Artificial intelligence

A*STAR researchers developed an AI-powered framework to identify microbial producers of valuable natural products from nature’s vast chemical landscape.

Even cutting-edge large language models can fall prey to persistent misleading arguments from users, a new evaluation framework reveals.

Inspired by computer vision hardware, researchers adapt a two-in-one crossbar-based chip design to boost the energy efficiency of AI systems.

Just by seeing the starting state and end goal, AI models could predict how to complete a task by filling in the unknown steps and focusing only on the actions that matter.

The internet’s latest privacy upgrades hide your data, but the patterns they leave behind can still reveal where you browse.

Nanopore sequencing and a self-enhancing AI model team up to enable a faster and more accurate method for reading synthetic genes.

A new framework to train artificial intelligence models draws on concepts from game theory to improve model stability and performance.

A new attribute-based approach to object detection helps visual artificial intelligence models spot unknown objects more accurately and efficiently.

The largest RNA language model to date helps researchers uncover the hidden roles played by non-coding RNA sequences in our cells.

By exploiting natural hardware imperfections in optical devices, a new photonics platform offers a base for robust and reliable AI models.

A new precision oncology platform taps into machine learning to guide colorectal cancer treatments based on individual genetics.

A new comprehensive benchmark for audio-based artificial intelligence allows researchers to gauge and improve the way models follow speech, soundscapes and everyday cues.