Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Models
| Date | Stars |
|---|---|
| 2026-07-31 | 846 |
| 2026-08-03 | 847 |
| 2026-08-06 | 847 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# RynnBrain 1.1
<p align="center">
<img src="./cookbooks/assets/images/logo.png" style="width: 60%; height: auto;">
</p>
<p align="center"><i>Towards More Capable and Generalizable Embodied Foundation Models</i></p>
<p align="center">
💫 <a href="https://alibaba-damo-academy.github.io/RynnBrain/"><b>Project Page</b></a> | 🤗 <a href="https://huggingface.co/collections/Alibaba-DAMO-Academy/rynnbrain-11"><b>Hugging Face</b></a> | 🤖 <a href="https://modelscope.cn/collections/DAMO_Academy/RynnBrain-11"><b>ModelScope</b></a> | 📚 <a href="https://github.com/alibaba-damo-academy/RynnBrain/tree/main/cookbooks"><b>Cookbooks</b></a> | 📄 <a href="https://arxiv.org/abs/2602.14979"><b>arXiv</b></a>
| 📄 <a href="https://raw.githubusercontent.com/alibaba-damo-academy/RynnBrain.github.io/main/assets1.1/RynnBrain_1_1.pdf"> <b>1.1 paper</b></a> </p>
## News
* **[2026.07.16]** ✨✨ Release **RynnBrain 1.1** checkpoints (**2B / 9B / 122B-A10B**) on <a href="https://huggingface.co/collections/Alibaba-DAMO-Academy/rynnbrain-11">Hugging Face</a> & <a href="https://modelscope.cn/collections/DAMO_Academy/RynnBrain-11">ModelScope</a>!
* **[2026.07.16]** ✨✨ Release **RynnBrain 1.1** <a href="https://raw.githubusercontent.com/alibaba-damo-academy/RynnBrain.github.io/main/assets1.1/RynnBrain_1_1.pdf">Technical Report</a> !
* **[2026.07.16]** ✨✨ Release **RynnBrain 1.1**! To access the resources of **RynnBrain 1.0**, please checkout to the <a href="https://github.com/alibaba-damo-academy/RynnBrain/tree/rynnbrain1.0">rynnbrain1.0</a> branch.
* **[2026.04.13]** 🔥🔥 Launch <a href="https://huggingface.co/Alibaba-DAMO-Academy/RynnBrain-4B">RynnBrain-4B </a> !!
* **[2026.02.17]** 🔥🔥 Release **RynnBrain 1.0** <a href="https://arxiv.org/abs/2602.14979v1">Technical Report</a> !!
* **[2026.02.09]** 🔥🔥 Release code and model checkpoints of **RynnBrain 1.0**!!
## Introduction
We present **RynnBrain 1.1**, a systematic upgrade of RynnBrain for embodied intelligence. RynnBrain 1.1 is released in three scales: **2B**, **9B**, and **122B-A10B**, extending the model family from compact dense models to its first 122B-level sparse-MoE model.
## What's New in 1.1 🚀
* **Unified Embodied Scaling to 122B**:
Establishes the first embodied brain model at the 122B scale under a unified training recipe shared across 2B, 9B, and 122B-A10B, enabling a systematic study of how embodied cognition, spatial reasoning, grounding, and planning evolve with scale.
* **Native 3D and contact point grounding**:
Introduces explicit 3D-grounded training and a new contact point prediction task, extending RynnBrain from image-plane localization to metric 3D understanding and action-relevant interaction grounding.
* **Real-robot VLA transfer**:
Bridges perception and action through RynnBrain-VLA, translating embodied understanding into real-robot control and demonstrating strong cross-platform generalization on Unitree G1, Astribot, and Tianji-Wuji across humanoid, bimanual, and dexterous-hand tasks.
<!-- <p align="center">
<img src="./cookbooks/assets/intro.png" style="width: 90%; height: auto;">
</p> -->
## Model Architecture
RynnBrain 1.1 adopts a unified decoder-only vision-language architecture across all scales, supporting both dense and sparse-MoE variants. It encodes omni-vision inputs with language instructions and produces aligned outputs — text, pointing sequences, 3D perception, and contact signals — enabling egocentric understanding, spatio-temporal grounding, physical-world reasoning, and fine-grained planning.
<p align="center">
<img src="./cookbooks/assets/images/model_arch.png" style="width: 80%; height: auto;">
</p>
## Performance
- General Embodied Understanding
<p align="center"><i>RynnBrain 1.1-2B vs. other 2B-scale models</i></p>
<p align="center">
<img src="./cookbooks/assets/images/RynnBrain1.1-2B.png" style="width:Excerpt of 20,263 characters
Read on GitHub
Bohan Hou · Shandong University
22
15
LI XIN · @alibaba
7
5
NLNR
3
Yuqian Yuan · Zhejiang University · China
2
2
2
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:318f73a7f622d7d8, llm:Repository title and description: 'RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Models' — indicates an embodied foundation model (likely for robotics/embodied AI). No topics provided.
matched fp:318f73a7f622d7d8, llm:Repository title and description: 'RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Models' — indicates an embodied foundation model (likely for robotics/embodied AI). No topics provided.
matched fp:318f73a7f622d7d8, llm:Repository title and description: 'RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Models' — indicates an embodied foundation model (likely for robotics/embodied AI). No topics provided.