Will Grathwohl

Artificial Intelligence · 2016–2022

A researcher in the Science corpus: 11 papers; trusts 480 researchers and is trusted by 82 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 195 citations into it; #5,254 of 35,345 by trust here, #3,907 by citations
• Computer Vision and Pattern Recognition — 164 citations into it; #4,080 of 21,575 by trust here, #3,875 by citations
• Generative Models — 127 citations into it; #376 of 1,956 by trust here, #473 by citations
• Probabilistic & Bayesian Methods — 78 citations into it; #1,137 of 1,525 by trust here, #485 by citations
• Signal Processing — 40 citations into it
• Natural Language Processing — 37 citations into it
• Statistical and Nonlinear Physics — 36 citations into it; #1,668 of 10,127 by trust here, #651 by citations
• Safety, Robustness & Interpretability — 33 citations into it

Whom Will Grathwohl trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Diederik P. Kingma
2. Geoffrey E. Hinton
3. Max Welling
4. Yoshua Bengio
5. Alex Krizhevsky
6. Yann LeCun
7. Jimmy Ba
8. Ilya Sutskever
9. Radford M. Neal
10. Ronald J. Williams

Who trusts Will Grathwohl overall

1. Arash Vahdat
2. Yang Song
3. Yilun Du
4. David Kristjanson Duvenaud
5. Michael S. Albergo
6. Geoffrey E. Hinton
7. Yuxi Li
8. Yoshua Bengio
9. Jörn-Henrik Jacobsen
10. Erik Nijkamp

Papers from Will Grathwohl's perspective

Ordered by how strongly the researchers Will Grathwohl trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Attention is All you Need (Neural Information Processing Systems)
5. Long Short-Term Memory
6. Gradient-based learning applied to document recognition
7. ImageNet: A large-scale hierarchical image database
8. Learning Multiple Layers of Features from Tiny Images
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models (2018) — 1,080 citations
• Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One (2019) — 664 citations
• Backpropagation through the Void: Optimizing control variates for black-box gradient estimation (2017) — 317 citations
• Disentangling Space and Time in Video with Hierarchical Variational Auto-encoders (2016) — 22 citations
• Understanding the Limitations of Conditional Generative Models (2019) — 65 citations
• Self-conditioned Embedding Diffusion for Text Generation (2022) — 134 citations
• Continuous diffusion for categorical data (2022) — 209 citations
• Precision medicine as a control problem: Using simulation and deep reinforcement learning to discover adaptive, personalized multi-cytokine therapy for sepsis (2018) — 27 citations
• Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling (2020) — 100 citations
• Scalable Reversible Generative Models with Free-form Continuous Dynamics (2018)
• Gradient-based Optimization of Neural Network Architecture (2018) — 12 citations