Michael Lee — accepted AI-conference papers

2026

Critique-Guided Distillation for Robust Reasoning via Refinement

Berkcan Kapusuzoglu, Supriyo Chakraborty, Zain Sarwar, Michael Lee, Sambit Sahu

ICML 2026poster

Supervised fine-tuning with expert demonstrations often produces models that imitate outputs without internalizing the reasoning processes needed for robust generalization. While critique-based approaches show promise, training models to generate critiques directly, such as Critique Fine-Tuning (CFT…

Cited by 0 Source ↗Scholar ↗

2022

Adversarially trained neural representations are already as robust as biological neural representations

Chong Guo, Michael Lee, Guillaume Leclerc, Joel Dapello, Yug Rao, Aleksander Madry +1

ICML 2022oral

Visual systems of primates are the gold standard of robust perception. There is thus a general belief that mimicking the neural representations that underlie those systems will yield artificial visual systems that are adversarially robust. In this work, we develop a method for performing adversarial…

Cited by 30 Source ↗PDF ↗Scholar ↗