LASS-ODE: Scaling ODE Computations to Connect Foundation Models with Dynamical Physical Systems

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Haoran, Xiao, Chenhan, Mai, Lihao, Weng, Yang, Blasch, Erik
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911420422029312
author Li, Haoran
Xiao, Chenhan
Mai, Lihao
Weng, Yang
Blasch, Erik
author_facet Li, Haoran
Xiao, Chenhan
Mai, Lihao
Weng, Yang
Blasch, Erik
contents Foundation models have transformed language, vision, and time series data analysis, yet progress on dynamic predictions for physical systems remains limited. Given the complexity of physical constraints, two challenges stand out. $(i)$ Physics-computation scalability: physics-informed learning can enforce physical regularization, but its computation (e.g., ODE integration) does not scale to extensive systems. $(ii)$ Knowledge-sharing efficiency: the attention mechanism is primarily computed within each system, which limits the extraction of shared ODE structures across systems. We show that enforcing ODE consistency does not require expensive nonlinear integration: a token-wise locally linear ODE representation preserves physical fidelity while scaling to foundation-model regimes. Thus, we propose novel token representations that respect locally linear ODE evolution. Such linearity substantially accelerates integration while accurately approximating the local data manifold. Second, we introduce a simple yet effective inter-system attention that augments attention with a common structure hub (CSH) that stores shared tokens and aggregates knowledge across systems. The resulting model, termed LASS-ODE (\underline{LA}rge-\underline{S}cale \underline{S}mall \underline{ODE}), is pretrained on our $40$GB ODE trajectory collections to enable strong in-domain performance, zero-shot generalization across diverse ODE systems, and additional improvements through fine-tuning.
format Preprint
id arxiv_https___arxiv_org_abs_2602_01009
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LASS-ODE: Scaling ODE Computations to Connect Foundation Models with Dynamical Physical Systems
Li, Haoran
Xiao, Chenhan
Mai, Lihao
Weng, Yang
Blasch, Erik
Machine Learning
Artificial Intelligence
Foundation models have transformed language, vision, and time series data analysis, yet progress on dynamic predictions for physical systems remains limited. Given the complexity of physical constraints, two challenges stand out. $(i)$ Physics-computation scalability: physics-informed learning can enforce physical regularization, but its computation (e.g., ODE integration) does not scale to extensive systems. $(ii)$ Knowledge-sharing efficiency: the attention mechanism is primarily computed within each system, which limits the extraction of shared ODE structures across systems. We show that enforcing ODE consistency does not require expensive nonlinear integration: a token-wise locally linear ODE representation preserves physical fidelity while scaling to foundation-model regimes. Thus, we propose novel token representations that respect locally linear ODE evolution. Such linearity substantially accelerates integration while accurately approximating the local data manifold. Second, we introduce a simple yet effective inter-system attention that augments attention with a common structure hub (CSH) that stores shared tokens and aggregates knowledge across systems. The resulting model, termed LASS-ODE (\underline{LA}rge-\underline{S}cale \underline{S}mall \underline{ODE}), is pretrained on our $40$GB ODE trajectory collections to enable strong in-domain performance, zero-shot generalization across diverse ODE systems, and additional improvements through fine-tuning.
title LASS-ODE: Scaling ODE Computations to Connect Foundation Models with Dynamical Physical Systems
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2602.01009