models and external tools to tackle complicated tasks, like analyzing a video and answering questions about it. But the way these highly fragmented systems are designed and deployed often causes inefficiencies that can lead to wasted computation, energy and cost.

To improve efficiency, researchers from MIT and Microsoft developed an intelligent system that streamlines the process of designing agentic workflows and automatically optimizes how those workflows are implemented. With this new method, a developer can describe what they want the agentic workflow to do in plain language, without needing to specify all the details of their application in advance.

The system automatically f...

Spiking neural networks (SNNs) are artificial intelligence (AI) models inspired by how biological neurons communicate with each other. While biological neurons exchange information in the form of electrical impulses, SNNs rely on brief signals known as spikes.

SNNs have proved promising for reducing power consumption, as developers can ensure they do not process information continuously, but rather ...

Neuromorphic computing is a computing approach that mimics how the human brain works. Our gray matter is a marvel of nature, capable of handling huge volumes of data with incredible energy efficiency. While modern AI hardware is becoming better at processing complex tasks, it consumes vast amounts of energy.

One of the promises of neuromorphic computing is that it places memory and processing in the same location, using far less energy than traditional AI chips. However, even the most sophisticated neuromorphic systems are fairly simple and don’t come close to matching the number of connections among human neurons.

But a new study published in the journal...

An auto factory worker can remember the storage bin where she left a partly assembled component the night before and quickly return to that spot to pick it up. But robots that may work side by side with her would struggle to develop and access this same type of “spatiotemporal” memory.

Now, MIT researchers have developed a long-term memory framework that allows robots to rapidly form and recall a detailed mental model of complicated, large-scale environments...