Knowledge distillation is commonly used for compressing neural networks ...
Despite the seeming success of contemporary grounded text generation sys...
Given a particular embodiment, we propose a novel method (C3PO) that lea...
Neural retrieval models have superseded classic bag-of-words methods suc...
We investigate models that can generate arbitrary natural language text ...
The goal of continuous control is to synthesize desired behaviors. In
re...
We use functional mirror ascent to propose a general framework (referred...
Learning data representations that are useful for various downstream tas...
We present Brax, an open source library for rigid body simulation with a...
Offline Reinforcement Learning (RL) aims at learning an optimal control ...
Concave Utility Reinforcement Learning (CURL) extends RL from linear to
...
Adversarial imitation learning has become a popular framework for imitat...
We address the issue of tuning hyperparameters (HPs) for imitation learn...
Hierarchical Agglomerative Clustering (HAC) is one of the oldest but sti...
The idea behind the unsupervised learning of disentangled
representation...
The goal of the unsupervised learning of disentangled representations is...
In recent years, on-policy reinforcement learning (RL) has been successf...
In self-supervised visual representation learning, a feature extractor i...
Intelligent agents should be able to learn useful representations by
obs...
Recent progress in the field of reinforcement learning has been accelera...
Learning meaningful and compact representations with structurally
disent...
Recently there has been a significant interest in learning disentangled
...
A disentangled representation encodes information about the salient fact...
Despite the tremendous progress in the estimation of generative models, ...
Learning disentangled representations is considered a cornerstone proble...
Deep generative models are becoming a cornerstone of modern machine lear...
Learning useful representations with little or no supervision is a key
c...
In recent years, the interest in unsupervised learning of disentangled
r...
Recent advances in generative modeling have led to an increased interest...
Scaling clustering algorithms to massive data sets is a challenging task...
We investigate coresets - succinct, small summaries of large data sets -...
Uniform deviation bounds limit the difference between a model's expected...
Coresets are compact representations of data sets such that models train...
A variety of large-scale machine learning problems can be cast as instan...
Outliers are ubiquitous in modern data sets. Distance-based techniques a...
Coresets are efficient representations of data sets such that models tra...