Paper Detail
Zhipeng Chang, Wenpeng Yin, Wenrui Hao
Many nonlinear models across physics, chemistry, and biology exhibit multiple solutions for the same parameters, and capturing this entire solution set is essential for understanding pattern-forming systems. Yet existing learned surrogates are fundamentally single-valued: neural operators map each parameter to a single output, and physics-informed neural networks converge to one branch. We develop \textbf{PatternFormer} (PF), a large language model-based framework for learning the multiple solutions of nonlinear partial differential equations. By transforming unordered coexisting solutions into canonical sequences, PF produces structured solution sets in a single autoregressive pass, terminating automatically for finite families and enforcing physical residual constraints for unbounded ones. On nonlinear elliptic problems it recovers all solution branches in one inference step; on Gray--Scott it generates coexisting Turing patterns, including physically valid states absent from the reference data and beyond training. PF can also be sequentially fine-tuned across multistable systems, toward general foundation models for solution landscapes.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{chang2026patternformer,
title = {PatternFormer: Learning Multiple Solution Patterns in Reaction--Diffusion Systems},
author = {Zhipeng Chang and Wenpeng Yin and Wenrui Hao},
year = {2026},
abstract = {Many nonlinear models across physics, chemistry, and biology exhibit multiple solutions for the same parameters, and capturing this entire solution set is essential for understanding pattern-forming systems. Yet existing learned surrogates are fundamentally single-valued: neural operators map each parameter to a single output, and physics-informed neural networks converge to one branch. We develop \textbackslash{}textbf\{PatternFormer\} (PF), a large language model-based framework for learning the multiple solut},
url = {https://arxiv.org/abs/2608.12286},
keywords = {math-ph},
eprint = {2608.12286},
archiveprefix = {arXiv},
}
{}