Aran Komatsuzaki

Artificial Intelligence · 2019–2022

A researcher in the Science corpus: 3 papers; trusts 97 researchers and is trusted by 7 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 61 citations into it; #17,180 of 35,345 by trust here, #5,458 by citations
• Computer Vision and Pattern Recognition — 43 citations into it; #10,860 of 21,575 by trust here, #4,067 by citations
• Large Language Models — 24 citations into it
• Efficiency & Compression — 18 citations into it
• Model Architectures — 15 citations into it
• Scaling & Learning Theory — 10 citations into it
• Natural Language Processing — 9 citations into it
• Evaluation & Benchmarks — 6 citations into it; #3,074 of 3,147 by trust here, #888 by citations

Whom Aran Komatsuzaki trusts overall

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

1. Noam Shazeer
2. Geoffrey E. Hinton
3. Jacob Devlin
4. Alex Krizhevsky
5. Yann LeCun
6. Yoshua Bengio
7. Ilya Sutskever
8. Kaiming He
9. Diederik P. Kingma
10. Ashish Vaswani

Who trusts Aran Komatsuzaki overall

1. Fabio Massimo Zanzotto
2. T. Henighan
3. Andrea Santilli
4. Jared Kaplan
5. J. Ainslie
6. Leonardo Ranaldi
7. Jared Kaplan
8. Niklas Muennighoff

Papers from Aran Komatsuzaki's perspective

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

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

Their papers

• LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs (2021) — 1,887 citations
• One Epoch Is All You Need (2019) — 64 citations
• Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints (2022) — 215 citations