Nina Rimsky

Artificial Intelligence · 2023–2024

A researcher in the Science corpus: 3 papers; trusts 1 researcher and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 80 citations into it

Whom Nina Rimsky trusts overall

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

1. Stephanie C. Lin
2. Andy Zou
3. Samyam Rajbhandari
4. Daniel M. Ziegler
5. Jason Wei
6. Alec Radford
7. Adam Paszke
8. Fabian Pedregosa
9. Geoffrey E. Hinton
10. Jacob Hilton

Papers from Nina Rimsky's perspective

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

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

Their papers

• Refusal in Language Models Is Mediated by a Single Direction (2024) — 866 citations
• Many-shot Jailbreaking (2024) — 300 citations
• Steering Llama 2 via Contrastive Activation Addition (2023) — 889 citations