Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.03198 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908863124471808 |
|---|---|
| author | Gong, Ziyang Luo, Zehang Tang, Anke Liu, Zhe Fu, Shi Hou, Zhi Yang, Ganlin Wang, Weiyun Wang, Xiaofeng Liu, Jianbo Luo, Gen Kang, Haolan Luo, Shuang Zhou, Yue Luo, Yong Shen, Li Jia, Xiaosong Mu, Yao Yang, Xue Liu, Chunxiao Yan, Junchi Zhao, Hengshuang Tao, Dacheng Wang, Xiaogang |
| author_facet | Gong, Ziyang Luo, Zehang Tang, Anke Liu, Zhe Fu, Shi Hou, Zhi Yang, Ganlin Wang, Weiyun Wang, Xiaofeng Liu, Jianbo Luo, Gen Kang, Haolan Luo, Shuang Zhou, Yue Luo, Yong Shen, Li Jia, Xiaosong Mu, Yao Yang, Xue Liu, Chunxiao Yan, Junchi Zhao, Hengshuang Tao, Dacheng Wang, Xiaogang |
| contents | Universal embodied intelligence demands robust generalization across heterogeneous embodiments, such as autonomous driving, robotics, and unmanned aerial vehicles (UAVs). However, existing embodied brain in training a unified model over diverse embodiments frequently triggers long-tail data, gradient interference, and catastrophic forgetting, making it notoriously difficult to balance universal generalization with domain-specific proficiency. In this report, we introduce ACE-Brain-0, a generalist foundation brain that unifies spatial reasoning, autonomous driving, and embodied manipulation within a single multimodal large language model~(MLLM). Our key insight is that spatial intelligence serves as a universal scaffold across diverse physical embodiments: although vehicles, robots, and UAVs differ drastically in morphology, they share a common need for modeling 3D mental space, making spatial cognition a natural, domain-agnostic foundation for cross-embodiment transfer. Building on this insight, we propose the Scaffold-Specialize-Reconcile~(SSR) paradigm, which first establishes a shared spatial foundation, then cultivates domain-specialized experts, and finally harmonizes them through data-free model merging. Furthermore, we adopt Group Relative Policy Optimization~(GRPO) to strengthen the model's comprehensive capability. Extensive experiments demonstrate that ACE-Brain-0 achieves competitive and even state-of-the-art performance across 24 spatial and embodiment-related benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_03198 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ACE-Brain-0: Spatial Intelligence as a Shared Scaffold for Universal Embodiments Gong, Ziyang Luo, Zehang Tang, Anke Liu, Zhe Fu, Shi Hou, Zhi Yang, Ganlin Wang, Weiyun Wang, Xiaofeng Liu, Jianbo Luo, Gen Kang, Haolan Luo, Shuang Zhou, Yue Luo, Yong Shen, Li Jia, Xiaosong Mu, Yao Yang, Xue Liu, Chunxiao Yan, Junchi Zhao, Hengshuang Tao, Dacheng Wang, Xiaogang Robotics Computation and Language Computer Vision and Pattern Recognition Universal embodied intelligence demands robust generalization across heterogeneous embodiments, such as autonomous driving, robotics, and unmanned aerial vehicles (UAVs). However, existing embodied brain in training a unified model over diverse embodiments frequently triggers long-tail data, gradient interference, and catastrophic forgetting, making it notoriously difficult to balance universal generalization with domain-specific proficiency. In this report, we introduce ACE-Brain-0, a generalist foundation brain that unifies spatial reasoning, autonomous driving, and embodied manipulation within a single multimodal large language model~(MLLM). Our key insight is that spatial intelligence serves as a universal scaffold across diverse physical embodiments: although vehicles, robots, and UAVs differ drastically in morphology, they share a common need for modeling 3D mental space, making spatial cognition a natural, domain-agnostic foundation for cross-embodiment transfer. Building on this insight, we propose the Scaffold-Specialize-Reconcile~(SSR) paradigm, which first establishes a shared spatial foundation, then cultivates domain-specialized experts, and finally harmonizes them through data-free model merging. Furthermore, we adopt Group Relative Policy Optimization~(GRPO) to strengthen the model's comprehensive capability. Extensive experiments demonstrate that ACE-Brain-0 achieves competitive and even state-of-the-art performance across 24 spatial and embodiment-related benchmarks. |
| title | ACE-Brain-0: Spatial Intelligence as a Shared Scaffold for Universal Embodiments |
| topic | Robotics Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.03198 |