arXiv AI October 27, 2026 By Vy Vo, Dinh Phung

Beyond Behaviour: A Stimulus-Response Safety Evaluation of Vision-Language-Action Models

The paper titled "Beyond Behaviour: A Stimulus-Response Safety Evaluation of Vision-Language-Action Models" examines how vision-language-action models respond to safety-critical stimuli. By testing three models on two video benchmarks, the authors analyze internal representations and action tendencies when faced with visible hazards and harmful outcomes. The results indicate that these models tend to continue task execution even after internally registering danger.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Oct 8

It Is Not Seeing the Hazard: A Frozen Vision-Language Safety Score Measures Its Caption Bank

arXiv:2610.09517v1 Announce Type: cross Abstract: Frozen vision-language models increasingly provide safety signals for reinforcement learning. Their use assumes that similarity to language describin...

By Samuel Tetteh, Cody Fleming

llms rag reinforcement-learning multimodal benchmarks safety

arXiv AI

Aug 25

EviSafe: Evidence-Grounded Safety Evaluation for Vision-Language Models

arXiv:2608.23313v1 Announce Type: new Abstract: Vision-language model safety benchmarks typically evaluate only final responses: whether a model refuses, warns, or complies. This outcome-level view c...

By Xuetong Li, Gaofeng Liu

llms multimodal benchmarks safety

arXiv AI

Oct 7

From Local Evidence to Safety Verdicts: Causal Tracing in Vision-Language Models

arXiv:2610.07514v1 Announce Type: new Abstract: A vision-language model may need to combine an image with a prompt to recognize a safety risk that neither reveals alone. Where does this joint safety...

By Faezeh Dehghan Tarzjani, Mevan Wijewardena, Alexander Romanus, Sampad Mohanty

llms multimodal safety

arXiv AI

Jun 26

The Inattentional Gap: Task-Conditioned Language and Vision Models Omit the Safety-Critical Signals They Can Otherwise Report

arXiv:2606. 26529v1 Announce Type: cross Abstract: AI safety is evaluated by how reliably a model detects the hazards it is told to find, yet accidents often arise from the hazard no one specified.

By Kwan Soo Shin

benchmarks safety

arXiv AI

Jun 2

PaSBench-Video: A Streaming Video Benchmark for Proactive Safety Warning

arXiv:2606. 02443v1 Announce Type: cross Abstract: Between the first visible sign of danger and the moment an accident occurs, there is often a window where intervention remains possible.

By Yusong Zhao, Yuejin Xie, Youliang Yuan, Junjie Hu, Jitian Guo, Yujiu Yang, Pinjia He

llms multimodal benchmarks safety

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.

By Siddhant Panpatil, Arth Singh, Mijin Koo, Chaeyun Kim, Haon Park, Dasol Choi

llms agents robotics multimodal benchmarks safety

One email a morning, machine-written

Related stories

It Is Not Seeing the Hazard: A Frozen Vision-Language Safety Score Measures Its Caption Bank

EviSafe: Evidence-Grounded Safety Evaluation for Vision-Language Models

From Local Evidence to Safety Verdicts: Causal Tracing in Vision-Language Models

The Inattentional Gap: Task-Conditioned Language and Vision Models Omit the Safety-Critical Signals They Can Otherwise Report

PaSBench-Video: A Streaming Video Benchmark for Proactive Safety Warning

EgoSafetyBench: A Diagnostic Egocentric Video Benchmark for Evaluating Embodied VLMs as Runtime Safety Guards