Dmsh is a new multi-agent RL framework that formulates mesh generation as an MDP and uses three coordinated agents plus curriculum learning to produce globally conforming all-quad meshes without post-processing.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
math.NA 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A novel FFT-accelerated iterative method minimizes a relaxed Ginzburg-Landau energy on an extended domain to generate high-quality quadrilateral meshes with guaranteed convergence.
citing papers explorer
-
Dmsh: A Multi-Agent Reinforcement Learning Framework for All-Quad Mesh Generation
Dmsh is a new multi-agent RL framework that formulates mesh generation as an MDP and uses three coordinated agents plus curriculum learning to produce globally conforming all-quad meshes without post-processing.
-
An efficient and stable diffusion generated method for quadrilateral mesh generation in general domains
A novel FFT-accelerated iterative method minimizes a relaxed Ginzburg-Landau energy on an extended domain to generate high-quality quadrilateral meshes with guaranteed convergence.