Zhewei Yao

34 papers receiving 1.3k citations

Hit Papers

Q-BERT: Hessian Based Ultra Low Precision Quantization of...20202026202220242020202450100150200

Peers

Zhewei Yao
Comparison fields: 5 of 104
  • Artificial Intelligence 777
  • Computer Vision and Pattern Recognition 613
  • Electrical and Electronic Engineering 198
  • Computational Mechanics 145
  • Statistical and Nonlinear Physics 120
Replace Zhi Yang with:
Zhi Yang China
Michaël Mathieu United States
Amir Gholami United States
Dmitry Vetrov Russia
Rohan Varma United States
Ri‐Gui Zhou China
Olivier Delalleau Canada
Srinadh Bhojanapalli United States
Levent Sagun United States
Zhewei Yao relative to Zhi Yang China Zhi Yang's profile →
Citations per field
00.5×1.6×
Zhi Yang · 1×
Citations per year

Countries citing papers authored by Zhewei Yao

Since Specialization
Citations

This map shows the geographic impact of Zhewei Yao's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Zhewei Yao with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Zhewei Yao more than expected).

Fields of papers citing papers by Zhewei Yao

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Zhewei Yao. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Zhewei Yao. The network helps show where Zhewei Yao may publish in the future.

Co-authorship network of co-authors of Zhewei Yao

This figure shows the co-authorship network connecting the top 25 collaborators of Zhewei Yao. A scholar is included among the top collaborators of Zhewei Yao based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Zhewei Yao. Zhewei Yao is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

20 of 20 papers shown
#WorkIndexed citations
1 0
2 0
3
AI and Memory Wallbreakdown →
79
4 7
5 11
6 23
7 3
8
Efficient Second-Order Methods for Non-Convex Optimization and Machine Learning
1
9
HAWQ-V3: Dyadic Neural Network Quantization
30
10
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
3
11 88
12
Benchmarking Semi-supervised Federated Learning
13
13 195
14 65
15
ANODEV2: A Coupled Neural ODE Framework
12
16 224
17
Hessian-based Analysis of Large Batch Training and Robustness to Adversaries
8
18 8
19 15
20 4

About Zhewei Yao

Zhewei Yao is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence and Statistics, Probability and Uncertainty, having authored 37 papers that have together received 1.4k indexed citations. Recurring topics across this work include Advanced Neural Network Applications (12 papers), Domain Adaptation and Few-Shot Learning (7 papers) and Stochastic Gradient Optimization Techniques (5 papers). The work is most often cited by research in Computer Vision and Pattern Recognition (613 citations), Artificial Intelligence (777 citations) and Computational Mathematics (12 citations). Zhewei Yao has collaborated with scholars based in United States, China and Australia. Frequent co-authors include Michael W. Mahoney, Kurt Keutzer, Amir Gholami, Zhen Dong, Sheng Shen, Yaohui Cai, Jiayu Ye, Linjian Ma, Zhen Dong and Steven L. Brunton. Their work appears in journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence, Journal of Computational Physics and Tribology International.

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact

Rankless by CCL
2026