Metraipolis › archive › dc_dfd3a539f53f

Self-Augmented Diffusion Guidance for Physics-Informed Generation — arXiv:2608.26748

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.26748
License (as archived)
CC0-1.0
Archived
2026-10-17T16:12:21.218Z
SHA-256 of the archived text
d567e288c75cd08e97ab027bac419cfaa06799dd7806ac9579ef53f189fe8a05
Stable URL of this page
https://metraipolis.com/documento/dc_dfd3a539f53f

How to cite

Self-Augmented Diffusion Guidance for Physics-Informed Generation — arXiv:2608.26748 — arXiv (en), https://arxiv.org/abs/2608.26748 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dfd3a539f53f (Metraipolis archive dc_dfd3a539f53f, sha256 d567e288c75cd08e97ab027bac419cfaa06799dd7806ac9579ef53f189fe8a05)
BibTeX
@misc{dcdfd3a539f53f,
  title = {Self-Augmented Diffusion Guidance for Physics-Informed Generation — arXiv:2608.26748},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26748},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dfd3a539f53f; sha256 d567e288c75cd08e97ab027bac419cfaa06799dd7806ac9579ef53f189fe8a05},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26748. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Diffusion models can be used to generate spatiotemporal signals of physical phenomena, such as time-series images of fluid dynamics. However, a major limitation of standard diffusion models is that they do not incorporate constraints derived from the underlying physical laws. Consequently, generated samples may appear visually plausible while deviating substantially from the true dynamics. In this study, we propose a simple yet effective physics-informed approach based on diffusion guidance with self-generated data augmentation. The proposed method learns the data distribution conditioned on the degree of deviation from the physically correct dynamics and generates samples by explicitly setting the deviation condition to be zero. The method decouples the evaluation of the governing equations from the diffusion model training and sampling processes, avoiding the need to solve the governing equations at every iteration of the denoising process. This design makes the method applicable to problems requiring computationally expensive numerical simulations and enables faster sample generation. Experimental results demonstrate that the proposed model not only significantly reduces the deviations compared with standard diffusion models but also achieves further reductions when combined with existing physics-constrained diffusion methods.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.26748 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T15:34:49.923Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).