Alexander Wei
Artificial Intelligence · 2022–2023
A researcher in the Science corpus: 2 papers; trusts 6 researchers and is trusted by 15 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 50 citations into it; #13,601 of 35,345 by trust here, #9,465 by citations
- Safety, Robustness & Interpretability — 19 citations into it
- Large Language Models — 18 citations into it
- Alignment & RLHF — 9 citations into it
Whom Alexander Wei trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Irene Solaiman
- Nisan Stiennon
- Paul Christiano
- Yuntao Bai
- Long Ouyang
- Daniel M. Ziegler
- Samuel Gehman
- Omar Shaikh
- Jeff Wu
- Jing Xu
Who trusts Alexander Wei overall
- Xiangyu Qi
- Zeming Wei
- Badhan Chandra Das
- Stav Cohen
- Erfan Shayegani
- Zheng-Xin Yong
- Jiahao Yu
- Melanie Sclar
- Xinyue Shen
- Federico Bianchi
Papers from Alexander Wei's perspective
Ordered by how strongly the researchers Alexander Wei trusts endorse each paper. Same corpus, a different order for every researcher.
- Attention is All you Need (Neural Information Processing Systems)
- 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)
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Long Short-Term Memory
- Language Models are Few-Shot Learners (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Language Models are Unsupervised Multitask Learners
- Gradient-based learning applied to document recognition
Their papers
- Jailbroken: How Does LLM Safety Training Fail? (2023) — 2,019 citations
- Human-level play in the game of Diplomacy by combining language models with strategic reasoning (2022) — 592 citations