Jan Leike
Artificial Intelligence · arXiv.org · 2015–2025
A researcher in the Science corpus: 23 papers; trusts 786 researchers and is trusted by 356 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 807 citations into it; #1,843 of 36,961 by trust here, #270 by citations
- Reinforcement Learning — 297 citations into it; #469 of 2,250 by trust here, #193 by citations
- Natural Language Processing — 222 citations into it; #4,845 of 5,725 by trust here, #1,869 by citations
- Computer Vision and Pattern Recognition — 194 citations into it; #21,025 of 21,973 by trust here, #1,188 by citations
- Safety, Robustness & Interpretability — 163 citations into it; #1,851 of 2,259 by trust here, #1,111 by citations
- Management Science and Operations Research — 93 citations into it; #6,641 of 12,201 by trust here, #4,790 by citations
- Evaluation & Benchmarks — 89 citations into it
- Control and Systems Engineering — 71 citations into it; #2,574 of 8,519 by trust here, #144 by citations
Whom Jan Leike trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Richard S. Sutton
- Diederik P. Kingma
- Geoffrey E. Hinton
- Andrew Y. Ng
- Alex Graves
- Yoshua Bengio
- Ronald J. Williams
- Alex Krizhevsky
- Yann LeCun
- Ilya Sutskever
Who trusts Jan Leike overall
- Tom Everitt
- Jeff Wu
- David Krueger
- Victoria Krakovna
- Richard Ngo
- Long Ouyang
- Leo Gao
- Iason Gabriel
- Daniel S. Brown
- Sergey Levine
Papers from Jan Leike's perspective
Ordered by how strongly the researchers Jan Leike 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)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Learning Multiple Layers of Features from Tiny Images
Their papers
- Training language models to follow instructions with human feedback (2022) — 22,660 citations
- Evaluating Large Language Models Trained on Code (2021) — 10,663 citations
- Deep Reinforcement Learning from Human Preferences (2017) — 5,646 citations
- GPT-4 Technical Report (2023) — 26,133 citations
- Recursively Summarizing Books with Human Feedback (2021) — 371 citations
- Learning to Understand Goal Specifications by Modelling Reward (2018) — 167 citations
- Reward learning from human preferences and demonstrations in Atari (2018) — 490 citations
- Self-critiquing models for assisting human evaluators (2022) — 423 citations
- Scalable agent alignment via reward modeling: a research direction (2018) — 615 citations
- AI Safety Gridworlds (2017) — 298 citations
- Thompson Sampling is Asymptotically Optimal in General Environments (2016) — 40 citations
- Learning to Follow Language Instructions with Adversarial Reward Induction (2018) — 33 citations
- Let's Verify Step by Step (2023) — 3,887 citations
- Hidden Incentives for Auto-Induced Distributional Shift (2020) — 57 citations
- Reasoning Models Don't Always Say What They Think (2025) — 366 citations
- Bad Universal Priors and Notions of Optimality (2015) — 45 citations
- A Formal Solution to the Grain of Truth Problem (2016) — 18 citations
- Active Reinforcement Learning: Observing Rewards at a Cost (2020) — 41 citations
- Scaling and evaluating sparse autoencoders (2024) — 535 citations
- GPT-4o System Card (2024) — 4,622 citations