Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

HoloBrain-0 Technical Report

About

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.

Xuewu Lin, Tianwei Lin, Yun Du, Hongyu Xie, Yiwei Jin, Jiawei Li, Shijie Wu, Qingze Wang, Mengdi Li, Mengao Zhao, Ziang Li, Chaodong Huang, Hongzhe Bi, Lichao Huang, Zhizhong Su• 2026

Related benchmarks

TaskDatasetResultRank
Robot ManipulationLIBERO
Goal Achievement97.6
494
Robot ManipulationRoboTwin Clean 2.0
Place Dual Shoes Success96
20
Robot ManipulationRoboTwin Randomized 2.0
Success Rate: Place Dual Shoes96
20
Robot ManipulationLIBERO-Plus Zero-shot
Camera Score66.3
20
Aggregate performance across 10 tasksHoloBrain-0 Real-world Evaluation Suite
Average Progress88.07
4
Fold clothesHoloBrain Real-world Evaluation Suite 0
Progress Score81.43
4
Fold paper boxHoloBrain-0 Real-world Evaluation Suite
Progress Score99.5
4
Fold TowelHoloBrain-0 Real-world Evaluation Suite
Progress Score95.26
4
Place shoeHoloBrain Real-world Evaluation Suite 0
Progress Score0.9677
4
Put bottles basketHoloBrain-0 Real-world Evaluation Suite
Progress Score96.67
4
Showing 10 of 16 rows

Other info

Follow for update