Cliff Young

Artificial Intelligence · 2004–2025

A researcher in the Science corpus: 15 papers; trusts 94 researchers and is trusted by 9 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 170 citations into it; #23,976 of 35,345 by trust here, #768 by citations
• Computer Vision and Pattern Recognition — 168 citations into it; #11,162 of 21,575 by trust here, #537 by citations
• Hardware and Architecture — 80 citations into it; #996 of 1,551 by trust here, #41 by citations
• Efficiency & Compression — 65 citations into it; #859 of 1,264 by trust here, #340 by citations
• Model Architectures — 55 citations into it
• Natural Language Processing — 46 citations into it; #5,549 of 5,688 by trust here, #224 by citations
• Optimization & Training — 46 citations into it
• Computational Theory and Mathematics — 13 citations into it

Whom Cliff Young trusts overall

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

1. Kaiming He
2. Yann LeCun
3. Geoffrey E. Hinton
4. Alex Krizhevsky
5. Sergey Ioffe
6. Ashish Vaswani
7. Diederik P. Kingma
8. Yoshua Bengio
9. Christian Szegedy
10. Ilya Sutskever

Who trusts Cliff Young overall

1. Yi Tay
2. Alexander Kolesnikov
3. N. Jouppi
4. Dustin Tran
5. Rohit Prabhavalkar
6. Barret Zoph
7. Haichuan Yang
8. Lucas Beyer
9. Gaurav Menghani

Papers from Cliff Young's perspective

Ordered by how strongly the researchers Cliff Young 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. Long Short-Term Memory
5. ImageNet: A large-scale hierarchical image database
6. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
7. Going deeper with convolutions
8. Gradient-based learning applied to document recognition
9. ImageNet Large Scale Visual Recognition Challenge
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation (2016) — 7,325 citations
• A domain-specific supercomputer for training deep neural networks (2020) — 294 citations
• Mesh-TensorFlow: Deep Learning for Supercomputers (2018) — 439 citations
• Ten Lessons From Three Generations Shaped Google’s TPUv4i : Industrial Product (2021) — 445 citations
• MLPerf Training Benchmark (2019) — 388 citations
• Sparse GPU Kernels for Deep Learning (2020) — 296 citations
• In-datacenter performance analysis of a tensor processing unit (2017) — 5,323 citations
• MegaBlocks: Efficient Sparse Training with Mixture-of-Experts (2022) — 234 citations
• Anton, a special-purpose machine for molecular dynamics simulation (2008) — 583 citations
• Anton 2: Raising the Bar for Performance and Programmability in a Special-Purpose Molecular Dynamics Supercomputer (2014) — 529 citations
• Anton, a special-purpose machine for molecular dynamics simulation (2007) — 489 citations
• Planaria: Dynamic Architecture Fission for Spatial Multi-Tenant Acceleration of Deep Neural Networks (2020) — 143 citations
• Neuromorphic computing at scale (2025) — 324 citations
• TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings (2023) — 685 citations
• Embedded Computing: A VLIW Approach to Architecture, Compilers and Tools (2004) — 316 citations