# RynnBrain 1.1：想用「一个大脑」驱动多种机器人

> 阿里达摩院开源了一组「具身」AI 模型，主打三维空间理解与机器人动作规划——不过亮眼的榜单成绩，目前仍是团队自测。

_Source: arXiv preprint / DAMO Academy (self-reported benchmarks) · 2026-07-22 · 6 min read · Verified against primary sources_

Canonical: https://iyu.app/zh/e/rynnbrain-1-1-embodied-foundation-model

## 全文

> **⚑ Caveat:** 下文的基准领先与真机优势均为**作者自测**，且是在其自选的基准上得出，尚未经独立复现。请把它们当作「说法」，而非定论。


### 一句话 — 为机器人而造的大脑，不是为聊天

阿里**达摩院**发布了 **RynnBrain 1.1**，一组*具身*基础模型。「具身」是关键词：与活在文字里的聊天机器人不同，这些模型被设计成装进机器人体内，帮它**感知场景、进行空间推理、定位物体并规划动作**。


---

_This is a members-only explainer; the excerpt above is the free preview. Full text: https://iyu.app/zh/e/rynnbrain-1-1-embodied-foundation-model_


## Primary sources

- [Hugging Face paper page — RynnBrain 1.1](https://huggingface.co/papers/2607.17977)
- [arXiv:2607.17977](https://arxiv.org/abs/2607.17977)
- [GitHub — alibaba-damo-academy/RynnBrain](https://github.com/alibaba-damo-academy/RynnBrain)

---
_Published by iyu (https://iyu.app) — the day's AI news, checked against primary sources and rewritten in plain language. Free to quote with attribution and a link to the canonical URL._