Paul Christiano
Artificial Intelligence · 2010–2024
A researcher in the Science corpus: 16 papers; trusts 580 researchers and is trusted by 1,017 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 446 citations into it; #1,047 of 36,961 by trust here, #310 by citations
- Natural Language Processing — 177 citations into it; #3,339 of 5,725 by trust here, #912 by citations
- Reinforcement Learning — 154 citations into it; #516 of 2,250 by trust here, #216 by citations
- Computer Vision and Pattern Recognition — 125 citations into it; #7,550 of 21,973 by trust here, #8,281 by citations
- Management Science and Operations Research — 46 citations into it; #6,172 of 12,201 by trust here, #2,826 by citations
- Large Language Models — 41 citations into it; #300 of 810 by trust here, #95 by citations
- Control and Systems Engineering — 39 citations into it; #1,883 of 8,519 by trust here, #127 by citations
- Optimization & Training — 25 citations into it
Whom Paul Christiano trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Alex Krizhevsky
- Yoshua Bengio
- Diederik P. Kingma
- Andrew Y. Ng
- Ilya Sutskever
- Pieter Abbeel
- Yann LeCun
- Sergey Levine
- Richard S. Sutton
Who trusts Paul Christiano overall
- Sergey Levine
- Tom Everitt
- Jan Leike
- Richard Ngo
- Jeff Wu
- Yilun Du
- Daniel S. Brown
- Pieter Abbeel
- Iason Gabriel
- Youliang Yuan
Papers from Paul Christiano's perspective
Ordered by how strongly the researchers Paul Christiano trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
Their papers
- Training language models to follow instructions with human feedback (2022) — 22,660 citations
- Deep Reinforcement Learning from Human Preferences (2017) — 5,646 citations
- Concrete Problems in AI Safety (2016) — 3,295 citations
- Learning to summarize from human feedback (2020) — 3,335 citations
- Theano: A Python framework for fast computation of mathematical expressions (2016) — 2,380 citations
- Fine-Tuning Language Models from Human Preferences (2019) — 2,638 citations
- A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models (2016) — 382 citations
- Recursively Summarizing Books with Human Feedback (2021) — 371 citations
- Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model (2016) — 270 citations
- AI safety via debate (2018) — 428 citations
- Supervising strong learners by amplifying weak experts (2018) — 178 citations
- Unrestricted Adversarial Examples (2018) — 108 citations
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training (2024) — 489 citations
- Robust Cooperation in the Prisoner's Dilemma: Program Equilibrium via Provability Logic (2014) — 30 citations
- Electrical flows, laplacian systems, and faster approximation of maximum flow in undirected graphs (2010) — 372 citations
- Learning to summarize with human feedback (2020) — 121 citations