Aaquib Syed

Artificial Intelligence · 2024

A researcher in the Science corpus: 1 paper; trusts 1 researcher and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 37 citations into it

Whom Aaquib Syed trusts overall

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

1. Andy Zou

Papers from Aaquib Syed's perspective

Ordered by how strongly the researchers Aaquib Syed trusts endorse each paper. Same corpus, a different order for every researcher.

1. Attention is All you Need (Neural Information Processing Systems)
2. Measuring Massive Multitask Language Understanding
3. Linguistic Regularities in Continuous Space Word Representations
4. Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback (arXiv.org)
5. Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
6. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
7. ImageNet classification with deep convolutional neural networks
8. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
9. Jailbroken: How Does LLM Safety Training Fail? (Neural Information Processing Systems)
10. HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal (International Conference on Machine Learning)

Their papers

• Refusal in Language Models Is Mediated by a Single Direction (2024) — 866 citations