Abstract: The present invention provides antibody or the antigen-binding portion thereof bind to carbohydrate antigen, such as Globo series antigens (e.g. Globo H, SSEA-4 or SSEA-3). Also disclosed herein are pharmaceutical compositions and methods for the inhibition of cancer cells in a subject in need thereof. The pharmaceutical compositions comprise an antibody or an antigen-binding portion thereof and at least one pharmaceutically acceptable carrier.

Abstract: Provided are systems and methods that improve the computational efficiency of Transformers or other attention-based neural networks or machine learning models by re-using a number of attention scores between layers and/or heads of the model. To reduce the computational cost of self-attention-based models while achieving comparable or even superior results, example aspects of the present disclosure propose a novel architecture that reuses attention scores computed in one layer in one or multiple subsequent layers.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for polynomial mapping of data for linear SVMs. In one aspect, a method includes training a linear classifier by receiving feature vectors and generating a condensed representation of a mapped vector corresponding to a polynomial mapping of each feature vector, the condensed representation including an index into a weight vector for each non-zero component of the mapped vector. A linear classifier is trained on the condensed representations. In another aspect, a method includes receiving a feature vector, identifying non-zero components resulting from a polynomial mapping of the feature vector, and mapping the combination of one or more elements of each non-zero component to a weight in a weight vector to determine a set of weights. The feature vector is classified according to a classification score derived by summing the set of weights.