AI Paper Atlas

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

NeurIPS 2026 · Graph learning › GNN architectures · approach: Physics-inspired GNNs

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy