Marius Mosbach

Artificial Intelligence · with Klakow · 2018–2020

A researcher in the Science corpus: 4 papers; trusts 89 researchers and is trusted by 11 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 92 citations into it; #26,372 of 35,345 by trust here, #19,873 by citations
• Safety, Robustness & Interpretability — 42 citations into it
• Computer Vision and Pattern Recognition — 37 citations into it
• Optimization & Training — 22 citations into it; #1,444 of 2,601 by trust here, #1,385 by citations
• Natural Language Processing — 20 citations into it
• Model Architectures — 17 citations into it
• Evaluation & Benchmarks — 11 citations into it
• Large Language Models — 10 citations into it; #323 of 799 by trust here, #564 by citations

Whom Marius Mosbach trusts overall

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

1. Kaiming He
2. Alex Krizhevsky
3. Yoshua Bengio
4. Geoffrey E. Hinton
5. Diederik P. Kingma
6. Yann LeCun
7. Ilya Sutskever
8. Christian Szegedy
9. Ian J. Goodfellow
10. X. Zhang

Who trusts Marius Mosbach overall

1. Francesco Croce
2. Steven Bethard
3. Sven Gowal
4. Sylvestre-Alvise Rebuffi
5. Clara Vania
6. Katikapalli Subramanyam Kalyan
7. William Huang
8. Eric Wallace
9. Matthias Hein
10. Maksym Andriushchenko

Papers from Marius Mosbach's perspective

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

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

Their papers

• Logit Pairing Methods Can Fool Gradient-Based Attacks (2018) — 87 citations
• On the security relevance of weights in deep learning. (2020)
• On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines (2020) — 475 citations
• Adversarial Initialization - when your network performs the way I want (2019) — 8 citations