Jev Drives a Simulator in Real Time
The author connected Jev to the raw controls of a driving simulator and shows it driving in real time, emphasizing real-time response rather than frame-by-frame video generation.
Sparked by the JEV decision model, this post discusses AI autonomous judgment and timely reminders in the real world, and introduces VLX-Flow and VLX-Seek, two streaming video understanding and visual grounding models for embodied scenarios.
JEV 把 AI 决策模型带火了,但如果让 AI 在现实世界里自己判断、及时提醒,会怎么样? 查了一下发现 VLX-Flow 和 VLX-Seek 这两个面向具身场景的流式视频理解与视觉定位模型! 一个能持续理解视频里正在发生什么,一个能精准定位画面中的目标, 我就在想,既然 AI