Zi-Mei Yao
Artificial Intelligence · 2017–2024
A researcher in the Science corpus: 20 papers; trusts 1,107 researchers and is trusted by 40 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 691 citations into it; #4,369 of 35,345 by trust here, #2,166 by citations
- Computer Vision and Pattern Recognition — 575 citations into it; #3,906 of 21,575 by trust here, #1,687 by citations
- Efficiency & Compression — 376 citations into it; #182 of 1,264 by trust here, #160 by citations
- Optimization & Training — 166 citations into it; #1,717 of 2,601 by trust here, #1,216 by citations
- Model Architectures — 158 citations into it
- Natural Language Processing — 143 citations into it
- Large Language Models — 130 citations into it
- Evaluation & Benchmarks — 64 citations into it; #2,485 of 3,147 by trust here, #2,133 by citations
Whom Zi-Mei Yao trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Geoffrey E. Hinton
- Yoshua Bengio
- Alex Krizhevsky
- Yann LeCun
- Diederik P. Kingma
- Ilya Sutskever
- Christian Szegedy
- L. Eon Bottou
- James Martens
Who trusts Zi-Mei Yao overall
- A. Gholami
- Sehoon Kim
- Elias Frantar
- Zhen Dong
- Michael W. Mahoney
- Kurt Keutzer
- Sheng Shen
- Dan Alistarh
- Tim Dettmers
- Coleman Hooper
Papers from Zi-Mei Yao's perspective
Ordered by how strongly the researchers Zi-Mei Yao trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- How Much Can CLIP Benefit Vision-and-Language Tasks? (2021) — 516 citations
- Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT (2019) — 675 citations
- Hessian-based Analysis of Large Batch Training and Robustness to Adversaries (2018) — 194 citations
- DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale (2022) — 591 citations
- ZeroQ: A Novel Zero Shot Quantization Framework (2020) — 496 citations
- ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers (2022) — 759 citations
- Loss Functions for Multiset Prediction (2017) — 22 citations
- HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-Precision (2019) — 686 citations
- On the Computational Inefficiency of Large Batch Sizes for Stochastic Gradient Descent (2018) — 82 citations
- PyHessian: Neural Networks Through the Lens of the Hessian (2019) — 401 citations
- I-BERT: Integer-only BERT Quantization (2021) — 459 citations
- A Survey of Quantization Methods for Efficient Neural Network Inference (2021) — 1,633 citations
- HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks (2019) — 394 citations
- Extreme Compression for Pre-trained Transformers Made Simple and Efficient (2022) — 31 citations
- ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning (2020) — 383 citations
- AI and Memory Wall (2024) — 374 citations
- MLPruning: A Multilevel Structured Pruning Framework for Transformer-based Models (2021) — 14 citations
- HAWQV3: Dyadic Neural Network Quantization (2020) — 93 citations
- PowerNorm: Rethinking Batch Normalization in Transformers (2020) — 90 citations
- A Statistical Framework for Low-bitwidth Training of Deep Neural Networks (2020) — 73 citations