| GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. | 0 | 0.34 | 2022 |
| Zero-Shot Text-to-Image Generation | 0 | 0.34 | 2021 |
| Deep Double Descent: Where Bigger Models and More Data Hurt. | 0 | 0.34 | 2020 |
| Generative Pretraining From Pixels | 0 | 0.34 | 2020 |
| Distribution Augmentation for Generative Modeling. | 0 | 0.34 | 2020 |
| Deep double descent: where bigger models and more data hurt* | 2 | 0.64 | 2020 |
| Language Models are Few-Shot Learners | 2 | 0.36 | 2020 |
| GamePad: A Learning Environment for Theorem Proving. | 0 | 0.34 | 2019 |
| FFJORD: Free-Form Continuous Dynamics for Scalable Reversible Generative Models. | 0 | 0.34 | 2019 |
| Generating Long Sequences with Sparse Transformers | 13 | 0.65 | 2019 |
| Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments. | 0 | 0.34 | 2018 |
| FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models. | 11 | 0.53 | 2018 |
| Synthesizing Robust Adversarial Examples. | 76 | 2.30 | 2018 |
| GamePad: A Learning Environment for Theorem Proving. | 4 | 0.38 | 2018 |
| Emergent Complexity via Multi-Agent Competition. | 0 | 0.34 | 2018 |
| The Importance of Sampling inMeta-Reinforcement Learning. | 0 | 0.34 | 2018 |
| Some Considerations on Learning to Explore via Meta-Reinforcement Learning. | 6 | 0.44 | 2018 |
| Emergent Complexity via Multi-Agent Competition. | 22 | 0.74 | 2017 |
| Variational Lossy Autoencoder. | 0 | 0.34 | 2017 |
| Third Person Imitation Learning. | 0 | 0.34 | 2017 |
| One-Shot Imitation Learning. | 0 | 0.34 | 2017 |
| Learning to Generate Reviews and Discovering Sentiment. | 49 | 1.33 | 2017 |
| Variational Lossy Autoencoder. | 0 | 0.34 | 2017 |
| Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments. | 26 | 0.73 | 2017 |
| An online sequence-to-sequence model for noisy speech recognition. | 1 | 0.37 | 2017 |
| Third Person Imitation Learning | 19 | 0.78 | 2017 |
| Evolution Strategies as a Scalable Alternative to Reinforcement Learning. | 105 | 3.04 | 2017 |
| Continuous Deep Q-Learning with Model-based Acceleration. | 70 | 2.15 | 2016 |
| RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning. | 0 | 0.34 | 2016 |
| TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. | 743 | 29.70 | 2016 |
| MuProp: Unbiased Backpropagation for Stochastic Neural Networks | 0 | 0.34 | 2016 |
| Neural Random-Access Machines | 0 | 0.34 | 2016 |
| An Online Sequence-to-Sequence Model Using Partial Conditioning. | 0 | 0.34 | 2016 |
| Extensions and Limitations of the Neural GPU. | 0 | 0.34 | 2016 |
| Improving Variational Autoencoders with Inverse Autoregressive Flow. | 0 | 0.34 | 2016 |
| Neural Programmer: Inducing Latent Programs with Gradient Descent | 0 | 0.34 | 2016 |
| InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets. | 321 | 8.31 | 2016 |
| Mastering the game of Go with deep neural networks and tree search. | 1643 | 63.63 | 2016 |
| Multi-task Sequence to Sequence Learning | 0 | 0.34 | 2016 |
| Neural GPUs Learn Algorithms | 1 | 0.35 | 2016 |
| Neural Programmer: Inducing Latent Programs with Gradient Descent | 68 | 2.34 | 2015 |
| Move Evaluation in Go Using Deep Convolutional Neural Networks | 0 | 0.34 | 2015 |
| An Empirical Exploration of Recurrent Network Architectures | 225 | 8.29 | 2015 |
| Multi-task Sequence to Sequence Learning | 117 | 3.21 | 2015 |
| Addressing The Rare Word Problem In Neural Machine Translation | 162 | 9.92 | 2015 |
| MuProp: Unbiased Backpropagation for Stochastic Neural Networks. | 21 | 0.87 | 2015 |
| Reinforcement Learning Neural Turing Machines | 33 | 2.08 | 2015 |
| Adding Gradient Noise Improves Learning for Very Deep Networks. | 56 | 2.61 | 2015 |
| Towards Principled Unsupervised Learning | 9 | 2.36 | 2015 |
| Neural GPUs Learn Algorithms | 3 | 0.39 | 2015 |
