Innovative methods make artificial intelligence work efficiently on tiny sensors with limited power and memory.

Researchers propose brain-like spiking neural networks and compute-in-memory hardware as the key to overcoming the massive energy bottleneck stifling sustainable AI advancement.

The AI industry's massive demand for memory chips is causing shortages and price spikes for consumer electronics, creating a new "macroeconomic risk" to global supply chains.

Researchers at the University of Southern California develop a memristor that functions at 700 degrees Celsius, far beyond the limits of conventional electronics.

A layered material transforms under pressure, offering energy-efficient, fast data storage for future computers.

Microsoft’s Majorana 1 chip uses a new topological design to push quantum computing toward solving major real-world problems.

Researchers at KAIST have developed a memristor-based chip that learns in real-time for on-board AI applications. 

Google has announced a new quantum chip called Willow, which has good error correction and does very fast quantum computations.

KAIST develops SpecEdge to make large language models more affordable by using consumer-grade graphics processing units alongside data center ones, cutting expenses and improving access.

Researchers created a device that processes information like a brain by using charged particles, allowing small electronics to run powerful artificial intelligence programs while using much less electricity.