Mind-Video: High-quality Video Reconstruction from Brain Activity

Mind-Video learns spatiotemporal information from continuous fMRI data of the cerebral cortex progressively through masked brain modeling, multimodal contrastive learning with spatiotemporal attention, and co-training with an augmented Stable Diffusion model that incorporates network temporal inflation

real

techbros.. requesting explanation in the comments

Elon Musk’s brain implant company Neuralink approved for in-human study

New Photoshop’s AI tool Generative Fill can predict the future

AudioToken: Audio-to-Image generation based on adaptation of text-conditioned diffusion models

Demo | Paper

let him cook

⚡️the robot uprising began

Japan Goes All In: Copyright Doesn’t Apply To AI Training

The policy allows AI to use any data “regardless of whether it is for non-profit or commercial purposes, whether it is an act other than reproduction, or whether it is content obtained from illegal sites or otherwise.”