8.9M views · 56K reactions | The magic behind product photoshoot. By Steve Giralt Visual Engineering | 9GAG | Facebook

High-capacity vision-language models (VLMs) are trained on large web datasets, enabling them to effectively recognize visual and language patterns and function across multiple languages. However, for robots to reach a similar level of proficiency, they would need to gather firsthand data across various objects, environments, tasks, and situations. In this context, researchers have introduced Robotic Transformer 2 (RT-2), a vision-language-action (VLA) model that learns from both web and robotics

895 reactions · 39 shares | Gary Harmer, Commercial Director at Hikvision UK & Ireland, participated in an ISJ interview discussing AI's role in modern physical security. Highlighting the use of LLMs and large vision models in Hikvision's AcuSeek NVRs, he explained they power efficient, intuitive video searches with natural language queries. ️烙#Hikvision #AI | Hikvision | Facebook