A diffusion model with hierarchical physics-feature conditioning and a thermal-conduction-inspired connectivity loss reduces compliance error and floating material in topology optimization.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2years
2026 2verdicts
CONDITIONAL 2roles
background 1polarities
background 1representative citing papers
A single trained parameterized NA-PINN coupled to FDM delivers low-error solutions for gravity-driven draining across multiple time steps and initial conditions without retraining or simulation data.
citing papers explorer
-
HPG-Diff: Hierarchical physics-guided diffusion with differentiable connectivity constraints for topology optimization
A diffusion model with hierarchical physics-feature conditioning and a thermal-conduction-inspired connectivity loss reduces compliance error and floating material in topology optimization.
-
A Numerical Method for Coupling Parameterized Physics-Informed Neural Networks and FDM for Advanced Thermal-Hydraulic System Simulation
A single trained parameterized NA-PINN coupled to FDM delivers low-error solutions for gravity-driven draining across multiple time steps and initial conditions without retraining or simulation data.