Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

Hugging Face Unveils RynnBrain 1.1: A Family of Embodied Foundation Models Up to 122B Parameters

AI By Crimson AI Hugging Face Papers 21 July 2026 · 00:00 6 views
Share: X Telegram

RynnBrain 1.1, a new family of embodied foundation models from Hugging Face, scales from 2B to 122B parameters and introduces contact-point prediction and native 3D grounding for improved robot manipulation. The models achieve state-of-the-art results on several embodied cognition benchmarks.

Hugging Face Unveils RynnBrain 1.1: A Family of Embodied Foundation Models Up to 122B Parameters

Key points

Hugging Face has released RynnBrain 1.1, a family of embodied foundation models designed to advance robot perception, reasoning, and manipulation. The models come in three sizes: 2B, 9B, and a mixture-of-experts 122B-A10B variant, all trained using a unified spatio-temporal and physically grounded framework.

Compared to its predecessor RynnBrain 1.0, version 1.1 introduces contact-point prediction across all model sizes and native 3D grounding for the 2B and 9B models. These enhancements aim to produce representations and outputs that are more directly aligned with real-world robot manipulation tasks.

The team also developed RynnBrain-VLA, a vision-language-action model that employs a unified cross-embodiment action space with embodiment-specific masking. This model has been deployed on three different robot platforms: Unitree G1, Astribot-S1, and Tianji-Wuji.

On benchmarks, the 122B-A10B model outperforms all evaluated proprietary and open-source models on VSI-Bench, MMSI, and RefSpatial-Bench. Real-robot experiments show that policies initialized with RynnBrain outperform those based on Qwen and other representative generalist vision-language-action models. Furthermore, joint multi-task and multi-embodiment training improves both process scores and success rates compared to per-task training.

The code and models are available on GitHub at alibaba-damo-academy/RynnBrain.

ModelParametersKey Features
RynnBrain 1.1 2B2BContact-point prediction, native 3D grounding
RynnBrain 1.1 9B9BContact-point prediction, native 3D grounding
RynnBrain 1.1 122B-A10B122B (MoE)Contact-point prediction
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

1
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

1
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

1