Nika Haghtalab

Artificial Intelligence · 2023

A researcher in the Science corpus: 1 paper; trusts 6 researchers and is trusted by 15 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 23 citations into it; #13,603 of 35,345 by trust here, #11,072 by citations
• Safety, Robustness & Interpretability — 14 citations into it
• Large Language Models — 12 citations into it
• Alignment & RLHF — 9 citations into it

Whom Nika Haghtalab trusts overall

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

1. Irene Solaiman
2. Nisan Stiennon
3. Paul Christiano
4. Yuntao Bai
5. Long Ouyang
6. Daniel M. Ziegler
7. Samuel Gehman
8. Omar Shaikh
9. Jeff Wu
10. Jing Xu

Who trusts Nika Haghtalab overall

1. Xiangyu Qi
2. Zeming Wei
3. Badhan Chandra Das
4. Stav Cohen
5. Erfan Shayegani
6. Zheng-Xin Yong
7. Jiahao Yu
8. Melanie Sclar
9. Xinyue Shen
10. Federico Bianchi

Papers from Nika Haghtalab's perspective

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

1. Attention is All you Need (Neural Information Processing Systems)
2. ImageNet classification with deep convolutional neural networks
3. Language Models are Few-Shot Learners (Neural Information Processing Systems)
4. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
5. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
6. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
7. Long Short-Term Memory
8. Language Models are Unsupervised Multitask Learners
9. ImageNet: A large-scale hierarchical image database
10. Gradient-based learning applied to document recognition

Their papers

• Jailbroken: How Does LLM Safety Training Fail? (2023) — 2,019 citations