arXiv AI
GuardianBench: A Same-Scene Instruction-Contrastive Benchmark for Latent Contextual Risk in Embodied AI
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 17
SafeRelBench: A Spatial-Relation-Aware Benchmark for Process-Level Safety in VLM-Driven Embodied Agents
arXiv:2607. 14543v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly used as the reasoning backbone of embodied agents, enabling robots to interpret visual scenes, follow language instructions, and plan multi-step actions.
arXiv AI
Jul 2
EgoSafetyBench: A Diagnostic Egocentric Video Benchmark for Evaluating Embodied VLMs as Runtime Safety Guards
arXiv:2607. 00218v1 Announce Type: cross Abstract: Vision-language models (VLMs) are now proposed as runtime safety guards for embodied agents in homes and factories.
arXiv AI
Sep 30
ThinkingGuard: Decoding Implicit Hazards via Step-by-Step Risk Attribution in Multimodal Large Language Models
arXiv:2609.36562v1 Announce Type: cross Abstract: While Multimodal Large Language Models (MLLMs) are increasingly deployed in safety-critical domains, their reliability is threatened by multimodal im...
arXiv Machine Learning
Sep 22
Seeing Through Conflicts: Improving Instruction Hierarchy Alignment in Vision-Language Models
arXiv:2609.22234v1 Announce Type: cross Abstract: Instruction hierarchy (IH) alignment teaches language models to prioritize higher-level instructions when inputs conflict. While studied primarily in...
Hugging Face Trending Papers
Aug 19
When Safety Overrides Vision: Exploring Dynamics between Vision Influence and Safety Alignment in Vision-Language Models
Aligned vision‑language models (VLMs) are designed to combine grounded visual reasoning with safe generation. The study finds that when safety constraints are applied, these models often abstain from answering questions that they could answer under default instruction, yet visual evidence continues to influence the decoding process. The authors show that safety‑induced abstention alters late‑stage hidden‑state dynamics, and that targeted interventions can restore grounded answering without retraining or changing visual inputs.
arXiv AI
Sep 17
Visual Compliance via Executable Safety Rule Entailment
GuardEn is an executable safeguard framework that transforms complex safety policies into atomic propositions via Safety‑Rule Compilation and models their composition as executable code. At inference, Scene‑Grounded Execution uses visual scene graphs to instantiate these propositions, allowing rule‑grounded and interpretable safety reasoning. Experiments on SafetyVisionBench show GuardEn improves F1 by an average of 9.8 points over the strongest baseline.