DenseAV, developed at MIT, learns to parse and understand the meaning of language just by watching videos of people talking, with potential applications in multimedia search, language learning, and robotics.

The technique characterizes a material’s electronic properties 85 times faster than conventional methods.

“Alchemist” system adjusts the material attributes of specific objects within images to potentially modify video game models to fit different environments, fine-tune VFX, and diversify robotic training.

The new technique could enable detailed studies of how brain cells develop and communicate with each other.

The more time you spend on image-led social media, the more likely you are to want to alter your appearance, researchers find.

Scientists have monitored mangroves in Mauritius, and found some forests are growing.

For the first time, researchers use a combination of MEG and fMRI to map the spatio-temporal human brain dynamics of a visual image being recognized.

By providing plausible label maps for one medical image, the Tyche machine-learning model could help clinicians and researchers capture crucial information.

The invisible threat of deepfake porn now pervades the lives of women and girls

An MRI method purported to detect neurons’ rapid impulses produces its own misleading signals instead, an MIT study finds.