# AeroJEPA: Learning Semantic Latent Representations for Scalable 3D Aerodynamic Field Modeling

arXiv: https://arxiv.org/abs/2605.05586 · HTML: https://mlsanity.com/paper/2605.05586/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 54 references that are in the map.
- First posted on arXiv 7 May 2026.

## Builds on (most cited first, 30 of 40)

- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [Transolver: A Fast Transformer Solver for PDEs on General Geometries](https://mlsanity.com/paper/2402.02366/) (2024)
- [LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels](https://mlsanity.com/paper/2603.19312/) (2026)
- [LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics](https://mlsanity.com/paper/2511.08544/) (2025)
- [Neural Operators for Accelerating Scientific Simulations and Design](https://mlsanity.com/paper/2309.15325/) (2023)
- [β-Variational autoencoders and transformers for reduced-order modelling of fluid flows](https://mlsanity.com/paper/2304.03571/) (2023)
- [Learning and Leveraging World Models in Visual Representation Learning](https://mlsanity.com/paper/2403.00504/) (2024)
- [VL-JEPA: Joint Embedding Predictive Architecture for Vision-language](https://mlsanity.com/paper/2512.10942/) (2025)
- [A-JEPA: Joint-Embedding Predictive Architecture Can Listen](https://mlsanity.com/paper/2311.15830/) (2023)
- [Towards extraction of orthogonal and parsimonious non-linear modes from turbulent flows](https://mlsanity.com/paper/2109.01514/) (2021)
- [Joint Embedding Predictive Architectures Focus on Slow Features](https://mlsanity.com/paper/2211.10831/) (2022)
- [Generalised Latent Assimilation in Heterogeneous Reduced Spaces with Machine Learning Surrogate Models](https://mlsanity.com/paper/2204.03497/) (2022)
- [Aero-Nef: Neural Fields for Rapid Aircraft Aerodynamics Simulations](https://mlsanity.com/paper/2407.19916/) (2024)
- [GeoTransolver: Learning Physics on Irregular Domains Using Multi-scale Geometry Aware Physics Attention Transformer](https://mlsanity.com/paper/2512.20399/) (2025)
- [Graph-level Representation Learning with Joint-Embedding Predictive Architectures](https://mlsanity.com/paper/2309.16014/) (2023)
- [Value-guided action planning with JEPA world models](https://mlsanity.com/paper/2601.00844/) (2025)
- [Connecting Joint-Embedding Predictive Architecture with Contrastive Self-supervised Learning](https://mlsanity.com/paper/2410.19560/) (2024)
- [Factorized Implicit Global Convolution for Automotive Computational Fluid Dynamics Prediction](https://mlsanity.com/paper/2502.04317/) (2025)
- [Video Representation Learning with Joint-Embedding Predictive Architectures](https://mlsanity.com/paper/2412.10925/) (2024)
- [3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning](https://mlsanity.com/paper/2409.15803/) (2024)
- [T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Data](https://mlsanity.com/paper/2410.05016/) (2024)
- [HEP-JEPA: A foundation model for collider physics using joint embedding predictive architecture](https://mlsanity.com/paper/2502.03933/) (2025)
- [Learning Symmetry-Independent Jet Representations via Jet-Based Joint Embedding Predictive Architecture](https://mlsanity.com/paper/2412.05333/) (2024)
- [Rethinking JEPA: Compute-Efficient Video SSL with Frozen Teachers](https://mlsanity.com/paper/2509.24317/) (2025)
- [Representation Learning for Spatiotemporal Physical Systems](https://mlsanity.com/paper/2603.13227/) (2026)
- [WirelessJEPA: A Multi-Antenna Foundation Model using Spatio-temporal Wireless Latent Predictions](https://mlsanity.com/paper/2601.20190/) (2026)
- [LaT-PFN: A Joint Embedding Predictive Architecture for In-context Time-series Forecasting](https://mlsanity.com/paper/2405.10093/) (2024)

## Built on by (most cited first, 4 of 4)

- [HiLiftAeroML: A High-Fidelity Computational Fluid Dynamics Dataset for High-Lift Aircraft Aerodynamics](https://mlsanity.com/paper/2605.19565/) (2026)
- [D-JEPA: Design-Recoverable JEPA Representation with Swappable Physics Decoders](https://mlsanity.com/paper/2609.33110/) (2026)
- [PDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEs](https://mlsanity.com/paper/2609.34715/) (2026)
- [Cross-Domain Pretraining for Steady-State Neural CFD Surrogates](https://mlsanity.com/paper/2610.10398/) (2026)

## Abstract (arXiv)

High-fidelity CFD is essential for aerodynamic design, but repeated simulations are computationally expensive, motivating surrogate models for rapid evaluation across geometries and operating conditions. Most existing surrogates are designed for direct field regression, requiring the evaluation of millions of field points even when only an aerodynamic quantity or a localized region is needed, while their internal representations are not intended for direct use in downstream tasks. We introduce AeroJEPA, a framework inspired by joint-embedding predictive architectures that represents the problem in two distinct latent spaces: context tokens encode geometry, while predicted tokens encode the aerodynamic state. Both representations remain directly accessible for downstream tasks, such as linear readouts of design variables and aerodynamic quantities without decoding and integrating the full field. When spatial detail is needed, a continuous implicit decoder evaluates the field only at the requested coordinates while reusing the encoded geometry. We evaluate AeroJEPA on HiLiftAeroML, with multi-million-point fields, and SuperWing, which spans a broad family of transonic wings. Compared with state-of-the-art direct-regression surrogates, AeroJEPA trades peak full-field accuracy for compact, reusable representations. In our selective-decoding experiment, however, AeroJEPA substantially outperforms the evaluated direct-regression surrogates while avoiding predictions over the remainder of the aircraft. The learned representations further support controlled interpolation, concept-vector arithmetic, and preliminary constrained latent-space optimization. These results show how predictive representations can support aerodynamic analysis with or without full-field reconstruction.