ByteBrief
We're a portrait publication through and through. Turn your phone back and your briefing picks up right where you left it.
(We tried widescreen once. It wasn't us.)

Researchers from the University of Rochester and NVIDIA presented PixelDiT2 at NeurIPS this December. This model trades latent space for pixel space to offer control over individual pixels in AI-generated images. The team plans to present findings on video generation next year.
Tap to vote and see what everyone thinks.
Summary by ByteBrief
Germany Announces Nvidia AI Partnership