RynnBrain 1.1：邁向更具能力與泛化性的具身基礎模型

RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model

July 20, 2026

作者: Kehan Li, Bohan Hou, Minghao Zhu, Tianyi Zhang, Zesen Cheng, Zhikai Wang, Sicong Leng, Xin Li, Xiao Lin, Biying Yao, Minghua Zeng, Jiangpin Liu, Ronghao Dang, Jiayan Guo, Siteng Huang, Haoyu Zhao, Heng Ping, Yaxi Zhao, Kexiang Wang, Tong Lu, Shengke Xue, Jiahao Tang, Yulei Wang, Zejing Wang, Jianwei Gao, Shijian Lu, Chengju Liu, Jianfei Yang, Mingxiu Chen, Deli Zhao

cs.AI

摘要

我們提出了 RynnBrain 1.1，這一系列具身基礎模型涵蓋 2B、9B 與 122B-A10B 參數量級。透過統一的時空與物理基礎框架進行訓練，RynnBrain 1.1 支援具身感知、空間推理、定位與規劃。相較於 RynnBrain 1.0，它進一步在整個模型家族中引入了接觸點預測，並針對 2B 與 9B 模型加入了原生 3D 定位能力，從而產生更直接對齊機器人操作的表徵與輸出。我們也開發了 RynnBrain-VLA，採用統一的跨本體動作空間與本體特定遮罩，並將其部署於 Unitree G1、Astribot-S1 與 Tianji-Wuji 上。RynnBrain 1.1 在具身認知、定位與 3D 定位方面取得了優異成果，其中 122B-A10B 模型在 VSI-Bench、MMSI 與 RefSpatial-Bench 上優於所有評估的專有與開源模型。真實機器人實驗表明，基於 RynnBrain 初始化的策略優於基於 Qwen 的代表性通用 VLA，而聯合多任務與多本體訓練相較於單任務訓練，能提升過程分數與成功率。

English

We present RynnBrain 1.1, a family of embodied foundation models spanning 2B, 9B, and 122B-A10B scales. Trained with a unified spatio-temporal and physically grounded framework, RynnBrain 1.1 supports embodied perception, spatial reasoning, localization, and planning. Compared with RynnBrain 1.0, it further introduces contact-point prediction across the model family and native 3D grounding for the 2B and 9B models, yielding representations and outputs that are more directly aligned with robot manipulation. We also develop RynnBrain-VLA with a unified cross-embodiment action space and embodiment-specific masking, and deploy it on Unitree G1, Astribot-S1, and Tianji-Wuji. RynnBrain 1.1 achieves strong results on embodied cognition, localization, and 3D grounding, with the 122B-A10B model outperforming all evaluated proprietary and open-source models on VSI-Bench, MMSI, and RefSpatial-Bench. Real-robot experiments show that RynnBrain-initialized policies outperform Qwen-based and representative generalist VLAs, while joint multi-task and multi-embodiment training improves process scores and success rates over per-task training.