Foundation models have revolutionized natural language processing through a ``train once, deploy anywhere'' paradigm, where a single pre-trained model adapts to countless downstream tasks without retraining. Access to a Physics Foundation Model (PFM) would be transformative - democratizing access to high-fidelity simulations, accelerating scientific discovery, and eliminating the need for specialized solver development. Yet current physics-aware machine learning approaches remain fundamentally limited to single, narrow domains and require retraining for each new system. We present the General Physics Transformer (GPhyT), trained on 1.8 TB of diverse simulation data, that demonstrates foundation model capabilities are achievable for physics. Our key insight is that transformers can learn to infer governing dynamics from context, enabling a single model to simulate fluid-solid interactions, shock waves, thermal convection, and multi-phase dynamics without being told the underlying equations. GPhyT achieves three critical breakthroughs: (1) superior performance across multiple physics domains, outperforming specialized architectures by more than 7x, (2) plausible zero-shot generalization to entirely unseen physical systems through in-context learning, and (3) more stable long-term predictions through long-horizon rollouts. By establishing that a single model can learn generalizable physical principles from data alone, this work opens the path toward a universal PFM that could transform computational science and engineering.

翻译：基础模型通过“一次训练，随处部署”的范式彻底改变了自然语言处理，其中单个预训练模型无需重新训练即可适应无数下游任务。获得一个物理基础模型将是变革性的——它能够普及高保真模拟的使用，加速科学发现，并消除对专门求解器开发的需求。然而，当前具有物理感知的机器学习方法从根本上仍然局限于单一、狭窄的领域，并且每个新系统都需要重新训练。我们提出了通用物理Transformer，该模型在1.8 TB的多样化模拟数据上训练，证明了基础模型的能力在物理学领域是可以实现的。我们的核心见解是，Transformer能够学会从上下文中推断支配性动力学，使得单个模型能够模拟流固相互作用、冲击波、热对流和多相动力学，而无需被告知底层方程。GPhyT实现了三个关键突破：在多个物理领域中均表现出卓越性能，其表现超过专用架构7倍以上；通过上下文学习，能够对完全未见过的物理系统进行合理的零样本泛化；通过长时程推演，实现了更稳定的长期预测。通过证明单个模型能够仅从数据中学习可泛化的物理原理，这项工作为通向可能改变计算科学与工程的通用PFM开辟了道路。