Mary Phuong

Publications by Year

Research Areas

Adversarial Robustness in Machine Learning, Software Engineering Research, Neural Networks and Applications, Simulation Techniques and Applications, Model Reduction and Neural Networks

Most-Cited Works

• → Distillation-Based Training for Multi-Exit Architectures(2019)172 cited
• → Towards Understanding Knowledge Distillation(2021)133 cited
• → Model evaluation for extreme risks(2023)54 cited
• → Formal Algorithms for Transformers(2022)52 cited
• The Mutual Autoencoder: Controlling Information in Latent Code Representations(2018)
• → Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals(2022)14 cited
• Functional vs. parametric equivalence of ReLU networks(2020)
• → Evaluating Frontier Models for Dangerous Capabilities(2024)9 cited
• The inductive bias of ReLU networks on orthogonally separable data(2021)
• → Against the Flow of Time with Multi-Output Models(2023)2 cited