MIBURI is a system that makes a talking digital character move its body and face expressively in real time while it speaks.
DreamWorld is a new way to make videos that not only look real but also follow common-sense rules about motion, space, and meaning.
SenCache speeds up video diffusion models by reusing past answers only when the model is predicted to change very little.
Diffusion models make great images but are slow because they fix noise step by step many times.
SARAH is a real-time system that makes virtual characters move their whole bodies naturally during a conversation while knowing where the user is.
MolHIT is a new AI that builds molecules as graphs, moving from broad chemical groups to exact atoms step by step.
DreamZero is a robot brain that learns actions by predicting short videos of the future and the matching moves at the same time.
DreamID-Omni is one model that can create, edit, and animate human-centered videos with matching voices, all in sync.
PixelGen is a new image generator that works directly with pixels and uses what-looks-good-to-people guidance (perceptual loss) to improve quality.
This paper shows how to make a whole picture in one go, directly in pixels, without using a hidden “latent” space or many tiny steps.
This paper shows how a video generator can improve its own videos during sampling, without extra training or outside checkers.
Alterbute is a diffusion-based method that changes an object's intrinsic attributes (color, texture, material, shape) in a photo while keeping the object's identity and the scene intact.