arXiv Machine Learning

Beyond Compression: Training Latent Representations for Stable Long-Horizon Rollout in Neural Surrogate Solvers

The paper investigates why latent neural surrogate solvers, which compress physical system dynamics into a lower‑dimensional space, often fail during long‑horizon autoregressive rollouts. It demonstrates that training the latent representation only for reconstruction leads to instability, and proposes a set of training interventions—Koopman operator learning, Hamming noise injection, and multi‑step rollout fine‑tuning—that align the latent space with long‑horizon forecasting. These interventions reduce long‑rollout error by about 40 % and achieve accuracy comparable to full‑resolution models while using far fewer floating‑point operations and GPU memory, enabling stable extrapolation in mesoscale crystal‑plasticity simulations of high‑cycle fatigue.

arXiv Machine Learning
Aug 7

Kastor: An efficient fine-tuning strategy for generative emulation of PDE simulations

arXiv:2608. 06107v1 Announce Type: new Abstract: Machine learning offers a promising avenue to accelerate physical simulations by replacing computationally expensive traditional Partial Differential Equation (PDE) solvers with fast, differentiable surrogate models.

By Guillaume Couairon, Alexis Jacq, Yu-Han Wu, Renu Singh, Yana Hasson, Quentin Berthet, Romuald Elie
arXiv Machine Learning
Oct 15

ReAl: Refine neural operators via aligning dynamical flow

ReAl: Refine neural operators via aligning dynamical flow introduces a model‑agnostic plug‑in that enhances pretrained PDE surrogates by adding a refinement stage with a conditional flow‑matching model to recover missing high‑frequency structures, and an alignment stage that generates multiple trajectories and uses trajectory‑level rewards to stabilize long‑horizon predictions. The method improves high‑frequency fidelity, forecasting accuracy, and long‑horizon stability across diverse surrogate architectures and PDE tasks.

By Jing Xu, Zenglin Xu, Li Yi, Ruoxi Jiang, Yuan Qi
arXiv AI
Aug 3

HERO: History-Enriched Rollout Training for Long-Horizon Autoregressive Neural Operators

arXiv:2607. 29135v1 Announce Type: cross Abstract: Neural operators provide fast surrogates for time-dependent partial differential equations (PDEs) by applying a learned evolution operator recursively to its own predictions, but this autoregressive rollout feeds every prediction error back as input, so local errors accumulate.

By Jiaquan Zhang, Shuxu Chen, Haifan Meng, Yi Lu, Zhihan Lyu, Fan Mo, Wei Dong, Yang Yang, Chaoning Zhang
arXiv AI
Jun 26

Error-Conditioned Neural Solvers

arXiv:2606. 27354v1 Announce Type: cross Abstract: Neural surrogate models offer fast approximate mappings from PDE parameters to solutions, but they typically treat solving as a purely statistical task: once trained, they struggle to correct their own constraint violations and extrapolate beyond the training distribution.

By Haina Jiang, Liam Wang, Peng-Chen Chen, Min Seop Kwak, Seungryong Kim, Brian Bell, Jeong Joon Park
arXiv Machine Learning
Oct 8

Cross-Domain Pretraining for Steady-State Neural CFD Surrogates

The paper presents cross‑domain pretraining for neural surrogates in steady‑state computational fluid dynamics (CFD). By training models across varied geometries, boundary conditions, and fidelities, the authors show that such pretraining improves zero‑ and few‑shot performance compared to training from scratch or transferring from domain‑specific experts. Finetuning a pretrained cross‑domain model can reduce errors by 2–3× at the same sample size and require eight times fewer samples to reach the same error, with benefits that grow with model size and dataset diversity.

By Anthony Zhou, Amir Barati Farimani, Shirley Ho, Rudy Morel
arXiv Machine Learning
Oct 8

Physics-Informed Neural Plasticity: PDE Solvers That Reshape Themselves

Physics-informed neural PDE solvers typically keep a fixed representation while adapting parameters, which limits performance on heterogeneous problems. The authors propose physics-informed neural plasticity, allowing the representation itself to reshape during training. Their ReCAP method dynamically redistributes capacity via local enrichment, residual-directed splitting, gate-based pruning, and function-aware merging, achieving the lowest relative $L^2$ error on five challenging 3D and 4D benchmarks and reducing error by 10.7%–27.5% compared to the best competing solvers.

By Chun-Wun Cheng, Bingcheng Hu, Angelica I. Aviles-Rivero