Pith. sign in

REVIEW 11 cited by

Generative Latent Neural PDE Solver using Flow Matching

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.22600 v1 pith:BVYJJX5H submitted 2025-03-28 cs.LG cs.AI

Generative Latent Neural PDE Solver using Flow Matching

classification cs.LG cs.AI
keywords diffusionlatenttrainingmodelneuralcomputationaldata-drivenflow
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Autoregressive next-step prediction models have become the de-facto standard for building data-driven neural solvers to forecast time-dependent partial differential equations (PDEs). Denoise training that is closely related to diffusion probabilistic model has been shown to enhance the temporal stability of neural solvers, while its stochastic inference mechanism enables ensemble predictions and uncertainty quantification. In principle, such training involves sampling a series of discretized diffusion timesteps during both training and inference, inevitably increasing computational overhead. In addition, most diffusion models apply isotropic Gaussian noise on structured, uniform grids, limiting their adaptability to irregular domains. We propose a latent diffusion model for PDE simulation that embeds the PDE state in a lower-dimensional latent space, which significantly reduces computational costs. Our framework uses an autoencoder to map different types of meshes onto a unified structured latent grid, capturing complex geometries. By analyzing common diffusion paths, we propose to use a coarsely sampled noise schedule from flow matching for both training and testing. Numerical experiments show that the proposed model outperforms several deterministic baselines in both accuracy and long-term stability, highlighting the potential of diffusion-based approaches for robust data-driven PDE learning.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. PerFlow: Physics-Embedded Rectified Flow for Efficient Reconstruction and Uncertainty Quantification of Spatiotemporal Dynamics

    cs.LG 2026-05 unverdicted novelty 7.0

    PerFlow embeds physics constraints into rectified flow sampling through guidance-free conditioning and constraint-preserving projections, achieving efficient sparse reconstruction and uncertainty quantification for sp...

  2. Generating synthetic evolution of turbulent flames with an experimental data-based spatiotemporal diffusion model

    physics.flu-dyn 2026-07 conditional novelty 6.0

    A spatiotemporal diffusion model generates realistic multi-modal flame sequences and user-controlled liftoff/reattachment transitions from experimental OH-PLIF/PIV data.

  3. Wavelet Flow Matching for Multi-Scale Physics Emulation

    cs.LG 2026-05 unverdicted novelty 6.0

    Wavelet Flow Matching emulates multi-scale PDE-governed systems by transporting velocities directly in a hierarchical wavelet representation via U-Net, yielding improved long-horizon stability and spectral accuracy on...

  4. Recovering Physical Dynamics from Discrete Observations via Intrinsic Differential Consistency

    cs.LG 2026-05 unverdicted novelty 6.0

    Enforcing semi-group consistency on a time-conditioned secant velocity field via Symmetry Rupture improves rollout accuracy and efficiency when learning physical dynamics from discrete observations.

  5. PerFlow: Physics-Embedded Rectified Flow for Efficient Reconstruction and Uncertainty Quantification of Spatiotemporal Dynamics

    cs.LG 2026-05 unverdicted novelty 6.0

    PerFlow decouples observation conditioning from physics enforcement in rectified flows using constraint-preserving projections and invariance guarantees for fast, physics-consistent reconstruction of spatiotemporal dynamics.

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

    cs.LG 2026-04 unverdicted novelty 6.0

    Flow learners parameterize transport vector fields to generate PDE trajectories through integration, offering a physics-to-physics organizing principle for learned solvers.

  7. Particle-Guided Diffusion Models for Partial Differential Equations

    cs.LG 2026-01 conditional novelty 6.0

    A guided diffusion sampling method using Sequential Monte Carlo and a second-order stochastic proposal with PDE-residual guidance reduces reconstruction error on several PDE benchmarks compared with DiffusionPDE.

  8. Flow marching for a generative PDE foundation model

    cs.LG 2025-09 unverdicted novelty 6.0

    Flow Marching jointly samples noise and physical time to learn a velocity field for generative PDE modeling, paired with a latent autoencoder and efficient transformer for large-scale pretraining on 2.5M trajectories.

  9. Di-BiLPS: Denoising induced Bidirectional Latent-PDE-Solver under Sparse Observations

    cs.LG 2026-05 unverdicted novelty 5.0

    Di-BiLPS combines a variational autoencoder, latent diffusion, and contrastive learning to achieve state-of-the-art accuracy on PDE problems with as little as 3% observations while supporting zero-shot super-resolutio...

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

    cs.LG 2026-04 conditional novelty 5.0

    Learned PDE solving should target transport over admissible futures via flow learners, not snapshot state regression.

  11. Physics Priors Offer Useful Accuracy-Carbon Trade-Offs in Spatio-Temporal Forecasting

    cs.LG 2025-09 unverdicted novelty 5.0

    Stronger physics priors in neural networks for spatio-temporal shear flow forecasting yield substantially lower training carbon footprints than weak or no priors, though inference savings are less consistent.