Science

New research shows that language models can be trained to reliably identify concepts they’ve been taught, opening a path toward more transparent and controllable artificial intelligence.

A new technique allows aggressively compressed neural networks to regain lost performance by generating synthetic data and transferring knowledge, offering a path to efficient and privacy-preserving AI.

New research reveals that carefully selecting the most impactful data can dramatically reduce the computational cost of training machine learning models for time series analysis in telecommunications.

Researchers are leveraging the power of artificial intelligence to simplify the configuration and management of private 5G networks through natural language commands.

New research examines whether electricity suppliers manipulate bids in response to automated systems designed to prevent market abuse.

A new framework leverages stable, bidirectional graph convolutional networks and intelligent data selection to achieve high accuracy in action recognition with significantly fewer labeled examples.

Researchers have unveiled a challenging benchmark to assess how well artificial intelligence can detect increasingly sophisticated audio-video forgeries.

Researchers have unveiled MarketGen, a scalable simulation environment designed to train and evaluate robots in realistic, automatically generated supermarket scenarios.

Researchers have developed a new framework for verifying the successful removal of malicious triggers from deep learning models.

A new attention mechanism, rooted in the principles of Modern Hopfield Networks, promises to enhance the performance and stability of Transformer models.