PhysisForcing: 物理强化机器人操作世界模拟器

摘要

视频生成模型已成为具身世界模拟的一种有前景的范式。然而，无论是通用域视频生成器还是基于机器人特定数据微调的模型，仍可能产生物理上不可信的操作，包括不连续的运动轨迹和机器人-物体间不一致的交互，这限制了它们作为世界模拟器的可靠性。通过大量实验，我们发现这种物理不稳定性主要源于两个因素：运动物体的形变以及交互实体间（尤其是接触过程中）不可信的时空相关性。基于这一发现，我们提出了PhysisForcing，一个可扩展的训练框架，通过联合优化像素级和语义级特征，将监督重点聚焦于物理信息区域，从而增强物理一致性。该框架包含一个像素级轨迹对齐损失，利用参考点轨迹监督扩散变换器（DiT）特征；以及一个语义级关系对齐损失，将DiT特征与从冻结视频理解编码器中提取的区域间关系进行对齐。在R-Bench、PAI-Bench和EZS-Bench上的大量实验表明，PhysisForcing在强基线上持续提升了具身视频生成性能，使Wan2.2-I2V-A14B和Cosmos3-Nano基模型在R-Bench上分别提升22.3%和9.2%（在普通微调基础上提升7.1%和3.7%），其中Cosmos3-Nano变体取得了最佳总体得分。在生成之外，作为WorldArena动作规划器协议下的世界模型，它将闭环成功率从16.0%提升至24.0%，并进一步改善了下游策略的成功率，表明物理对齐的视频模型能为机器人操作提供更强的表征能力。

English

Video generation models have emerged as a promising paradigm for embodied world simulation. However, both general-domain video generators and robot-specific data fine-tuned models can still produce physically implausible manipulations, including discontinuous motion trajectories and inconsistent robot-object interactions, which limits their reliability as world simulators. Through extensive experiments, we find that such physical instability mainly arises from two factors: deformation of moving objects and implausible spatio-temporal correlations among interacting entities, particularly during contact. Building on this observation, we propose PhysisForcing, a scalable training framework that strengthens physical consistency by focusing supervision on physics-informative regions through joint optimization of pixel-level and semantic-level features. The framework consists of a pixel-level trajectory alignment loss, which supervises DiT features using reference point trajectories, and a semantic-level relational alignment loss, which aligns DiT features with inter-region relations extracted from a frozen video understanding encoder. Extensive experiments on R-Bench, PAI-Bench, and EZS-Bench show that PhysisForcing consistently improves embodied video generation over strong baselines, improving the Wan2.2-I2V-A14B and Cosmos3-Nano base models on R-Bench by 22.3\% and 9.2\% (7.1\% and 3.7\% over vanilla finetuning), with the Cosmos3-Nano variant attaining the best overall score. Beyond generation, as a world model under the WorldArena action-planner protocol it raises the closed-loop success rate from 16.0\% to 24.0\% and further improves downstream policy success, indicating that physically aligned video models yield stronger representations for robotic manipulation.