| Understanding the Variance Collapse of SVGD in High Dimensions | 0 | 0.34 | 2022 |
| LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning | 0 | 0.34 | 2021 |
| Planning from Pixels using Inverse Dynamics Models | 0 | 0.34 | 2021 |
| When Does Preconditioning Help or Hurt Generalization? | 0 | 0.34 | 2021 |
| INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving | 0 | 0.34 | 2021 |
| How does a Neural Network's Architecture Impact its Robustness to Noisy Labels? | 0 | 0.34 | 2021 |
| Clockwork Variational Autoencoders. | 0 | 0.34 | 2021 |
| Mastering Atari with Discrete World Models | 0 | 0.34 | 2021 |
| Efficient Statistical Tests: A Neural Tangent Kernel Approach | 0 | 0.34 | 2021 |
| Learning Domain Invariant Representations in Goal-conditioned Block MDPs. | 0 | 0.34 | 2021 |
| Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning | 0 | 0.34 | 2020 |
| BatchEnsemble: an Alternative Approach to Efficient Ensemble and Lifelong Learning | 0 | 0.34 | 2020 |
| Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint | 0 | 0.34 | 2020 |
| Learning Intrinsic Rewards as a Bi-Level Optimization Problem. | 0 | 0.34 | 2020 |
| On Solving Minimax Optimization Locally: A Follow-the-Ridge Approach | 0 | 0.34 | 2020 |
| An Inductive Bias for Distances: Neural Nets that Respect the Triangle Inequality | 0 | 0.34 | 2020 |
| Dream to Control: Learning Behaviors by Latent Imagination | 0 | 0.34 | 2020 |
| An Empirical Study of Stochastic Gradient Descent with Structured Covariance Noise. | 0 | 0.34 | 2020 |
| Improving Transformer Optimization Through Better Initialization | 0 | 0.34 | 2020 |
| Neural Graph Evolution: Towards Efficient Automatic Robot Design. | 0 | 0.34 | 2019 |
| Graph Normalizing Flows. | 0 | 0.34 | 2019 |
| ACTRCE: Augmenting Experience via Teacher's Advice For Multi-Goal Reinforcement Learning. | 0 | 0.34 | 2019 |
| DOM-Q-NET: Grounded RL on Structured Language. | 0 | 0.34 | 2019 |
| Interplay Between Optimization and Generalization of Stochastic Gradient Descent with Covariance Noise. | 1 | 0.34 | 2019 |
| Exploring Model-based Planning with Policy Networks. | 1 | 0.35 | 2019 |
| On the Convergence and Robustness of Training GANs with Regularized Optimal Transport. | 4 | 0.41 | 2018 |
| Reversible Recurrent Neural Networks. | 2 | 0.37 | 2018 |
| Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches. | 4 | 0.39 | 2018 |
| Kronecker-factored Curvature Approximations for Recurrent Neural Networks | 6 | 0.44 | 2018 |
| NerveNet: Learning Structured Policy with Graph Neural Networks | 13 | 0.50 | 2018 |
| Solving Approximate Wasserstein GANs to Stationarity. | 1 | 0.35 | 2018 |
| Distributed Second-Order Optimization using Kronecker-Factored Approximations | 10 | 0.56 | 2017 |
| Second-order Optimization for Deep Reinforcement Learning using Kronecker-factored Approximation. | 1 | 0.38 | 2017 |
| Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation. | 43 | 1.43 | 2017 |
| Layer Normalization. | 0 | 0.34 | 2016 |
| Classifying and segmenting microscopy images with deep multiple instance learning. | 20 | 0.87 | 2016 |
| Classifying and Segmenting Microscopy Images Using Convolutional Multiple Instance Learning. | 27 | 0.97 | 2015 |
| Learning Wake-Sleep Recurrent Attention Models | 21 | 1.10 | 2015 |
| Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning | 63 | 2.09 | 2015 |
| "SQUEAKeys": A friction idiophone, for physical interaction with mobile devices | 1 | 0.36 | 2015 |
| Show, Attend and Tell: Neural Image Caption Generation with Visual Attention. | 1061 | 32.46 | 2015 |
| Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions | 75 | 2.01 | 2015 |
| Generating Images from Captions with Attention | 49 | 2.32 | 2015 |
| Multiple Object Recognition with Visual Attention. | 161 | 7.91 | 2014 |
| Adam: A Method for Stochastic Optimization. | 7040 | 220.14 | 2014 |
| Adaptive dropout for training deep neural networks. | 48 | 2.65 | 2013 |
| Do Deep Nets Really Need to be Deep? | 230 | 9.55 | 2013 |
| User-interfaces based on the water-hammer effect: water-hammer piano as an interactive percussion surface | 5 | 0.51 | 2011 |
