This new machine-learning model can match corresponding audio and visual data, which could someday help robots interact in the real world.

The CausVid generative AI tool uses a diffusion model to teach an autoregressive (frame-by-frame) system to rapidly produce stable, high-resolution videos.

A lot of sophisticated digital plumbing goes into delivering that streaming video to your phone, computer or TV.

The success of the world’s biggest online video platform has been down to several key innovations.

In a world where algorithms increasingly shape everyday life, many works of art are beginning to reflect how intertwined we’ve become with computational systems.

A new method can train a neural network to sort corrupted data while anticipating next steps. It can make flexible plans for robots, generate high-quality video, and help AI agents navigate digital environments.

The video game is helping China advance toward two strategic goals: bolstering domestic semiconductor production and putting Chinese culture on the global stage.

Researchers find large language models make inconsistent decisions about whether to call the police when analyzing surveillance videos.

A pioneering effort that allowed a teenager with a neck injury to play pinball sheds light on today’s vibrant community of esports players with disabilities.