
Touchbased Curiosity for SparseReward Tasks
Robots in many realworld settings have access to force/torque sensors i...
read it

Learning Task Decomposition with Ordered Memory Policy Network
Many complex realworld tasks are composed of several levels of subtask...
read it

Continuous Coordination As a Realistic Scenario for Lifelong Learning
Current deep reinforcement learning (RL) algorithms are still highly tas...
read it

Emergent Communication under Competition
The literature in modern machine learning has only negative results for ...
read it

Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex Optimization
Flowbased models are powerful tools for designing probabilistic models ...
read it

StructFormer: Joint Unsupervised Induction of Dependency and Constituency Structure from Masked Language Modeling
There are two major classes of natural language grammars – the dependenc...
read it

Gradient Starvation: A Learning Proclivity in Neural Networks
We identify and formalize a fundamental gradient descent phenomenon resu...
read it

Unsupervised Learning of Dense Visual Representations
Contrastive selfsupervised learning has emerged as a promising approach...
read it

NUGAN: High resolution neural upsampling with GAN
In this paper, we propose NUGAN, a new method for resampling audio from...
read it

Neural Approximate Sufficient Statistics for Implicit Models
We consider the fundamental problem of how to automatically construct su...
read it

Recursive TopDown Production for Sentence Generation with Latent Trees
We model the recursive production property of contextfree grammars for ...
read it

Supervised Seeded Iterated Learning for Interactive Language Learning
Language drift has been one of the major obstacles to train language mod...
read it

Integrating Categorical Semantics into Unsupervised Domain Translation
While unsupervised domain translation (UDT) has seen a lot of success re...
read it

DataEfficient Reinforcement Learning with Momentum Predictive Representations
While deep reinforcement learning excels at solving tasks where large am...
read it

Generative Graph Perturbations for Scene Graph Prediction
Inferring objects and their relationships from an image is useful in man...
read it

ARDAE: Towards Unbiased Neural Entropy Gradient Estimation
Entropy is ubiquitous in machine learning, but it is in general intracta...
read it

Graph DensityAware Losses for Novel Compositions in Scene Graph Generation
Scene graph generation (SGG) aims to predict graphstructured descriptio...
read it

A LargeScale, OpenDomain, MixedInterface DialogueBased ITS for STEM
We present Korbit, a largescale, opendomain, mixedinterface, dialogue...
read it

Countering Language Drift with Seeded Iterated Learning
Supervised learning methods excel at capturing statistical properties of...
read it

Pix2Shape – Towards Unsupervised Learning of 3D Scenes from Images using a Viewbased Representation
We infer and generate threedimensional (3D) scene information from a si...
read it

OutofDistribution Generalization via Risk Extrapolation (REx)
Generalizing outside of the training distribution is an open challenge f...
read it

Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models
In this work, we propose a new family of generative flows on an augmente...
read it

CLOSURE: Assessing Systematic Generalization of CLEVR Models
The CLEVR dataset of naturallooking questions about 3Drendered scenes ...
read it

Selective Brain Damage: Measuring the Disparate Impact of Model Pruning
Neural network pruning techniques have demonstrated it is possible to re...
read it

Ordered Memory
Stackaugmented recurrent neural networks (RNNs) have been of interest t...
read it

Icentia11K: An Unsupervised Representation Learning Dataset for Arrhythmia Subtype Discovery
We release the largest public ECG dataset of continuous raw signals for ...
read it

MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
Previous works <cit.> have found that generating coherent raw audio wave...
read it

No Press Diplomacy: Modeling MultiAgent Gameplay
Diplomacy is a sevenplayer nonstochastic, noncooperative game, where ...
read it

VideoNavQA: Bridging the Gap between Visual and Embodied Question Answering
Embodied Question Answering (EQA) is a recently proposed task, where an ...
read it

Detecting semantic anomalies
We critically appraise the recent interest in outofdistribution (OOD) ...
read it

Benchmarking BonusBased Exploration Methods on the Arcade Learning Environment
This paper provides an empirical evaluation of recently developed explor...
read it

Adversarial Computation of Optimal Transport Maps
Computing optimal transport maps between highdimensional and continuous...
read it

Investigating Biases in Textual Entailment Datasets
The ability to understand logical relationships between sentences is an ...
read it

Stochastic Neural Network with Kronecker Flow
Recent advances in variational inference enable the modelling of highly ...
read it

Note on the bias and variance of variational inference
In this note, we study the relationship between the variational gap and ...
read it

Batch weight for domain adaptation with mass shift
Unsupervised domain transfer is the task of transferring or translating ...
read it

Hierarchical Importance Weighted Autoencoders
Importance weighted variational inference (Burda et al., 2015) uses mult...
read it

Improved Conditional VRNNs for Video Prediction
Predicting future frames for a video sequence is a challenging generativ...
read it

Counterpoint by Convolution
Machine learning models of music typically break up the task of composit...
read it

Maximum Entropy Generators for EnergyBased Models
Unsupervised learning is about capturing dependencies between variables ...
read it

Deep Generative Modeling of LiDAR Data
Building models capable of generating structured output is a key challen...
read it

Systematic Generalization: What Is Required and Can It Be Learned?
Numerous models for grounded language understanding have been recently p...
read it

Planning in Dynamic Environments with Conditional Autoregressive Models
We demonstrate the use of conditional autoregressive generative models (...
read it

Harmonic Recomposition using Conditional Autoregressive Modeling
We demonstrate a conditional autoregressive pipeline for efficient music...
read it

Representation Mixing for TTS Synthesis
Recent character and phonemebased parametric TTS systems using deep lea...
read it

Blindfold Baselines for Embodied QA
We explore blindfold (questiononly) baselines for Embodied Question Ans...
read it

Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks
Recurrent neural network (RNN) models are widely used for processing seq...
read it

On the Learning Dynamics of Deep Neural Networks
While a lot of progress has been made in recent years, the dynamics of l...
read it

Improving Explorability in Variational Inference with Annealed Variational Objectives
Despite the advances in the representational capacity of approximate dis...
read it

Approximate Exploration through State Abstraction
Although exploration in reinforcement learning is well understood from a...
read it