# RynnBrain 1.1: one "brain" that tries to drive many robots

> Alibaba's DAMO Academy released a family of embodied AI models built to see space in 3D and plan robot actions — with headline benchmark wins that are, for now, the team's own.

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

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

## Full explainer

> **⚑ Caveat:** The benchmark leadership and real-robot wins below are **self-reported by the authors**, on benchmarks they chose, and have not yet been independently reproduced. Treat them as claims, not settled results.


### The gist — A brain built for robots, not chat

Alibaba's **DAMO Academy** released **RynnBrain 1.1**, a family of *embodied* foundation models. "Embodied" is the key word: unlike a chatbot that lives in text, these models are designed to sit inside a robot and help it **perceive a scene, reason about physical space, locate objects, and plan actions**.


---

_This is a members-only explainer; the excerpt above is the free preview. Full text: https://iyu.app/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._