← Search

Joseph James Vincent

1 accepted papers

2026

DynaGuard: A Dynamic Guardian Model With User-Defined Policies

ICLR 2026poster

Guardian models play a crucial role in ensuring the safety and ethical behavior of user-facing AI applications by enforcing guardrails and detecting harmful content. While standard guardian models are limited to predefined, static harm categories, we introduce DynaGuard, a suite of dynamic guardian…

Cited by 0SourcecodeScholar