Research map / Graph learning / GNN architectures
PhySPRING: Structure-Preserving Reduction of Physics-Informed Digital Twins via Graph Neural Networks
Yixiong Jing, Xingyuan Chen, Guangming Wang, Olaf Wysocki, Haibing Wu, Brian Sheil
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes PhySPRING, a method that reduces physics-informed digital twins (spring-mass models) to a physically meaningful, lower-complexity structure using graph neural networks, for real-to-sim-to-real robotics.
Problem
Physics-based digital twins reconstructed from visual data (e.g., spring-mass systems) inherit the resolution of the visual reconstruction rather than being reduced to the physical complexity required for dynamics prediction under interaction.
Approach
Reduces an explicit spring-mass digital twin to a structure-preserving lower-complexity model using graph neural networks, so that the reduced model keeps physical structure while matching the required complexity.
Closest papers by meaning
- Boba: Batched Simulation for Physics-Based Gaussian Digital Twins (ECCV 2026 · similarity 0.89)
- DeformGen: Dynamics-Based Topology Augmentation for Deformable Manipulation Policy Learning (NeurIPS 2026 · similarity 0.86)
- RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins (CVPR 2025 · similarity 0.86)
- Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation (ICLR 2025 · similarity 0.85)
- A Riemannian Framework for Learning Reduced-order Lagrangian Dynamics (ICLR 2025 · similarity 0.85)
- PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation (NeurIPS 2025 · similarity 0.85)
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.
