Skip to content
conftrace_
2025 ICML ICML 2025

ROME is Forged in Adversity: Robust Distilled Datasets via Information Bottleneck

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Zheng Zhou, Wenquan Feng, Qiaosheng Zhang, Shuchang Lyu, Qi Zhao, Guangliang Cheng

Topics

Artificial Intelligence > Core AI > AI Safety Machine Learning > Core Methods > Representation Learning

Keywords

adversarial robustness information bottleneck feature distribution dataset distillation synthetic dataset improved robustness ratio
Download PDF