蚂蚁灵波 4 天发布 6 款 LingBot 2.0 模型
That's a wrap on LingBot 2.0 Release Week — 6 models in 4 days.
蚂蚁灵波（Robbyant）结束 LingBot 2.0 发布周，4 天内共发布 6 款模型。其中包括面向空间感知的 LingBot-Vision 与 LingBot-Depth 2.0、让同一大脑适配多台机器人的 LingBot-VLA 2.0、用于实时交互的 LingBot-World 2.0、高效视频生成的 LingBot-Video，以及压轴的 LingBot-VA 2.0。官方称 LingBot-VA 2.0 从零预训练，围绕动力学建模、因果预测与实时执行等与物理世界交互的需求设计。
正文
当前显示原文，中文全文译文尚未就绪。
That's a wrap on LingBot 2.0 Release Week — 6 models in 4 days. 👀LingBot-Vision & LingBot-Depth 2.0 for spatial. 🧠LingBot-VLA 2.0 for one brain across many robots. 🎮LingBot-World 2.0 for real-time interaction. 🎦LingBot-Video for efficient video generation 🦾And the finale: LingBot-VA 2.0 — pretrained from scratch around what interacting with the physical world truly demands: dynamics modeling, causal prediction, and real-time execution. A new stage of embodied-native AI begins here. Stay tuned for what's next.✨https://t.co/noDgmuQx1o