UPS: Towards Foundation Models for PDE Solving via Cross-Modal Adaptation

arXiv:2403.07187v1 Announce Type: new
Abstract: We introduce UPS (Unified PDE Solver), an effective and data-efficient approach to solve diverse spatiotemporal PDEs defined over various domains, dimensions, and resolutions. UPS unifies different PDEs into a consistent representation space and processes diverse collections of PDE data using a unified network architecture that combines LLMs with domain-specific neural operators. We train the network via a two-stage cross-modal adaptation process, leveraging ideas of modality alignment and multi-task learning. By adapting from pretrained LLMs and …

abstract architecture arxiv consistent cs.lg data dimensions diverse domains foundation modal network network architecture processes representation solve solver space type ups via