arXiv CS AI
techLean Right
Distilling Vision-Language Models for On-Device Fire Understandingtranslating…
arXiv:2609.05782v1 Announce Type: new
Abstract: Vision-language models (VLMs) offer a promising alternative to conventional fire detection systems by reasoning about the semantic context of a scene and thus reducing false alarms, yet their large model size makes deployment on…
Keywords#Vision-Language Models#Fire#Distilling#Distilling Vision-Language#Distilling Vision-Language Models