LiDAR sensors play an important role in the perception stack of modern
a...
Clinical decision making requires counterfactual reasoning based on a fa...
Transformers were originally proposed as a sequence-to-sequence model fo...
Programming is a powerful and ubiquitous problem-solving tool. Developin...
Studying phenotype-gene association can uncover mechanism of diseases an...
Travel-time prediction constitutes a task of high importance in
transpor...
We present a new dataset of Wikipedia articles each paired with a knowle...
Computer-Aided Design (CAD) applications are used in manufacturing to mo...
Mixed Integer Programming (MIP) solvers rely on an array of sophisticate...
We study the problem of learning efficient algorithms that strongly
gene...
Learning graph generative models is a challenging task for deep learning...
Clustering with variable selection is a challenging but critical task fo...
We propose prioritized unit propagation with periodic resetting, which i...
This paper considers the problem of efficient exploration of unseen
envi...
We propose a new family of efficient and expressive deep generative mode...
Estimating the number of clusters (K) is a critical and often difficult ...
Graph neural networks have become increasingly popular in recent years d...
Effective modeling of electronic health records (EHR) is rapidly becomin...
We present a deep reinforcement learning approach to optimizing the exec...
This paper addresses the challenging problem of retrieval and matching o...
We introduce a framework for Compositional Imitation Learning and Execut...
In sequence generation task, many works use policy gradient for model
op...
We introduce an approach for deep reinforcement learning (RL) that impro...
Artificial intelligence (AI) has undergone a renaissance recently, makin...
Graphs are fundamental data structures which concisely capture the relat...
We introduce Imagination-Augmented Agents (I2As), a novel architecture f...
Conventional wisdom holds that model-based planning is a powerful approa...
Generative adversarial nets (GANs) are a promising technique for modelin...
We study characteristics of receptive fields of units in deep convolutio...
Graph-structured data appears frequently in domains including chemistry,...
We investigate the problem of learning representations that are invarian...
We consider the problem of learning deep generative models from data. We...
A key element in transfer learning is representation learning; if
repres...
The mean field algorithm is a widely used approximate inference algorith...