pith. sign in

12 A Implementation details Training details.The active configuration uses L= 3 (comprising four levels, including l= 0 ); latent dimension 128; positional-encoding dimension 30

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.RO 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

PhySPRING: Structure-Preserving Reduction of Physics-Informed Twins via GNN

cs.RO · 2026-05-08 · unverdicted · novelty 7.0

PhySPRING uses differentiable GNNs to learn hierarchical coarsened spring-mass topologies and parameters from observations, delivering up to 2.3x speedup on PhysTwin benchmarks and comparable robot policy success rates in zero-shot Real2Sim substitution.

citing papers explorer

Showing 1 of 1 citing paper.

  • PhySPRING: Structure-Preserving Reduction of Physics-Informed Twins via GNN cs.RO · 2026-05-08 · unverdicted · none · ref 55

    PhySPRING uses differentiable GNNs to learn hierarchical coarsened spring-mass topologies and parameters from observations, delivering up to 2.3x speedup on PhysTwin benchmarks and comparable robot policy success rates in zero-shot Real2Sim substitution.