An old patent from MIT Professor Bill Freeman inspired the new “Y-zipper,” a three-sided fastener that snaps gear, robots, and art into shape at the push of a button.
The CausVid generative AI tool uses a diffusion model to teach an autoregressive (frame-by-frame) system to rapidly produce stable, high-resolution videos.
New dataset of “illusory” faces reveals differences between human and algorithmic face detection, links to animal face recognition, and a formula predicting where people most often perceive faces.