Research map / Probabilistic and scientific modeling / Dynamical systems
Accurately Solving Rod Dynamics with Graph Learning
Han Shao, Tassilo Kugelstadt, Torsten Hädrich, Wojtek Palubicki, Jan Bender, Soren Pirk, Dominik Michels
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace CG initial guess (zeros) with COPINGNet prediction | PBD rod solver · Tree simulation 10 rods | runtime improvement: 17.0% | Improved |
| increase tree size from 10 to 70 rods | COPINGNet-assisted PBD · Tree simulation | runtime improvement: 17.0% -> 11.1% | Hurt |
| use COPINGNet only for initial guess instead of replacing the constraint projection end-to-end (ablation) | COPINGNet · Bending rod, rod length stability | rod length stability | Improved |
| replace COPINGNet guess with k-NN guess (k=3) (ablation) | COPINGNet-assisted PBD · Bending rod and helix | speedup | Hurt |
| more nodes per rod | COPINGNet-assisted PBD · Bending rod and helix | speedup: up to 50% | Improved |
| few nodes in the rod | COPINGNet-assisted PBD · Bending rod | speedup | Hurt |
| simulate beyond the 50 training time steps | COPINGNet-assisted PBD · Elastic helix | speedup: approximately 50% | No clear effect |
| simulate beyond the 50 training time steps | COPINGNet-assisted PBD · Bending rod | speedup | Hurt |
Closest papers by meaning
- Diffusion-Based Hierarchical Graph Neural Networks for Simulating Nonlinear Solid Mechanics (NeurIPS 2025 · similarity 0.86)
- EGODE: An Event-attended Graph ODE Framework for Modeling Rigid Dynamics (NeurIPS 2024 · similarity 0.85)
- MaNGO — Adaptable Graph Network Simulators via Meta-Learning (NeurIPS 2025 · similarity 0.85)
- PhyMPGN: Physics-encoded Message Passing Graph Network for spatiotemporal PDE systems (ICLR 2025 · similarity 0.84)
- Breaking the Discretization Barrier of Continuous Physics Simulation Learning (NeurIPS 2025 · similarity 0.84)
- EvoMesh: Adaptive Physical Simulation with Hierarchical Graph Evolutions (ICML 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
