具身智能领域这个月真的太精彩了,前有王兴兴预言 GPT-7 可能会打穿 #
PhysicalAI,后有#
@deepseek_ai 也在考虑下场做具身。
自然意志
@naturewill 成立才9个月就推出了500亿参数的 MoE 模型 Natura-1,百万小时级别的 Egocentric 视频预训练数据规模在全球也不超过三家。
跟大部分模型厂商不同的是,Natura-1 没有针对测试任务做专门训练,也没用同一物体、场景、指令组合的数据做后训练,但就能直接根据自然语言指令干活。比如让机器人打开笔记本电脑屏幕再按下空格键,即便在训练里从来没见过电脑和键盘,它也自己摸索着完成了。他们的六个 Demo 包馄饨、打包快递、泡茶、做酸奶碗、手机贴膜、写毛笔字也全是零样本操作(包馄饨、手机贴膜这种场景真的不是爪夹能实现的,必须上灵巧手)。
Natura-1 证明了大规模人类经验 + 一个无主从的端到端架构 + 自研基础设施这条路真的能走通,零样本泛化和灵巧操作可以在一个统一模型里同时涌现。
这是最坏的时代。这是最好的时代。
Introducing Natura-1, our first general foundation model for the physical world.
It follows natural-language instructions zero-shot and turns them into action with dexterous hands.
Natura-1 is a 50-billion-parameter mixture-of-experts (MoE) model pretrained on one million hours of egocentric human experience.
On top of this foundation, we conduct efficient post-training on a limited amount of robot data to adapt pretrained world knowledge to dexterous manipulation, yielding a model that generalizes to a wide range of unseen scenarios.
Natura-1 follows complex natural-language instructions zero-shot, reasoning through spatial constraints, multi-object relationships, and negative conditions.
It can also autonomously carry out long and continuous workflows to perform long-horizon executions.
Natura-1 provides early evidence that generalization—and even emergent behavior—can coexist with the complexity of dexterous hands.
Further progress depends on the full stack: infrastructure for faster training and real-time inference, pretraining data at greater scale and coverage, and models that transfer to robots with less adaptation.
We expect it to be a long-term research and engineering effort.
もっと見る