PhysisForcing：物理強化世界模擬器，用於機器人操作

摘要

視頻生成模型已展現出作為具身世界模擬的潛力。然而，無論是通用領域的視頻生成器，還是針對機器人數據微調的模型，仍會產生物理上不合理的操作，包括不連續的運動軌跡與不一致的機器人-物體互動，這限制了其作為世界模擬器的可靠性。透過大量實驗，我們發現此類物理不穩定性主要源自兩個因素：移動物體的形變，以及互動實體之間（特別是在接觸時）不合理的時空關聯性。基於此觀察，我們提出 PhysisForcing，一個可擴展的訓練框架，透過聯合優化像素層級與語義層級特徵，將監督聚焦於物理資訊豐富的區域，從而強化物理一致性。該框架包含一個像素層級的軌跡對齊損失（利用參考點軌跡監督 DiT 特徵），以及一個語義層級的關係對齊損失（將 DiT 特徵與從凍結的視頻理解編碼器中提取的區域間關係進行對齊）。在 R-Bench、PAI-Bench 與 EZS-Bench 上的大量實驗顯示，PhysisForcing 能一致性地提升基於強基線的具身視頻生成效能：在 R-Bench 上，Wan2.2-I2V-A14B 與 Cosmos3-Nano 基礎模型分別提升 22.3% 與 9.2%（相較於標準微調分別提升 7.1% 與 3.7%），其中 Cosmos3-Nano 變體取得最佳整體分數。在生成之外，作為 WorldArena 行動規劃器協定下的世界模型，它將封閉循環成功率從 16.0% 提升至 24.0%，並進一步改善下游策略的成功率，表明物理對齊的視頻模型能為機器人操作提供更強的表徵。

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.