JEV-27B-VL 视觉决策模型答疑：computer use 与 3D 路线

AutoTrust @AutoTrustAI原推发布于 2026.10.03

在 X 上打开原推

Thanks @Gorden_Sun, @potechi_takusan, @Read_Acted, and @a_captaincook — the questions have been great. A few clear answers: • Computer use: yes. The path from screen state → calibrated next action → click / type / scroll loop is a core direction for JEV-27B-VL. • 3D + robotics: also yes. The current release takes 2D image state; 3D scene understanding and embodied / robotics workflows are directions we are actively building toward, not capabilities we claim are fully solved today. • Local deployment: agreed — an 80GB GPU is too much for many builders. The current BF16 release targets that class of hardware, but quantized and GGUF variants are coming soon. • For agent engineers: JEV-27B-VL is open-weight under Apache-2.0, with vLLM and SGLang deployment paths. It is designed for calibrated visual decisions, not just image description. Mario and Tetris make the loop easy to see: see → decide → act. The destination is broader: computer use, visual agents, and eventually embodied systems. JEV-27B-VL: https://huggingface.co/autotrust/JEV-27B-VL For AutoTrust AI’s full research-agent workspace, download ScienceGuru for Windows or macOS: https://scienceguru.ai/

这条是引用着另一条写的：x.com/autotrustai/status/2105476752449679686