RoboBrain 2.0 Technical Report

BAAI RoboBrain Team, Mingyu Cao, tanhuajie2001, yuhengji, MinglanLin, lizhiyu, Caozhou, Pengwei Wang, Zhoues, Han.Yi, Yingbo Tang, Xiangqi Xu, wei, Yaoxu Lyu, Yijie Xu, ShiJy, Cheng Chi, Mengdi Zhao, Xiaoshuai Hao, Shanyu Rong, Zhengliang Cai, Bolun Zhang, Shuyi Zhang, huaihai lyu, Mengfei Du, Lingfeng Zhang, Xi Feng, Xiaodan Liu, Yance Jiao, Chenrui He, lyu, Zhuo Chen, Yulong Ao, Xue Sun, Zheqi He, Jingshu Zheng, Xi Yang, Donghai Shi, Kunchang Xie, Bochao Zhang, Shaokai Nie, Chunlei Men, Yonghua Lin, Zhongyuan Wang, Tiejun Huang, Shanghang Zhang

RoboBrain 2.0 Technical Report: 26 upvotes on Hugging Face Daily Papers, #9 of 27 papers on 2025-07-08. Day-by-day upvote history. It lost 10 votes when the Hub removed votes in bulk.

We introduce RoboBrain 2.0, our latest generation of embodied vision-language foundation models, designed to unify perception, reasoning, and planning for complex embodied tasks in physical environments. It comes in two variants: a lightweight 7B model and a full-scale 32B model, featuring a heterogeneous architecture with a vision encoder and a language model. Despite its compact size, RoboBrain 2.0 achieves strong performance across a wide spectrum of embodied reasoning tasks. On both spatial and temporal benchmarks, the 32B variant achieves leading results, surpassing prior open-source and proprietary models. In particular, it supports key real-world embodied AI capabilities, including spatial understanding (e.g., affordance prediction, spatial referring, trajectory forecasting) and temporal decision-making (e.g., closed-loop interaction, multi-agent long-horizon planning, and scene graph updating). This report details the model architecture, data construction, multi-stage training strategies, infrastructure and practical applications. We hope RoboBrain 2.0 advances embodied AI research and serves as a practical step toward building generalist embodied agents. The code, checkpoint and benchmark are available at https://superrobobrain.github.io.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.