Latest Technologies
Explore the technologies shaping our future.
A class of machine learning frameworks used to generate new data with the same statistics as the training set.
A machine learning technique that trains an algorithm across multiple decentralized edge devices or servers holding local data samples.
A method by which one party can prove to another party that a given statement is true, without conveying any additional information apart from the fact that the statement is indeed true.
The practice of using the physical world as a canvas for digital content, blending the real and virtual worlds seamlessly.
Featured Research
Dive into recent papers from leading researchers.
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.
We present a new algorithm for real-time ambient occlusion. It is robust, artifact-free, and handles dynamic scenes. The algorithm is based on a new formulation of ambient occlusion as a problem of searching for occluders in a volume.