AI 中文总结
提出D-JEPA，一种以几何为中心的JEPA表示，通过轻量物理解码器实现跨工况复用，支持设计可恢复、优化与迁移，在四个3D基准上保持精度并实现近乎完美的设计参数恢复。
AI 中文摘要
联合嵌入预测架构（JEPAs）提供了一种无需直接重建高维观测即可学习紧凑表示的框架。然而，在参数化物理系统中，学习到的表示可能将几何与运行条件及任务特定的物理响应纠缠在一起，限制了其在预测任务中的复用。我们提出了D-JEPA（设计可恢复JEPA），一种以几何为中心的JEPA，它仅从几何计算紧凑表示，并通过轻量级物理专用解码器在运行条件和物理响应空间之间复用该表示。显式的设计可恢复性目标鼓励几何潜变量保留底层设计变量的信息，使表示能够支持设计分析和优化。我们进一步识别了一种案例级坍缩失效模式，其中目标表示在不同几何之间几乎不变，尽管重建误差较低，并通过案例级变化约束和辅助目标重建来缓解这一问题。在四个3D空气动力学、水动力学和结构基准上，D-JEPA保持或提高了全场预测精度，同时实现了设计参数的近乎完美的线性可恢复性。冻结的几何表示可在保留的运行条件下复用，并可迁移到具有更少可训练参数的结构响应任务。最后，该表示支持可微设计优化，设计通过高保真CFD验证，保持了候选设计的预测排名。这些结果表明，将可复用的几何表示与物理特定预测分离，为科学代理建模和设计提供了一种实用的表示。
英文摘要
Joint-Embedding Predictive Architectures (JEPAs) provide a framework for learning compact representations without directly reconstructing high-dimensional observations. However, in parameterized physical systems, learned representations can entangle geometry with operating conditions and task-specific physical responses, limiting their reuse across prediction tasks. We introduce D-JEPA (Design-recoverable JEPA), a geometry-centric JEPA that computes a compact representation from geometry alone and reuses it across operating conditions and physical response spaces through lightweight physics-specific decoders. An explicit design-recoverability objective encourages the geometry latent to preserve information about the underlying design variables, enabling the representation to support design analysis and optimization. We further identify a case-level collapse failure mode in which target representations become nearly invariant across distinct geometries despite low reconstruction error, and mitigate it using case-level variation constraints and auxiliary target reconstruction. Across four 3D aerodynamic, hydrodynamic, and structural benchmarks, D-JEPA maintains or improves full-field prediction accuracy while achieving near-perfect linear recoverability of design parameters. The frozen geometry representation can be reused at held-out operating conditions and transferred to a structural response task with fewer trainable parameters. Finally, the representation supports differentiable design optimization, with designs validated using high-fidelity CFD, preserving the predicted ranking of candidate designs. These results demonstrate that separating a reusable geometry representation from physics-specific prediction provides a practical representation for scientific surrogate modeling and design.
