EMBGuard introduces an MLLM-based guardrail that evaluates action-conditioned physical risks on a new 15.1K-pair dataset and 329-scenario benchmark, matching proprietary models at lower false-positive rates with 2B/4B parameter versions.
arXiv preprint arXiv:2509.23614 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LiSA improves AI guardrails lifelong by inducing conservative policies from sparse noisy failure reports via structured memory, conflict-aware rules, and posterior lower-bound gating.
citing papers explorer
-
EMBGuard: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents
EMBGuard introduces an MLLM-based guardrail that evaluates action-conditioned physical risks on a new 15.1K-pair dataset and 329-scenario benchmark, matching proprietary models at lower false-positive rates with 2B/4B parameter versions.
-
LiSA: Lifelong Safety Adaptation via Conservative Policy Induction
LiSA improves AI guardrails lifelong by inducing conservative policies from sparse noisy failure reports via structured memory, conflict-aware rules, and posterior lower-bound gating.