RynnBrain: Open Embodied Foundation Models

TL;DR

RynnBrain is an open-source, multi-scale foundation model designed for embodied intelligence, integrating perception, reasoning, and planning within real-world dynamics, and demonstrating superior performance on diverse benchmarks.

Contribution

The paper introduces RynnBrain, a unified, physically grounded foundation model for embodied intelligence, with multiple scales and variants tailored for various embodied and spatial reasoning tasks.

Findings

Outperforms existing embodied models on 20 benchmarks

Demonstrates strong capabilities in perception, reasoning, and planning

Enables efficient adaptation to diverse embodied tasks

Abstract

Despite rapid progress in multimodal foundation models, embodied intelligence community still lacks a unified, physically grounded foundation model that integrates perception, reasoning, and planning within real-world spatial-temporal dynamics. We introduce RynnBrain, an open-source spatiotemporal foundation model for embodied intelligence. RynnBrain strengthens four core capabilities in a unified framework: comprehensive egocentric understanding, diverse spatiotemporal localization, physically grounded reasoning, and physics-aware planning. The RynnBrain family comprises three foundation model scales (2B, 8B, and 30B-A3B MoE) and four post-trained variants tailored for downstream embodied tasks (i.e., RynnBrain-Nav, RynnBrain-Plan, and RynnBrain-VLA) or complex spatial reasoning tasks (i.e., RynnBrain-CoP). In terms of extensive evaluations on 20 embodied benchmarks and 8 general vision understanding benchmarks, our RynnBrain foundation models largely outperform existing embodied foundation models by a significant margin. The post-trained model suite further substantiates two key potentials of the RynnBrain foundation model: (i) enabling physically grounded reasoning and planning, and (ii) serving as a strong pretrained backbone that can be efficiently adapted to diverse embodied tasks.