Jacob Steinhardt
Artificial Intelligence · 2011–2023
A researcher in the Science corpus: 38 papers; trusts 1,974 researchers and is trusted by 1,043 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,047 citations into it; #1,016 of 36,961 by trust here, #438 by citations
- Safety, Robustness & Interpretability — 411 citations into it; #61 of 2,259 by trust here, #31 by citations
- Computer Vision and Pattern Recognition — 339 citations into it; #3,969 of 21,973 by trust here, #2,427 by citations
- Natural Language Processing — 159 citations into it
- Evaluation & Benchmarks — 128 citations into it; #2,295 of 3,155 by trust here, #173 by citations
- Signal Processing — 117 citations into it; #3,478 of 7,592 by trust here, #520 by citations
- Statistics and Probability — 117 citations into it; #3,731 of 13,188 by trust here, #4,277 by citations
- Computer Networks and Communications — 111 citations into it; #4,772 of 9,996 by trust here, #1,295 by citations
Whom Jacob Steinhardt trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Alex Krizhevsky
- John C. Duchi
- Yoshua Bengio
- Diederik P. Kingma
- Kaiming He
- Ian J. Goodfellow
- Yann LeCun
- Ilya Sutskever
- Christian Szegedy
Who trusts Jacob Steinhardt overall
- Ilias Diakonikolas
- Vitaly Feldman
- Dan Hendrycks
- Pang Wei Koh
- Gregory Valiant
- Lili Su
- Dong Yin
- Jerry Zheng Li
- Percy Liang
- Michela Meister
Papers from Jacob Steinhardt's perspective
Ordered by how strongly the researchers Jacob Steinhardt trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- 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
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Measuring Massive Multitask Language Understanding (2020) — 8,927 citations
- Concrete Problems in AI Safety (2016) — 3,295 citations
- The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization (2020) — 2,442 citations
- Natural Adversarial Examples (2019) — 1,984 citations
- Measuring Mathematical Problem Solving With the MATH Dataset (2021) — 5,902 citations
- Measuring Coding Challenge Competence With APPS (2021) — 1,191 citations
- Certified Defenses against Adversarial Examples (2018) — 1,019 citations
- Aligning AI With Shared Human Values (2020) — 970 citations
- Unsolved Problems in ML Safety (2021) — 390 citations
- Scaling Out-of-Distribution Detection for Real-World Settings (2022) — 690 citations
- Identifying Statistical Bias in Dataset Replication (2020) — 55 citations
- Certified Defenses for Data Poisoning Attacks (2017) — 884 citations
- The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation (2018) — 923 citations
- Testing Robustness Against Unforeseen Adversaries (2019) — 144 citations
- Troubling Trends in Machine Learning Scholarship (2018) — 367 citations
- Learning from untrusted data (2016) — 320 citations
- Transfer of Adversarial Robustness Between Perturbation Types (2019) — 53 citations
- Semidefinite relaxations for certifying robustness to adversarial examples (2018) — 461 citations
- Discovering Latent Knowledge in Language Models Without Supervision (2022) — 771 citations
- Jailbroken: How Does LLM Safety Training Fail? (2023) — 2,019 citations