Airfoil drag minimization is reformulated as optimization in the latent space of a diffusion model, with CFD adjoint gradients backpropagated through the diffusion sampler; the approach beats a Hicks-Henne baseline in transonic RANS tests.
Dynamic geometry control for robust aerodynamic shape optimization,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CE 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Adjoint-Based Aerodynamic Shape Optimization with a Manifold Constraint Learned by Diffusion Models
Airfoil drag minimization is reformulated as optimization in the latent space of a diffusion model, with CFD adjoint gradients backpropagated through the diffusion sampler; the approach beats a Hicks-Henne baseline in transonic RANS tests.