About me
I am Yuhao Mao, a PhD student at the Secure, Reliable, and Intelligent Systems Lab of ETH Zürich, advised by Prof. Martin Vechev, since September 2023. For latest information, please visit my personal website.
Education
- ETH Zurich, 2021 - 2023
- Zhejiang University, 2017 - 2021
M. Sc. Computer Science
B. Sc. Mathematics and Applied Mathematics, B. Sc. Finance
Work Experience
- Higgs Asset, Hangzhou, March 2021 - July 2021
Internship in Quant Research
Publications
2025
CTBENCH: A Library and Benchmark for Certified Training
Yuhao Mao, Stefan Balauca, Martin Vechev
ICML
2025
Average Certified Radius is a Poor Metric for Randomized Smoothing
Chenhao Sun*, Yuhao Mao*, Mark Niklas Müller, Martin Vechev
ICML
2025
* Equal contribution
Gaussian Loss Smoothing Enables Certified Training with Tight Convex Relaxations
Stefan Balauca, Mark Niklas Müller, Yuhao Mao, Maximilian Baader, Marc Fischer, Martin Vechev
TMLR
2025
2024
Understanding Certified Training with Interval Bound Propagation
Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin Vechev
ICLR
2024
Expressivity of ReLU-Networks under Convex Relaxations
Maximilian Baader*, Mark Niklas Müller*, Yuhao Mao, Martin Vechev
ICLR
2024
* Equal contribution
2023
Connecting Certified and Adversarial Training
Yuhao Mao, Mark Niklas Müller, Marc Fischer, Martin Vechev
NeuIPS
2023