arXiv Machine Learning October 8, 2026 By Chun-Wun Cheng, Bingcheng Hu, Angelica I. Aviles-Rivero

Physics-Informed Neural Plasticity: PDE Solvers That Reshape Themselves

Read the original on arXiv Machine Learning →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers

Oct 7

Physics-Informed Neural Plasticity: PDE Solvers That Reshape Themselves

Physics-informed neural PDE solvers adapt their parameters to satisfy governing equations, yet their representational structure typically remains fixed throughout training. This rigidity is poorly mat...

efficiency benchmarks

arXiv Machine Learning

Jun 3

Flow Learners for PDEs: Toward a Physics-to-Physics Paradigm for Scientific Computing

arXiv:2604. 07366v2 Announce Type: replace Abstract: Partial differential equations (PDEs) govern nearly every physical process in science and engineering, but solving them at scale remains prohibitively expensive.

By Yilong Dai, Shengyu Chen, Xiaowei Jia, Runlong Yu

diffusion safety

arXiv Machine Learning

Aug 26

Physics-Integrated Operator Learning via Gaussian Splatting Representations

arXiv:2608.24049v1 Announce Type: new Abstract: Neural operators provide efficient surrogates for spatiotemporal PDE systems, but purely data-driven formulations often accumulate substantial errors d...

By Jihao Zhang, Junyi Guo, Jian-Xun Wang

diffusion benchmarks

arXiv Machine Learning

Aug 6

Continual-Learning Physics-Informed Neural Networks for Parameterized Partial Differential Equations

arXiv:2608. 04778v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) incorporate governing equations into neural-network training and can approximate PDE solutions without requiring large observational datasets.

By Xujia Chen, Xinyue Hu, Letian Chen, Yi Liu, Wenhui Fan

benchmarks

arXiv Machine Learning

Aug 14

Physics-Informed Laplace Neural Operator for Solving Partial Differential Equations

arXiv:2602. 12706v2 Announce Type: replace Abstract: Neural operators have emerged as fast surrogate solvers for parametric partial differential equations (PDEs).

By Heechang Kim, Qianying Cao, Hyomin Shin, Seungchul Lee, George Em Karniadakis, Minseok Choi

rag diffusion benchmarks

arXiv AI

Sep 30

Transolver-$\sigma$: Joint Spectral-Physical Subspace Modeling for Neural PDE Solving

Transolver‑σ is a neural PDE solver that jointly models spectral and physical subspaces to improve accuracy in both one‑step and autoregressive rollouts. The method uses adaptive physical-state interactions, Slice‑Residual Physics‑Attention, and an axis‑factorized Fourier operator to enable information exchange between representations. Across five standard PDE benchmarks, Transolver‑σ reduces benchmark‑averaged relative error by 33.4% compared to the strongest baseline and shows strong performance on coupled multiphysics systems and real‑world fluid and combustion data.

By Haonan Shangguan, Hang Zhou, Haixu Wu, Yuezhou Ma, Jianmin Wang, Mingsheng Long

benchmarks

One email a morning, machine-written

Related stories

Physics-Informed Neural Plasticity: PDE Solvers That Reshape Themselves

Flow Learners for PDEs: Toward a Physics-to-Physics Paradigm for Scientific Computing

Physics-Integrated Operator Learning via Gaussian Splatting Representations

Continual-Learning Physics-Informed Neural Networks for Parameterized Partial Differential Equations

Physics-Informed Laplace Neural Operator for Solving Partial Differential Equations

Transolver-$\sigma$: Joint Spectral-Physical Subspace Modeling for Neural PDE Solving