Paulius Micikevicius

Artificial Intelligence · 2009–2022

A researcher in the Science corpus: 9 papers; trusts 176 researchers and is trusted by 20 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 159 citations into it; #26,802 of 35,345 by trust here, #8,007 by citations
• Computer Vision and Pattern Recognition — 140 citations into it; #12,085 of 21,575 by trust here, #2,410 by citations
• Natural Language Processing — 54 citations into it
• Model Architectures — 47 citations into it
• Optimization & Training — 26 citations into it; #2,082 of 2,601 by trust here, #378 by citations
• Evaluation & Benchmarks — 22 citations into it

Whom Paulius Micikevicius trusts overall

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

1. Kaiming He
2. Christian Szegedy
3. Alex Krizhevsky
4. Geoffrey E. Hinton
5. Yoshua Bengio
6. Sergey Ioffe
7. Ilya Sutskever
8. Karen Simonyan
9. Alex Graves
10. Shaoqing Ren

Who trusts Paulius Micikevicius overall

1. David S. Lawrie
2. Tim Dettmers
3. Boris Ginsburg
4. Dimitri Komatitsch
5. Raul Puri
6. Luke S. Zettlemoyer
7. Stanislav Beliaev
8. Oleksii Kuchaiev
9. Anthony D. Nguyen
10. Yuan Tang

Papers from Paulius Micikevicius's perspective

Ordered by how strongly the researchers Paulius Micikevicius 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. Long Short-Term Memory
4. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
5. Attention is All you Need (Neural Information Processing Systems)
6. ImageNet: A large-scale hierarchical image database
7. Gradient-based learning applied to document recognition
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. Going deeper with convolutions
10. ImageNet Large Scale Visual Recognition Challenge

Their papers

• Mixed Precision Training (2017) — 2,457 citations
• OpenSeq2Seq: Extensible Toolkit for Distributed and Mixed Precision Training of Sequence-to-Sequence Models (2018) — 33 citations
• MLPerf Training Benchmark (2019) — 388 citations
• Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation (2020) — 488 citations
• Mixed-Precision Training for NLP and Speech Recognition with OpenSeq2Seq (2018) — 52 citations
• FP8 Formats for Deep Learning (2022) — 285 citations
• MLPerf: An Industry Standard Benchmark Suite for Machine Learning Performance (2020) — 194 citations
• Accelerating Sparse Deep Neural Networks (2021) — 344 citations
• 3D finite difference computation on GPUs using CUDA (2009) — 611 citations