外观
论文arXiv 2610.0973421 天前
ΔWAM：将 Action Tangent Fields 蒸馏到 World Action Models 中
原文链接：ΔWAM: Distilling Action Tangent Fields into World Action Models（arXiv 2610.09734 · 发布日期：2026-10-07）
ΔWAM: Distilling Action Tangent Fields into World Action Models
针对WAM监督易受外观持久性主导的问题，ΔWAM以Action Tangent Fields引导去噪监督，并在多个机器人基准上验证鲁棒性。
核心要点
- 稀疏动作监督需密集未来预测补充，但可预测未来常由外观和场景持久性主导。
- 方法用动作对未来动力学影响的局部Taylor展开，重构更高效的世界监督。
- 在Residual-VAE空间中借助ACWM探测动作变化与残差世界变化的局部对应，并蒸馏进WAM。
- 在三个基准上对光照、背景、相机、布局等扰动持续提升鲁棒性，并将VideoDiT去噪蒸馏为单步。
验证范围与局限：验证范围为LIBERO-Plus、RoboTwin和RoboTwin2.0-Plus上的环境扰动鲁棒性。
英文摘要 (Abstract)
World Action Models (WAM) improve robot policies by augmenting sparse action supervision with dense future prediction. However, much of the predictable future is dominated by appearance and scene persistence rather than action-dependent dynamics. We observe that several recent WAM designs, including optical flow, motion-centric representations, and latent actions, can be understood from a common perspective in which world supervision becomes more efficient as it contains a higher proportion of action-relevant variation. Based on this insight, we introduce Action Tangent Fields, which reformulate world supervision through a local Taylor expansion of how actions induce changes in future dynamics. We represent future dynamics in Residual-VAE space, where the future latent remains recoverable from the current latent and its residual, and use a strong action-conditioned world model (ACWM) to probe the local correspondence between action variations and residual-world variations. This local first-order structure is distilled into the WAM to guide its denoising supervision toward dynamics that are more tightly coupled to action, rather than merely predictable from appearance. Across LIBERO-Plus, RoboTwin, and RoboTwin2.0-Plus, our method consistently improves robustness to lighting, background, camera, layout, and other environmental perturbations. Despite using no large-scale embodied pretraining, it achieves stronger robustness under several distribution shifts than pretrained policies. We further distill multi-step VideoDiT denoising into a single step for efficient inference. Our results suggest that effective WAM supervision should remain information-rich while concentrating its predictive capacity on the directions along which actions change the future.
作者：Ke Wu, Hanwen Huang, Bo Gu, Kaizhao Zhang, Xiangting Meng, Yupeng Zheng, Zijun Xu, Jieru Zhao, Wenchao Ding
来源
本页事实对应的公开页面，以原文为准。