1
We present a method to produce abstractive summaries of long documents that exceed several thousand words via neural abstractive …
Acquiring count annotations generally requires less human effort than point-level and bounding box annotations. Thus, we propose the …
Instance segmentation methods often require costly per-pixel labels. We propose a method called WISE-Net that only requires point-level …
Scene graph generation (SGG) aims to predict graph-structured descriptions of input images, in the form of objects and relationships …
Few-shot classification is challenging because the data distribution of the training set can be widely different to the test set as …
Entropy is ubiquitous in machine learning, but it is in general intractable to compute the entropy of the distribution of an arbitrary …
We propose to study the generalization error of a learned predictor ĥ in terms of that of a surrogate (potentially randomized) …
We study whether a neural network optimizes to the same, linearly connected minimum under different samples of SGD noise (e.g., random …
We introduce and study the problem of Online Continual Compression, where one attempts to simultaneously learn to compress and store a …
Knowledge graphs store facts using relations between two entities. In this work, we address the question of link prediction in …