GigaWorld-Policy-0.5: 由AutoResearch驱动的更快更强的WAM

摘要

世界动作模型（WAMs）通过联合建模动作与未来视觉观测，利用未来场景演化作为物理驱动动作生成的密集监督信号，从而提升机器人策略学习效果。然而，现有WAMs的常见设计是在推理时显式生成未来视频，这不仅产生大量计算开销，还阻碍了实时闭环部署。GigaWorld-Policy通过以动作为核心的框架解决了这一问题：训练阶段利用未来视觉动态，而推理阶段仅进行动作解码。在此基础上，我们提出GigaWorld-Policy-0.5——一种面向更高效机器人控制的增强型动作中心WAM。在预训练阶段，GigaWorld-Policy-0.5采用混合的"动作条件世界建模"（AC-WM）与WAM训练策略，这强化了视觉动态与机器人动作之间的耦合，并提升了动作表示在下游策略学习中的迁移能力。为实现高效推理，GigaWorld-Policy-0.5引入混合Transformer架构，将视觉动态建模与动作生成分离为专门专家模块，从而在仅动作推理时减少活跃计算量，并在本地RTX 4090平台上实现85毫秒的推理延迟。此外，我们采用基于智能体的AutoResearch管线系统性地搜索训练配置，从而更高效地识别最优实验设置，同时减少超参数调优所需的时间与人工干预。实验与消融研究表明，GigaWorld-Policy-0.5既保留了未来视觉动态带来的训练优势，又提升了机器人控制的推理效率。

English

World Action Models (WAMs) improve robot policy learning by jointly modeling actions and future visual observations, using future scene evolution as dense supervision for physically grounded action generation. However, a common design in existing WAMs is to explicitly generate future videos at inference time, incurring substantial computational overhead and hindering real-time closed-loop deployment. GigaWorld-Policy addresses this issue with an action-centered formulation, where future visual dynamics are used during training while action-only decoding is used at inference time. Building upon this framework, we present GigaWorld-Policy-0.5, an enhanced action-centered WAM designed for more efficient robot control. During pretraining, GigaWorld-Policy-0.5 adopts a mixed Action-Conditioned World Modeling (AC-WM) and WAM training strategy. This strengthens the coupling between visual dynamics and robot actions and improves the transferability of action representations for downstream policy learning. For efficient inference, GigaWorld-Policy-0.5 introduces a Mixture-of-Transformers architecture that separates visual dynamics modeling and action generation into specialized experts, reducing active computation during action-only inference and achieving 85 ms inference latency on a local RTX 4090 setup. In addition, we employ an agent-based AutoResearch pipeline to systematically search training configurations, enabling more efficient identification of optimal experimental setups while reducing the time and manual intervention required for hyperparameter tuning. Experiments and ablations show that GigaWorld-Policy-0.5 preserves the training benefits of future visual dynamics while improving inference efficiency for robot control.