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.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
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.
Existing video benchmarks evaluate action recognition on consumer videos, egocentric recordings, or simulated industrial environments. They do not test vision-language models under the visual and procedural conditions of real industrial CCTV, where workers appear as distant figures amid dust, steam, low light, glare, occlusion, and overlapping activities.
Large vision-language models (LVLMs) have recently shown immense potential in automated content moderation, sparking growing interest in developing harmful-video benchmarks. However, we identify two primary limitations in existing works: 1) The multi-layered characteristics of harmful videos are overlooked.
arXiv:2606. 05177v1 Announce Type: cross Abstract: Existing multimodal safety benchmarks focus solely on visual inputs and cannot assess Omni Large Language Models (LLMs) that process vision, audio, and text.
arXiv:2603. 29759v2 Announce Type: replace-cross Abstract: Recent advances in vision-language models (VLMs) have accelerated their application to indoor safety hazards assessment.
arXiv:2607. 18325v1 Announce Type: cross Abstract: Modern safety-critical systems increasingly rely on human-robot interaction to reduce disaster risk and support decision-making during emergencies.