{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"Research Square"}],"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T08:06:30Z","timestamp":1789027590038,"version":"build-2803163510"},"posted":{"date-parts":[[2026,9,10]]},"group-title":"In Review","reference-count":0,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T00:00:00Z","timestamp":1788998400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,7,30]]},"abstract":"<title>Abstract<\/title>\n                <p>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 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.<\/p>","DOI":"10.21203\/rs.3.rs-10537151\/v1","type":"posted-content","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T07:11:00Z","timestamp":1789024260000},"source":"Crossref","is-referenced-by-count":0,"title":["PatternFormer: Learning Multiple Solution Patterns in Reaction--Diffusion Systems"],"prefix":"10.21203","author":[{"given":"Wenrui","family":"Hao","sequence":"first","affiliation":[{"name":"Penn State University Park"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhipeng","family":"Chang","sequence":"additional","affiliation":[{"name":"Pennsylvania State University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenpeng","family":"Yin","sequence":"additional","affiliation":[{"name":"Penn State University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","container-title":[],"original-title":[],"link":[{"URL":"https:\/\/www.researchsquare.com\/article\/rs-10537151\/v1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.researchsquare.com\/article\/rs-10537151\/v1.html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T07:11:06Z","timestamp":1789024266000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.researchsquare.com\/article\/rs-10537151\/v1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,10]]},"references-count":0,"URL":"https:\/\/doi.org\/10.21203\/rs.3.rs-10537151\/v1","relation":{},"subject":[],"published":{"date-parts":[[2026,9,10]]},"subtype":"preprint"}}