Abstract: This paper proposes a novel deep reinforcement learning approach, named GRIDDPG (Graph-Reinforced Intelligent Dispatch with Deep Policy Gradient), for intra-day optimization dispatch in ...

This is the codebase for our work TetWeave: Isosurface Extraction using On-The-Fly Delaunay Tetrahedral Grids for Gradient-Based Mesh Optimization, accepted as Journal Paper at SIGGRAPH 2025. It ...

We're rolling out a new type of likelihood approximation using a fixed grid, and including gradients. These approximations should be a lot faster to compute, especially for SCCS analyses, and could ...