Owain Evans

Artificial Intelligence · 2009–2023

A researcher in the Science corpus: 14 papers; trusts 127 researchers and is trusted by 29 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 212 citations into it; #6,828 of 35,345 by trust here, #2,880 by citations
• Reinforcement Learning — 77 citations into it; #822 of 2,242 by trust here, #1,084 by citations
• Natural Language Processing — 69 citations into it
• Safety, Robustness & Interpretability — 61 citations into it; #1,326 of 2,251 by trust here, #570 by citations
• Computer Vision and Pattern Recognition — 51 citations into it
• Large Language Models — 41 citations into it; #297 of 799 by trust here, #204 by citations
• Evaluation & Benchmarks — 33 citations into it; #1,633 of 3,147 by trust here, #312 by citations
• Management Science and Operations Research — 28 citations into it; #3,267 of 11,946 by trust here, #2,185 by citations

Whom Owain Evans trusts overall

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

1. Andrew Y. Ng
2. Geoffrey E. Hinton
3. Richard S. Sutton
4. Yoshua Bengio
5. Diederik P. Kingma
6. Arthur Guez
7. Alex Krizhevsky
8. Yann LeCun
9. Ilya Sutskever
10. Alex Graves

Who trusts Owain Evans overall

1. Tom Everitt
2. Jan Leike
3. David Krueger
4. Stuart Armstrong
5. Collin Burns
6. Sebastian Schulze
7. Neil C. Rabinowitz
8. Zhibin Gou
9. Sören Mindermann
10. Gary Lea

Papers from Owain Evans's perspective

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

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
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. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
9. Learning Multiple Layers of Features from Tiny Images
10. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)

Their papers

• TruthfulQA: Measuring How Models Mimic Human Falsehoods (2021) — 3,631 citations
• Truthful AI: Developing and governing AI that does not lie (2021) — 155 citations
• The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation (2018) — 923 citations
• Trial without Error: Towards Safe Reinforcement Learning via Human Intervention (2017) — 277 citations
• Teaching Models to Express Their Uncertainty in Words (2022) — 778 citations
• Learning the Preferences of Ignorant, Inconsistent Agents (2015) — 138 citations
• Agent-Agnostic Human-in-the-Loop Reinforcement Learning (2017) — 66 citations
• Active Reinforcement Learning with Monte-Carlo Tree Search (2018) — 20 citations
• When Will AI Exceed Human Performance? Evidence from AI Experts (2017) — 703 citations
• Active Reinforcement Learning: Observing Rewards at a Cost (2020) — 41 citations
• The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" (2023) — 511 citations
• Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2022) — 2,561 citations
• FHI Oxford Technical Report # 2018-2 Predicting Human Deliberative Judgments with Machine Learning (2018)
• Help or Hinder: Bayesian Models of Social Goal Inference (2009) — 214 citations