Kelvin Xu

Publications21
h-index10
Citations9,501
Highly Influential Citations927
Claim Author Page
Author pages are created from data sourced from our academic publisher partnerships and public sources.

Recommended Authors

  • Sergey Levine
  • 310 Publications • 32,115 Citations
  • P. Abbeel
  • 452 Publications • 46,199 Citations
  • Yoshua Bengio
  • 811 Publications • 257,906 Citations
  • K. Kavukcuoglu
  • 89 Publications • 64,789 Citations
  • Publications
  • Influence
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
TLDR
We introduce an attention based model that automatically learns to describe the content of images. Expand
  • 5,962
  • 571
  • PDF
Theano: A Python framework for fast computation of mathematical expressions
TLDR
Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Expand
  • 1,930
  • 144
  • PDF
An Actor-Critic Algorithm for Sequence Prediction
TLDR
We present an approach to training neural networks to generate sequences using actor-critic methods from reinforcement learning (RL). Expand
  • 398
  • 60
  • PDF
On Using Monolingual Corpora in Neural Machine Translation
TLDR
In this work, we investigate how to leverage abundant monolingual corpora for neural machine translation. Expand
  • 340
  • 40
  • PDF
Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
TLDR
We propose Meta-Dataset: a new benchmark for training and evaluating models that is large-scale, consists of diverse datasets, and presents more realistic tasks. Expand
  • 161
  • 36
  • PDF
Probabilistic Model-Agnostic Meta-Learning
TLDR
We extend model-agnostic meta-learning, which adapts to new tasks via gradient descent, to incorporate a parameter distribution that is trained via a variational lower bound. Expand
  • 255
  • 30
  • PDF
Bridging the Gap Between Value and Policy Based Reinforcement Learning
TLDR
We establish a new connection between value and policy based reinforcement learning (RL) based on a relationship between softmax temporal value consistency and policy optimality under entropy regularization. Expand
  • 215
  • 22
  • PDF
Trust-PCL: An Off-Policy Trust Region Method for Continuous Control
Trust region methods, such as TRPO, are often used to stabilize policy optimization algorithms in reinforcement learning (RL). While current trust region strategies are effective for continuous… Expand
  • 60
  • 10
  • PDF
On integrating a language model into neural machine translation
TLDR
We combine scores from neural language model trained only on target monolingual data with neural machine translation model and fusing hidden-states of these two models. Expand
  • 66
  • 8
Unsupervised Perceptual Rewards for Imitation Learning
TLDR
We present a method that is able to identify key intermediate steps of a task from only a handful of demonstration sequences, and automatically identify the most discriminative features for identifying these steps. Expand
  • 78
  • 5
  • PDF
...
1
2
3
...