← Search

Xiaofei Zhao

1 accepted papers

2026

Composable Assurance for AI Alignment: A Framework for Propagating Formal Safety Properties Through MLOps

AAAI 2026technical

The increasing complexity of modern AI systems exposes a significant assurance gap: safety evidence from practices like red-teaming and robustness testing remains fragmented, lacking a formal mechanism for composition and propagation throughout the development lifecycle. This prevents the constructi

Cited by 0SourcePDFScholar