Weizhe Hua

Principal Researcher, Microsoft AI

Joined

September 2019

Names

Weizhe Hua (Preferred)

Emails

****@cornell.edu (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Homepage

Google Scholar

Career & Education History

Principal Researcher

Microsoft AI (microsoft.com)

2025 – Present

Senior Research Scientist

Google Deepmind (google.com)

2022 – 2024

PhD student

Cornell University (cornell.edu)

2016 – 2022

Advisors, Relations & Conflicts

Coauthor

Chris De Sa

2018 – 2022

PhD Advisor

Edward Suh

2016 – 2022

Coauthor

Zhiru Zhang

2016 – 2022

Expertise

deep learning

2018 – 2022

pruning

2018 – 2022

quantization

2018 – 2022

Publications

Structured Pruning of CNNs at Initialization
Yaohui Cai, Weizhe Hua, Hongzheng Chen, G. Edward Suh, Christopher De Sa, Zhiru Zhang
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Structured Pruning of CNNs at Initialization
Yaohui Cai, Weizhe Hua, Hongzheng Chen, Fengyu Li, G. Edward Suh, Christopher De Sa, Zhiru Zhang
- Published: 01 Feb 2023, Last Modified: 13 Feb 2023
- Submitted to ICLR 2023
- Readers: Everyone
Transformer Quality in Linear Time
Weizhe Hua, Zihang Dai, Hanxiao Liu, Quoc V Le
- 01 Apr 2022
- OpenReview Archive Direct Upload
- Readers: Everyone
BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining
Weizhe Hua, Yichi Zhang, Chuan Guo, Zhiru Zhang, G. Edward Suh
- Published: 09 Nov 2021, Last Modified: 05 May 2023
- NeurIPS 2021 Poster
- Readers: Everyone
MgX: Near-Zero Overhead Memory Protection with an Application to Secure DNN Acceleration
Weizhe Hua, Muhammad Umar, Zhiru Zhang, G. Edward Suh
- 2020 (modified: 15 May 2025)
- CoRR 2020
- Readers: Everyone
Boosting the Performance of CNN Accelerators with Dynamic Fine-Grained Channel Gating
Weizhe Hua, Yuan Zhou, Christopher De Sa, Zhiru Zhang, G. Edward Suh
- 2019 (modified: 15 May 2025)
- MICRO 2019
- Readers: Everyone
Reverse engineering convolutional neural networks through side-channel information leaks
Weizhe Hua, Zhiru Zhang, G. Edward Suh
- 2018 (modified: 15 May 2025)
- DAC 2018
- Readers: Everyone

Weizhe Hua

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Structured Pruning of CNNs at Initialization

Structured Pruning of CNNs at Initialization

Transformer Quality in Linear Time

BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining

MgX: Near-Zero Overhead Memory Protection with an Application to Secure DNN Acceleration

Boosting the Performance of CNN Accelerators with Dynamic Fine-Grained Channel Gating

Reverse engineering convolutional neural networks through side-channel information leaks

Co-Authors