GB-FESO backpropagates a KL-divergence loss through a frozen conditional diffusion model's sampling trajectory to optimize system parameters so the generated ensemble matches a target free-energy surface.
Science Advances , month =
2 Pith papers cite this work, alongside 7 external citations. Polarity classification is still indexing.
2
Pith papers citing it
7
external citations · OpenAlex
years
2026 2representative citing papers
GNN-based MD simulators achieve stable structure-only initialization and reliable OOD generalization through inference-time physics optimization and a GNN barostat on elastic network compression tasks.
citing papers explorer
-
Gradient-Based Inverse Design of Free-Energy Landscapes with Diffusion Models
GB-FESO backpropagates a KL-divergence loss through a frozen conditional diffusion model's sampling trajectory to optimize system parameters so the generated ensemble matches a target free-energy surface.
-
Enabling Structure-Only Initialization and Out-of-Distribution Generalization in GNN-based Molecular Dynamics Simulators
GNN-based MD simulators achieve stable structure-only initialization and reliable OOD generalization through inference-time physics optimization and a GNN barostat on elastic network compression tasks.