➡️
继续阅读
-
LightNav-0——激发VLM空间智能实现跨本体通用:基于单目RGB与统一token接口,结合时间感知历史压缩、两阶段课程与GRPO在线强化
LightNav-0是一种基于Qwen3-VL-4B构建的紧凑通用具身导航模型,无需任务特定预测头。它通过双通道指向接口(可供性点与物体点)表达空间意图,...
-
银河通用具身智能方案入选北京文旅科技创新优秀解决方案
北京银河通用机器人联合北大、海淀文旅集团报送的“具身智能机器人‘文旅+消费’场景创新解决方案”,入选北京市文旅科技创新优秀解决方案,为具身智能领域唯一入选...
-
Kia’s electric van lineup is getting more interesting with reveal of PV7
You may not know it, but minivans are making a comeback in the US. Look aroun...
-
One of the best 3D printers for beginners is almost $100 off
If the high price tag of premium 3D printers have kept you from exploring the...
- 推出 Gemini 3.8 Live 与 3.8 Live Extended Thinking
-
使用 Gemini 3.8 Live 和 3.5 Transcribe 构建实时语音应用
Try the models today in ai.studio/live