Human Guided Exploration (HuGE) enables AI agents to learn quickly with some help from humans, even if the humans make mistakes.

With the PockEngine training method, machine-learning models can efficiently and continuously learn from user data on edge devices like smartphones.

Researchers coaxed a family of generative AI models to work together to solve multistep robot manipulation problems.

By focusing on causal relationships in genome regulation, a new AI method could help scientists identify new immunotherapy techniques or regenerative therapies.

A new study bridging neuroscience and machine learning offers insights into the potential role of astrocytes in the human brain.

Researchers discover how to control the anomalous Hall effect and Berry curvature to create flexible quantum magnets for use in computers, robotics, and sensors.

This AI system only needs a small amount of data to predict molecular properties, which could speed up drug discovery and material development.

Training artificial neural networks with data from real brains can make computer vision more robust.

MAGE merges the two key tasks of image generation and recognition, typically trained separately, into a single system.

A new multimodal technique blends major self-supervised learning methods to learn more similarly to humans.