Metraipolis › archive › dc_69de763ec922

RD-JEPA: Predictive latent pretraining for few-trajectory transfer across reaction--diffusion equations — arXiv:2609.29403

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29403
License (as archived)
CC0-1.0
Archived
2026-10-08T04:26:10.316Z
SHA-256 of the archived text
81a279e0a689c0541d8b922fbd2ccbe71a0674476a2cde1aefbadc9e316ad850
Stable URL of this page
https://metraipolis.com/documento/dc_69de763ec922

How to cite

RD-JEPA: Predictive latent pretraining for few-trajectory transfer across reaction--diffusion equations — arXiv:2609.29403 — arXiv (en), https://arxiv.org/abs/2609.29403 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_69de763ec922 (Metraipolis archive dc_69de763ec922, sha256 81a279e0a689c0541d8b922fbd2ccbe71a0674476a2cde1aefbadc9e316ad850)
BibTeX
@misc{dc69de763ec922,
  title = {RD-JEPA: Predictive latent pretraining for few-trajectory transfer across reaction--diffusion equations — arXiv:2609.29403},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29403},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_69de763ec922; sha256 81a279e0a689c0541d8b922fbd2ccbe71a0674476a2cde1aefbadc9e316ad850},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29403. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Learning surrogates for time-dependent partial differential equations often requires a new simulation corpus when the governing operator changes. We introduce RD-JEPA, a joint-embedding predictive architecture for self-supervised pretraining on reaction-diffusion trajectories. A single model is pretrained on five parameterized systems and then adapted to three held-out systems whose reaction operators and trajectories are excluded from pretraining. Using one, five, or ten complete trajectories from a held-out system, RD-JEPA achieves lower mean relative discrete $\ell^2$ field error and mean absolute spatial first-difference error than five supervised surrogate baselines, an independently trained control that removes the trajectory-dependent predictive latent pathway, and an architecture-matched model trained from scratch. Within the evaluated equations, output resolution, forecast horizons, and choices of adaptation trajectories, the results indicate that prediction of future-state representations can support data-efficient adaptation across related reaction-diffusion systems.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.29403 — 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 2026-10-08T03:50:57.771Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).