Saurav Kadavath

Artificial Intelligence · 2019–2023

A researcher in the Science corpus: 11 papers; trusts 167 researchers and is trusted by 16 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 382 citations into it; #12,081 of 35,345 by trust here, #953 by citations
• Safety, Robustness & Interpretability — 150 citations into it
• Computer Vision and Pattern Recognition — 126 citations into it
• Evaluation & Benchmarks — 87 citations into it
• Information Systems — 44 citations into it
• Representation & Self-Supervised Learning — 23 citations into it; #1,549 of 3,145 by trust here, #1,479 by citations
• Model Architectures — 16 citations into it
• Optimization & Training — 13 citations into it

Whom Saurav Kadavath trusts overall

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

1. Dan Hendrycks
2. Geoffrey E. Hinton
3. Kaiming He
4. Alex Krizhevsky
5. Ilya Sutskever
6. Diederik P. Kingma
7. Yoshua Bengio
8. Yann LeCun
9. Ross B. Girshick
10. Christian Szegedy

Who trusts Saurav Kadavath overall

1. Dan Hendrycks
2. Zhihong Shao
3. Richard Ngo
4. Lorenz Kuhn
5. Mahmoud Assran
6. Xinyun Chen
7. Sebastian Farquhar
8. Zhibin Gou
9. Zhiqing Sun
10. Yu Sun

Papers from Saurav Kadavath's perspective

Ordered by how strongly the researchers Saurav Kadavath 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. Attention is All you Need (Neural Information Processing Systems)
4. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
5. Long Short-Term Memory
6. ImageNet: A large-scale hierarchical image database
7. Gradient-based learning applied to document recognition
8. ImageNet Large Scale Visual Recognition Challenge
9. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
10. Learning Multiple Layers of Features from Tiny Images

Their papers

• The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization (2020) — 2,442 citations
• Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback (2022) — 4,254 citations
• Measuring Mathematical Problem Solving With the MATH Dataset (2021) — 5,902 citations
• Constitutional AI: Harmlessness from AI Feedback (2022) — 3,377 citations
• Measuring Coding Challenge Competence With APPS (2021) — 1,191 citations
• Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty (2019) — 1,072 citations
• Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned (2022) — 837 citations
• Language Models (Mostly) Know What They Know (2022) — 1,782 citations
• Discovering Language Model Behaviors with Model-Written Evaluations (2022) — 917 citations
• The Capacity for Moral Self-Correction in Large Language Models (2023) — 214 citations
• Measuring Faithfulness in Chain-of-Thought Reasoning (2023) — 499 citations