Vision-Language-Action (VLA) models benefit from large-scale and diverse embodied data, yet scaling robot trajectory collection is costly and labor-intensive. Recent advances show that large-scale egocentric human videos provide complementary real-world supervision in pretraining. However, joint training on human and robot data remains challenging due to divergences in action spaces, embodiment structures, temporal dynamics, and supervision quality. We introduce ACE-EGO-0, a unified VLA pretraining framework jointly leveraging heterogeneous data sources. To extract large-scale pretraining supervision from egocentric human videos, we build a scalable egocentric video-to-action pipeline that converts raw human videos into robot-format pseudo-action trajectories. To make these labels comparable with robot demonstrations, ACE-EGO-0 uses a unified action representation based on camera-space actions, morphology conditioning, and time-aligned action chunking. To robustly leverage noisy pseudo-action supervision from egocentric human videos, we formulate a reliability-aware training objective with a human auxiliary loss that concentrates supervision on reliable signals. We instantiate ACE-EGO-0 on 4.53K hours of robot and simulation data, together with 1.48K hours of pseudo-action-labeled egocentric human data. Experiments show that incorporating large-scale human supervision under reliability-aware weighting consistently improves both unified joint pretraining and supervised fine-tuning. ACE-EGO-0 achieves state-of-the-art performance on RoboCasa GR1 TableTop and RoboTwin 2.0, while demonstrating strong transfer to real-world bimanual manipulation.

翻译：视觉-语言-动作（VLA）模型受益于大规模多元具身数据，但机器人轨迹数据的规模化采集成本高昂且劳动密集。近期进展表明，大规模自我中心人类视频能为预训练提供互补的真实世界监督信号。然而，由于动作空间、具身结构、时序动态与监督质量的差异，人类与机器人数据的联合训练仍具挑战性。本文提出ACE-EGO-0，一个统一化的VLA预训练框架，可联合利用异构数据源。为从自我中心人类视频中提取大规模预训练监督信号，我们构建了一套可扩展的自我中心视频到动作流水线，将原始人类视频转化为机器人格式的伪动作轨迹。为使这些标签与机器人示范数据可比较，ACE-EGO-0采用基于相机空间动作、形态条件约束与时序对齐动作分段的统一化动作表征。为稳健利用来自自我中心人类视频的含噪伪动作监督信号，我们设计了可靠性感知的训练目标与人类辅助损失函数，将监督信号聚焦于可靠信号。我们在4.53K小时机器人及仿真数据与1.48K小时伪动作标注自我中心人类数据上实例化ACE-EGO-0。实验表明，在可靠性感知加权机制下引入大规模人类监督信号，可一致提升统一化联合预训练与监督微调性能。ACE-EGO-0在RoboCasa GR1桌面操作与RoboTwin 2.0任务上达到最优性能，并展现出对真实世界双臂操作的强迁移能力。