conftrace_

Yuhao Mao

5 papers · 2023–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze

Venues

ICLR (2) ICML (2) NeurIPS (1)

Top co-authors

Martin Vechev (5) Mark Niklas Mueller (3) Marc Fischer (2) Stefan Balauca (1) Maximilian Baader (1) Chenhao Sun (1) Mark Müller (1)

Research topics

Machine Learning (4) Optimization & Theory · Machine Learning (3) Artificial Intelligence (2) Deep Learning (2) Core AI (2) Architectures (1) Learning Types (1) Optimization & Theory · Deep Learning (1)

Keywords

certified robustness (3) interval bound propagation (2) neural network verification (2) convex relaxation (1) piecewise linear (1) adversarial attack (1) randomized smoothing (1) relu network (1) robustness verification (1) noisy data (1) training schedule (1) global optimum (1) neural network (1) certified accuracy (1) robust neural network (1) certified training (1) algorithmic improvement (1) certification method (1) average certified radius (1) training certifiably robust (1)

Papers

Average Certified Radius is a Poor Metric for Randomized Smoothing ICML 2025 CTBench: A Library and Benchmark for Certified Training ICML 2025 Expressivity of ReLU-Networks under Convex Relaxations ICLR 2024 Understanding Certified Training with Interval Bound Propagation ICLR 2024 Connecting Certified and Adversarial Training NeurIPS 2023