轻量级世界模型提升物理一致性，兼顾精度与效率
Enhancing Physical Consistency in Lightweight World Models
- 引入软掩码机制优化动态物体建模与未来预测
- 参数量400M时综合得分提升60.6%，130M版本提速28%且更优
- 适合边缘设备部署，零样本推理即可获得高质量预测
世界模型在部署时面临规模与性能的权衡：大型模型能捕捉丰富物理动态但需大量计算资源，小型模型虽易部署却常难以学习准确物理规律。本文提出物理感知的鸟瞰图世界模型（PIWM），通过训练阶段的软掩码机制，高效建模物理交互。同时引入简单的温启动（Warm Start）技术，在推理阶段实现零样本高质量预测。实验表明，在相同参数量（400M）下，PIWM相较基线提升60.6%的加权综合得分；即使对比最大基线模型（400M），最小版本（130M Soft Mask）仍取得7.4%更高的得分，且推理速度提升28%。
原文摘要 · Abstract (English)
A major challenge in deploying world models is the trade-off between size and performance. Large world models can capture rich physical dynamics but require massive computing resources, making them impractical for edge devices. Small world models are easier to deploy but often struggle to learn accurate physics, leading to poor predictions. We propose the Physics-Informed BEV World Model (PIWM), a compact model designed to efficiently capture physical interactions in bird's-eye-view (BEV) representations. PIWM uses Soft Mask during training to improve dynamic object modeling and future prediction. We also introduce a simple yet effective technique, Warm Start, for inference to enhance prediction quality with a zero-shot model. Experiments show that at the same parameter scale (400M), PIWM surpasses the baseline by 60.6% in weighted overall score. Moreover, even when compared with the largest baseline model (400M), the smallest PIWM (130M Soft Mask) achieves a 7.4% higher weighted overall score with a 28% faster inference speed.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。