Metraipolis › archive › dc_43dbf411090f
HotPOT: Operator Transformer with Heterogeneous Physics Experts for Large-Scale PDE Pre-training — arXiv:2610.38218
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.38218
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:24:46.777Z
- SHA-256 of the archived text
3111da0ba88834789b5d9cd990d71d669c4ae4634539ccd2cd490da176a15b17- Stable URL of this page
https://metraipolis.com/documento/dc_43dbf411090f
How to cite
HotPOT: Operator Transformer with Heterogeneous Physics Experts for Large-Scale PDE Pre-training — arXiv:2610.38218 — arXiv (en), https://arxiv.org/abs/2610.38218 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_43dbf411090f (Metraipolis archive dc_43dbf411090f, sha256 3111da0ba88834789b5d9cd990d71d669c4ae4634539ccd2cd490da176a15b17)
BibTeX
@misc{dc43dbf411090f,
title = {HotPOT: Operator Transformer with Heterogeneous Physics Experts for Large-Scale PDE Pre-training — arXiv:2610.38218},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.38218},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_43dbf411090f; sha256 3111da0ba88834789b5d9cd990d71d669c4ae4634539ccd2cd490da176a15b17},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38218. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large-scale PDE pre-training trains a single model on the data from multiple partial differential equations (PDEs). However, adding heterogeneous PDEs with different governing equations, physical variables, and variable interactions does not always improve predictive performance across tasks. Existing PDE mixture-of-experts models mitigate cross-task interference through learned routing, but typically use homogeneous expert architectures, making it difficult to directly reflect differences in state evolution across equations. We introduce HotPOT, an operator transformer with heterogeneous physics experts for large-scale PDE pre-training. HotPOT uses a shared encoder to capture information common across PDEs, while each PDE family uses a neural-numerical expert that pairs a learnable predictor with a fixed numerical update containing no trainable parameters. Each predictor outputs the quantities required by its paired numerical update, which then computes the next state. This design allows different PDEs to share a common encoder while retaining their own learnable predictors and numerical updates. Experiments across five PDE families and six settings show that HotPOT outperforms MoE-POT in all 24 matched-scale comparisons before and after fine-tuning, reducing rollout error by 50.7% on average. Notably, the 17M model also surpasses substantially larger MoE-POT models, and the performance gains extend to zero-shot prediction under unseen physical conditions. Code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.38218 — 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 2026-11-01T02:12:44.112Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).