A pretrained PDE foundation model fine-tuned with only PDE residuals and boundary conditions reaches within about 2.5x of supervised fine-tuning on seven of eight 2D benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unsupervised Adaptation of PDE Foundation Models
A pretrained PDE foundation model fine-tuned with only PDE residuals and boundary conditions reaches within about 2.5x of supervised fine-tuning on seven of eight 2D benchmarks.