Andy Zou
Artificial Intelligence · 2020–2025
A researcher in the Science corpus: 10 papers; trusts 54 researchers and is trusted by 10 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 255 citations into it; #15,911 of 35,345 by trust here, #2,097 by citations
- Safety, Robustness & Interpretability — 84 citations into it
- Computer Vision and Pattern Recognition — 75 citations into it
- Reinforcement Learning — 22 citations into it
Whom Andy Zou trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Diederik P. Kingma
- Ian J. Goodfellow
- Alex Krizhevsky
- Kaiming He
- Yoshua Bengio
- Dan Hendrycks
- Christian Szegedy
- Yann LeCun
- Ilya Sutskever
Who trusts Andy Zou overall
- Andy Arditi
- Xiangyu Qi
- Gabriel Alon
- Zeming Wei
- Alexander Robey
- Xiaogeng Liu
- Zheng-Xin Yong
- Qiusi Zhan
- Melanie Sclar
- Jiahao Yu
Papers from Andy Zou's perspective
Ordered by how strongly the researchers Andy Zou 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
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
Their papers
- Measuring Massive Multitask Language Understanding (2020) — 8,927 citations
- Scaling Out-of-Distribution Detection for Real-World Settings (2022) — 690 citations
- Universal and Transferable Adversarial Attacks on Aligned Language Models (2023) — 3,387 citations
- What Would Jiminy Cricket Do? Towards Agents That Behave Morally (2021) — 76 citations
- Representation Engineering: A Top-Down Approach to AI Transparency (2023) — 1,173 citations
- A benchmark of expert-level academic questions to assess AI capabilities (2025) — 349 citations
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal (2024) — 1,335 citations
- The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning (2024) — 473 citations
- Improving Alignment and Robustness with Circuit Breakers (2024) — 311 citations
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2022) — 2,561 citations