Multigrid training accelerates convergence and improves generalization for receptor-conditioned 3D ligand generation by transferring parameters from coarse to fine graph and voxel resolutions.
Alex Nichol and Prafulla Dhariwal
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
KinetiDiff generates de novo ACVR1 inhibitors via docking-guided geometric diffusion, yielding a best candidate with 19.2% improved predicted affinity over the reference.
citing papers explorer
-
Multigrid Training for Molecular Generation using Graph Neural Networks
Multigrid training accelerates convergence and improves generalization for receptor-conditioned 3D ligand generation by transferring parameters from coarse to fine graph and voxel resolutions.
-
KinetiDiff: Docking-Guided Diffusion for De Novo ACVR1 Inhibitor Design in Fibrodysplasia Ossificans Progressiva
KinetiDiff generates de novo ACVR1 inhibitors via docking-guided geometric diffusion, yielding a best candidate with 19.2% improved predicted affinity over the reference.