ACE-Brain-0: Spatial Intelligence as a Shared Scaffold for Universal Embodiments
This work addresses the problem of universal embodied intelligence for researchers and developers working on autonomous systems, such as autonomous driving, robotics, and UAVs, providing an incremental yet significant step forward in this field.
The authors tackled the problem of universal embodied intelligence across diverse embodiments, achieving competitive and state-of-the-art performance on 24 benchmarks with their ACE-Brain-0 model. The model demonstrated robust generalization, with results implying a significant improvement in balancing universal generalization with domain-specific proficiency.
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.