HoloBrain-0 Technical Report

TL;DR

HoloBrain-0 introduces a novel vision-language-action framework for robots that incorporates embodiment priors, achieves state-of-the-art results, and is fully open-sourced to facilitate research and deployment.

Contribution

The paper presents HoloBrain-0, a new VLA architecture that explicitly models robot embodiment and demonstrates scalable pre-training and deployment capabilities.

Findings

State-of-the-art results on RoboTwin 2.0, LIBERO, and GenieSim benchmarks.

Efficient 0.2B-parameter model rivals larger baselines.

Open-source ecosystem supports research and practical deployment.

Abstract

In this work, we introduce HoloBrain-0, a comprehensive Vision-Language-Action (VLA) framework that bridges the gap between foundation model research and reliable real-world robot deployment. The core of our system is a novel VLA architecture that explicitly incorporates robot embodiment priors, including multi-view camera parameters and kinematic descriptions (URDF), to enhance 3D spatial reasoning and support diverse embodiments. We validate this design through a scalable ``pre-train then post-train" paradigm, achieving state-of-the-art results on simulation benchmarks such as RoboTwin 2.0, LIBERO, and GenieSim, as well as strong results on challenging long-horizon real-world manipulation tasks. Notably, our efficient 0.2B-parameter variant rivals significantly larger baselines, enabling low-latency on-device deployment. To further accelerate research and practical adoption, we fully open-source the entire HoloBrain ecosystem, which includes: (1) powerful pre-trained VLA foundations; (2) post-trained checkpoints for multiple simulation suites and real-world tasks; and (3) RoboOrchard, a full-stack VLA infrastructure for data curation, model training and deployment. Together with standardized data collection protocols, this release provides the community with a complete, reproducible path toward high-performance robotic manipulation.