Jacob Pfau

Artificial Intelligence · 2021–2023

A researcher in the Science corpus: 2 papers; trusts 1 researcher and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 124 citations into it
• Safety, Robustness & Interpretability — 43 citations into it

Whom Jacob Pfau trusts overall

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

1. Joseph B. Kruskal
2. Martín Arjovsky

Papers from Jacob Pfau's perspective

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

1. Intriguing properties of neural networks
2. ImageNet classification with deep convolutional neural networks
3. Explaining and Harnessing Adversarial Examples
4. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
5. Proximal Policy Optimization Algorithms (arXiv.org)
6. Gradient-based learning applied to document recognition
7. Long Short-Term Memory
8. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
9. Unbiased look at dataset bias
10. Attention is All you Need (Neural Information Processing Systems)

Their papers

• Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback (2023) — 934 citations
• Objective Robustness in Deep Reinforcement Learning (2021) — 16 citations