Marzena Karpinska

Artificial Intelligence · 2021–2023

A researcher in the Science corpus: 2 papers; trusts 69 researchers and is trusted by 5 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 80 citations into it; #21,375 of 35,345 by trust here, #17,776 by citations
• Natural Language Processing — 65 citations into it
• Computer Vision and Pattern Recognition — 29 citations into it
• Evaluation & Benchmarks — 24 citations into it; #1,925 of 3,147 by trust here, #2,590 by citations
• Large Language Models — 15 citations into it
• Safety, Robustness & Interpretability — 10 citations into it
• Sociology and Political Science — 5 citations into it
• Natural Language Generation — 5 citations into it

Whom Marzena Karpinska trusts overall

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

1. Angela Fan
2. Geoffrey E. Hinton
3. Yoshua Bengio
4. Alec Radford
5. Diederik P. Kingma
6. Ilya Sutskever
7. Alex Krizhevsky
8. Ari Holtzman
9. Yann LeCun
10. Kaiming He

Who trusts Marzena Karpinska overall

1. Cheng-Han Chiang
2. Maurice Jakesch
3. Kalpesh Krishna
4. Eric Wallace
5. Hung-yi Lee
6. Jeffrey T. Hancock
7. Adina Williams
8. Yapei Chang

Papers from Marzena Karpinska's perspective

Ordered by how strongly the researchers Marzena Karpinska 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. ImageNet classification with deep convolutional neural networks
4. Long Short-Term Memory
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. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
8. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
9. Gradient-based learning applied to document recognition
10. ImageNet: A large-scale hierarchical image database

Their papers

• The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation (2021) — 136 citations
• Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense (2023) — 572 citations