Data collected from the real world tends to be biased, unbalanced, and a...
In this work we propose a novel end-to-end multi-stage Knowledge Graph (...
Inverse protein folding, i.e., designing sequences that fold into a give...
With the prospect of automating a number of chemical tasks with high
fid...
Computational protein design, i.e. inferring novel and diverse protein
s...
Automatic construction of relevant Knowledge Bases (KBs) from text, and
...
Designing novel protein sequences for a desired 3D topological fold is a...
Image captioning has recently demonstrated impressive progress largely o...
Image captioning systems have made substantial progress, largely due to ...
Tabular datasets are ubiquitous in data science applications. Given thei...
In this work, we present a dual learning approach for unsupervised text ...
The loss landscapes of deep neural networks are not well understood due ...
In this paper we propose to perform model ensembling in a multiclass or ...
We study the flow of information and the evolution of internal
represent...
We introduce a new approach to tackle the problem of offensive language ...
In this paper we propose a new conditional GAN for image captioning that...
We present a deep learning model, DE-LSTM, for the simulation of a stoch...
Text attribute transfer using non-parallel data requires methods that ca...
Multivariate time-series modeling and forecasting is an important proble...
We present a new topic model that generates documents by sampling a topi...
While considerable advances have been made in estimating high-dimensiona...
In this work we consider the problem of anomaly detection in heterogeneo...
Hidden semi-Markov models (HSMMs) are latent variable models which allow...