
-
Cross-Modal Contrastive Learning for Text-to-Image Generation
The output of text-to-image synthesis systems should be coherent, clear,...
read it
-
Evolving Reinforcement Learning Algorithms
We propose a method for meta-learning reinforcement learning algorithms ...
read it
-
Few-shot Sequence Learning with Transformers
Few-shot algorithms aim at learning new tasks provided only a handful of...
read it
-
Text-to-Image Generation Grounded by Fine-Grained User Attention
Localized Narratives is a dataset with detailed natural language descrip...
read it
-
What's in a Loss Function for Image Classification?
It is common to use the softmax cross-entropy loss to train neural netwo...
read it
-
Reinforcement Learning for Sparse-Reward Object-Interaction Tasks in First-person Simulated 3D Environments
First-person object-interaction tasks in high-fidelity, 3D, simulated en...
read it
-
Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning
Sample efficiency has been one of the major challenges for deep reinforc...
read it
-
i-Mix: A Strategy for Regularizing Contrastive Representation Learning
Contrastive representation learning has shown to be an effective way of ...
read it
-
Text as Neural Operator: Image Manipulation by Text Instruction
In this paper, we study a new task that allows users to edit an input im...
read it
-
Predictive Information Accelerates Learning in RL
The Predictive Information is the mutual information between the past an...
read it
-
An Ode to an ODE
We present a new paradigm for Neural ODE algorithms, calledODEtoODE, whe...
read it
-
CompressNet: Generative Compression at Extremely Low Bitrates
Compressing images at extremely low bitrates (< 0.1 bpp) has always been...
read it
-
Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning
Model-based reinforcement learning (RL) enjoys several benefits, such as...
read it
-
Time Dependence in Non-Autonomous Neural ODEs
Neural Ordinary Differential Equations (ODEs) are elegant reinterpretati...
read it
-
Improved Consistency Regularization for GANs
Recent work has increased the performance of Generative Adversarial Netw...
read it
-
BRPO: Batch Residual Policy Optimization
In batch reinforcement learning (RL), one often constrains a learned pol...
read it
-
High-Fidelity Synthesis with Disentangled Representation
Learning disentangled representation of data without supervision is an i...
read it
-
Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies
We propose and address a novel few-shot RL problem, where a task is char...
read it
-
Efficient Adversarial Training with Transferable Adversarial Examples
Adversarial training is an effective defense method to protect classific...
read it
-
How Should an Agent Practice?
We present a method for learning intrinsic reward functions to drive the...
read it
-
High Fidelity Video Prediction with Large Stochastic Recurrent Neural Networks
Predicting future video frames is extremely challenging, as there are ma...
read it
-
Consistency Regularization for Generative Adversarial Networks
Generative Adversarial Networks (GANs) are known to be difficult to trai...
read it
-
A Simple Randomization Technique for Generalization in Deep Reinforcement Learning
Deep reinforcement learning (RL) agents often fail to generalize to unse...
read it
-
IEG: Robust Neural Network Training to Tackle Severe Label Noise
Collecting large-scale data with clean labels for supervised training of...
read it
-
Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?
Hierarchical reinforcement learning has demonstrated significant success...
read it
-
Efficient Exploration with Self-Imitation Learning via Trajectory-Conditioned Policy
This paper proposes a method for learning a trajectory-conditioned polic...
read it
-
Data-Efficient Learning for Sim-to-Real Robotic Grasping using Deep Point Cloud Prediction Networks
Training a deep network policy for robot manipulation is notoriously cos...
read it
-
SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing
Deep neural networks (DNNs) have achieved great success in various appli...
read it
-
Unsupervised Learning of Object Structure and Dynamics from Videos
Extracting and predicting object structure and dynamics from videos with...
read it
-
Zero-Shot Entity Linking by Reading Entity Descriptions
We present the zero-shot entity linking task, where mentions must be lin...
read it
-
Similarity of Neural Network Representations Revisited
Recent work has sought to understand the behavior of neural networks by ...
read it
-
Incremental Learning with Unlabeled Data in the Wild
Deep neural networks are known to suffer from catastrophic forgetting in...
read it
-
Robust Inference via Generative Classifiers for Handling Noisy Labels
Large-scale datasets may contain significant proportions of noisy (incor...
read it
-
Diversity-Sensitive Conditional Generative Adversarial Networks
We propose a simple yet highly effective method that addresses the mode-...
read it
-
Generative Adversarial Self-Imitation Learning
This paper explores a simple regularizer for reinforcement learning by p...
read it
-
Learning Latent Dynamics for Planning from Pixels
Planning has been very successful for control tasks with known environme...
read it
-
Contingency-Aware Exploration in Reinforcement Learning
This paper investigates whether learning contingency-awareness and contr...
read it
-
Content preserving text generation with attribute controls
In this work, we address the problem of modifying textual attributes of ...
read it
-
Near-Optimal Representation Learning for Hierarchical Reinforcement Learning
We study the problem of representation learning in goal-conditioned hier...
read it
-
Learning Hierarchical Semantic Image Manipulation through Structured Representations
Understanding, reasoning, and manipulating semantic concepts of images h...
read it
-
MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics
Long-term human motion can be represented as a series of motion modes---...
read it
-
Multitask Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies
We introduce a new RL problem where the agent is required to execute a g...
read it
-
A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
Detecting test samples drawn sufficiently far away from the training dis...
read it
-
Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion
Integrating model-free and model-based approaches in reinforcement learn...
read it
-
Self-Imitation Learning
This paper proposes Self-Imitation Learning (SIL), a simple off-policy a...
read it
-
Hierarchical Long-term Video Prediction without Supervision
Much of recent research has been devoted to video prediction and generat...
read it
-
Data-Efficient Hierarchical Reinforcement Learning
Hierarchical reinforcement learning (HRL) is a promising approach to ext...
read it
-
Neural Kinematic Networks for Unsupervised Motion Retargetting
We propose a recurrent neural network architecture with a Forward Kinema...
read it
-
Unsupervised Discovery of Object Landmarks as Structural Representations
Deep neural networks can model images with rich latent representations, ...
read it
-
Hierarchical Novelty Detection for Visual Object Recognition
Deep neural networks have achieved impressive success in large-scale vis...
read it