ByteBrief
We're a portrait publication through and through. Turn your phone back and your briefing picks up right where you left it.
(We tried widescreen once. It wasn't us.)

Alibaba's Qwen team released Qwen-Drive-1.0-4B, an open-source model combining driving-scene understanding with movement planning. Built with Huazhong University of Science and Technology, it uses Qwen3.5-4B as its vision-language foundation and adds components for 3D perception and trajectory generation. Code, weights, and demo data are under Apache 2.0.
Tap to vote and see what everyone thinks.
Summary by ByteBrief
Alibaba's Amap open-sources 3D reconstruction model