Pith. sign in

REVIEW 6 cited by

DiffusionPDE: Generative PDE-Solving Under Partial Observation

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 2406.17763 v2 pith:OKXL2UOY submitted 2024-06-25 cs.LG cs.AIcs.CVcs.NAmath.NA

DiffusionPDE: Generative PDE-Solving Under Partial Observation

classification cs.LG cs.AIcs.CVcs.NAmath.NA
keywords generativepartialdiffusionpdeforwardframeworkinverseobservationpdes
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We introduce a general framework for solving partial differential equations (PDEs) using generative diffusion models. In particular, we focus on the scenarios where we do not have the full knowledge of the scene necessary to apply classical solvers. Most existing forward or inverse PDE approaches perform poorly when the observations on the data or the underlying coefficients are incomplete, which is a common assumption for real-world measurements. In this work, we propose DiffusionPDE that can simultaneously fill in the missing information and solve a PDE by modeling the joint distribution of the solution and coefficient spaces. We show that the learned generative priors lead to a versatile framework for accurately solving a wide range of PDEs under partial observation, significantly outperforming the state-of-the-art methods for both forward and inverse directions.

discussion (0)

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

Forward citations

Cited by 6 Pith papers

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

  1. Observation-Aligned Mask Priors for Learning Physical Dynamics from Authentic Occlusions

    cs.CV 2026-05 unverdicted novelty 7.0

    A framework pretrained on authentic binary occlusion masks uses guided sampling and intersection-based partitioning to train diffusion models on incomplete physical observations without zero-query regions.

  2. Latent Generative Solvers for Generalizable Long-Term Physics Simulation

    cs.AI 2026-02 unverdicted novelty 7.0

    LGS pretrained on 2.5M trajectories across 16 systems matches deterministic baselines at one step and halves 20-step error while using far less compute and adapting to held-out higher-resolution flows.

  3. Image Editing Models are Numerical Solvers

    cs.CV 2026-07 conditional novelty 6.0

    A FLUX image editor, adapted per task, maps rendered inputs to rendered solutions across ten numerical problems, but several encodings leak the target's scale and the model cannot track chaotic Kuramoto-Sivashinsky dynamics.

  4. AS-Bridge: A Bidirectional Generative Framework Bridging Next-Generation Astronomical Surveys

    astro-ph.IM 2026-03 conditional novelty 6.0

    A Brownian-bridge diffusion model learns probabilistic LSST↔Euclid image translation on simulations and uses reconstruction inconsistency to detect strong lenses.

  5. 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.

  6. Incomplete Data, Complete Dynamics: A Diffusion Approach

    cs.LG 2025-09 unverdicted novelty 5.0

    A conditional diffusion model trained on partitioned incomplete samples for physical dynamics achieves asymptotic convergence to the true generative process under mild conditions and outperforms baselines in imputation.