Dylan Hadfield-Menell

Artificial Intelligence · 2016–2023

A researcher in the Science corpus: 10 papers; trusts 142 researchers and is trusted by 27 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 192 citations into it; #6,728 of 35,345 by trust here, #5,084 by citations
• Safety, Robustness & Interpretability — 82 citations into it; #1,533 of 2,251 by trust here, #1,454 by citations
• Reinforcement Learning — 71 citations into it; #749 of 2,242 by trust here, #574 by citations
• Computer Vision and Pattern Recognition — 55 citations into it
• Alignment & RLHF — 42 citations into it; #54 of 62 by trust here, #58 by citations
• Safety Research — 24 citations into it
• Control and Systems Engineering — 17 citations into it
• Economics and Econometrics — 11 citations into it; #19,942 of 23,481 by trust here, #15,581 by citations

Whom Dylan Hadfield-Menell trusts overall

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

1. Pieter Abbeel
2. Andrew Y. Ng
3. Diederik P. Kingma
4. Geoffrey E. Hinton
5. Stuart J. Russell
6. Alex Krizhevsky
7. Brian D. Ziebart
8. Yoshua Bengio
9. Ian J. Goodfellow
10. Kaiming He

Who trusts Dylan Hadfield-Menell overall

1. Tom Everitt
2. Victoria Krakovna
3. Daniel S. Brown
4. Jan Leike
5. Stuart Armstrong
6. Smitha Milli
7. Anca Dragan
8. Simon Zhuang
9. Peter Eckersley
10. Laurent Orseau

Papers from Dylan Hadfield-Menell's perspective

Ordered by how strongly the researchers Dylan Hadfield-Menell 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. Long Short-Term Memory
5. Gradient-based learning applied to document recognition
6. Attention is All you Need (Neural Information Processing Systems)
7. ImageNet: A large-scale hierarchical image database
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. Learning Multiple Layers of Features from Tiny Images
10. ImageNet Large Scale Visual Recognition Challenge

Their papers

• Cooperative Inverse Reinforcement Learning (2016) — 776 citations
• Inverse Reward Design (2017) — 495 citations
• Pragmatic-Pedagogic Value Alignment (2017) — 92 citations
• Should Robots be Obedient? (2017) — 70 citations
• On the Geometry of Adversarial Examples (2018) — 88 citations
• Consequences of Misaligned AI (2021) — 109 citations
• The Off-Switch Game (2016) — 206 citations
• Incomplete Contracting and AI Alignment (2018) — 123 citations
• Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback (2023) — 934 citations
• Robust Feature-Level Adversaries are Interpretability Tools (2021) — 34 citations