State-of-the-art Vision-Language-Action (VLA) models excel at semantic generalization but struggle to generalize to unseen physical motions in novel environments. We introduce DreamZero, a World Action Model (WAM) built upon a pretrained video diffusion backbone. Unlike VLAs, WAMs learn physical dynamics by predicting future world states and actions, using video as a dense representation of how the world evolves. By jointly modeling video and action, DreamZero learns diverse skills effectively from heterogeneous robot data without relying on repetitive demonstrations. This results in over 2x improvement in generalization to new tasks and environments compared to state-of-the-art VLAs in real robot experiments. Crucially, through model and system optimizations, we enable a 14B autoregressive video diffusion model to perform real-time closed-loop control at 7Hz. Finally, we demonstrate two forms of cross-embodiment transfer: video-only demonstrations from other robots or humans yield a relative improvement of over 42% on unseen task performance with just 10-20 minutes of data. More surprisingly, DreamZero enables few-shot embodiment adaptation, transferring to a new embodiment with only 30 minutes of play data while retaining zero-shot generalization.

翻译：当前最先进的视觉-语言-行动（VLA）模型在语义泛化方面表现出色，但在新环境中泛化到未见过的物理动作方面存在困难。我们提出了DreamZero，这是一个基于预训练视频扩散主干构建的世界行动模型（WAM）。与VLA模型不同，WAM通过预测未来世界状态和行动来学习物理动态，将视频用作世界演化的密集表征。通过联合建模视频和行动，DreamZero能够从异构机器人数据中有效学习多样化技能，而无需依赖重复演示。在真实机器人实验中，与最先进的VLA模型相比，该方法在新任务和新环境中的泛化能力提高了2倍以上。关键的是，通过模型和系统优化，我们使一个140亿参数的自回归视频扩散模型能够以7Hz的频率执行实时闭环控制。最后，我们展示了两种形式的跨具身迁移：来自其他机器人或人类的纯视频演示，仅需10-20分钟的数据，就能在未见任务性能上实现超过42%的相对提升。更令人惊讶的是，DreamZero实现了少样本具身适应，仅需30分钟的交互数据即可迁移到新的具身形态，同时保持零样本泛化能力。