HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task
Vision-Language Models (VLMs) empower embodied agents to execute complex instructions, yet they remain vulnerable to contextual safety risks where benign commands become hazardous due to subtle environmental states. Existing safeguards often prove inadequate. Rule-based methods lack scalability in object-dense scenes, whereas model-based approaches relying on prompt engineering suffer from unfocused perception, resulting in missed risks or hallucinations. To address this, we propose an architecture-agnostic safeguard featuring Context-Guided Chain-of-Thought (CG-CoT). This mechanism decomposes risk assessment into active perception that sequentially anchors attention to interaction target...
| Authors | Xiaoya Lu, Yijin Zhou, Zeren Chen et al. |
|---|---|
| Primary category | cs.CV |
| Published | 15 March 2026 |
| Last updated at source | 15 March 2026 |
Connected in the knowledge graph
- Ursulalala/HomeSafeDataset · cited by
Models and datasets referencing this paper
- Ursulalala/HomeSafeDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.