Reformulates CFD inference as self-supervised inpainting on tokenized velocity fields to produce reusable flow priors that handle boundary and geometry shifts better than supervised surrogates.
Stuart and Anima Anandkumar , title =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Inpainting physics: self-supervised learning for context-driven fluid simulation
Reformulates CFD inference as self-supervised inpainting on tokenized velocity fields to produce reusable flow priors that handle boundary and geometry shifts better than supervised surrogates.