Recent advances in high-fidelity simulators have enabled closed-loop tra...
We revisit the challenging problem of training Gaussian-Bernoulli restri...
Forward gradient learning computes a noisy directional gradient and is a...
Large language models have recently shown promising progress in mathemat...
Real world learning scenarios involve a nonstationary distribution of cl...
Self-driving vehicles must perceive and predict the future positions of
...
Modern self-driving perception systems have been shown to improve upon
p...
Recent work on hyperparameters optimization (HPO) has shown the possibil...
Growing at a very fast pace, modern autonomous systems will soon be depl...
Self-supervised representation learning is able to learn semantically
me...
As self-driving systems become better, simulating scenarios where the
au...
We consider the problem of generating realistic traffic scenes automatic...
Existing approaches to few-shot learning deal with tasks that have
persi...
Learned communication makes multi-agent systems more effective by aggreg...
In this paper, we propose an end-to-end self-driving network featuring a...
Machine learning models have traditionally been developed under the
assu...
Sketch drawings are an intuitive visual domain that appeals to human
ins...
In this paper we propose a novel end-to-end learnable network that perfo...
In this paper, we tackle the problem of detecting objects in 3D and
fore...
Deep neural nets typically perform end-to-end backpropagation to learn t...
In this paper we tackle the problem of routing multiple agents in a
coor...
We aim to bridge the gap between typical human and machine-learning
envi...
Modern autonomous driving systems rely heavily on deep learning models t...
In the past few years, we have seen great progress in perception algorit...
Recent studies on catastrophic forgetting during sequential learning
typ...
The motion planners used in self-driving vehicles need to generate
traje...
Point clouds are the native output of many real-world 3D sensors. To bor...
Machine learning classifiers are often trained to recognize a set of
pre...
Neural architecture search (NAS) automatically finds the best task-speci...
Deep neural networks have been shown to be very powerful modeling tools ...
Careful tuning of the learning rate, or even schedules thereof, can be
c...
In few-shot classification, we are interested in learning algorithms tha...
Conventional deep convolutional neural networks (CNNs) apply convolution...
Deep residual networks (ResNets) have significantly pushed forward the
s...
Normalization techniques have only recently begun to be exploited in
sup...
While convolutional neural networks have gained impressive success recen...
This work aims to address the problem of image-based question-answering ...