Driven by scalable diffusion models trained on large-scale paired text-i...
Plain text has become a prevalent interface for text-to-image synthesis....
There has been tremendous progress in large-scale text-to-image synthesi...
Videos are created to express emotion, exchange information, and share
e...
Unsupervised learning has recently made exceptional progress because of ...
We ask the question: to what extent can recent large-scale language and ...
Shift invariance is a critical property of CNNs that improves performanc...
Sketching or doodling is a popular creative activity that people engage ...
In order to generate novel 3D shapes with machine learning, one must all...
In this work, we explore the idea that effective generative models for p...
Search results personalization has become an effective way to improve th...
Sound effects play an essential role in producing high-quality radio sto...
We explore the intersection of human and machine creativity by generatin...
Despite their renowned predictive power on i.i.d. data, convolutional ne...
Our team of artists and machine learning researchers designed a creative...