Natural language processing and 2D vision models have attained remarkabl...
We propose Neural Priming, a technique for adapting large pretrained mod...
Compositional representations of the world are a promising step towards
...
Learned representations are a central component in modern ML systems, se...
Adapting pre-trained models with broad capabilities has become standard
...
Learning binary representations of instances and classes is a classical
...
Enabling robust intelligence in the wild entails learning systems that o...
Visual recognition ecosystems (e.g. ImageNet, Pascal, COCO) have undenia...