A physics-guided FiLM convolutional neural network with soft OAM conservation loss reconstructs the joint radial-azimuthal modal distribution of high-dimensional SPDC entanglement at high fidelity and 128x speedup over numerical simulation.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
quant-ph 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Spectral filters produce a flat-dip-rise profile in near-field conditional position width for non-degenerate SPDC, narrowing by ~10% at a bandwidth set by the crystal phase-matching width, while degenerate cases remain pump-limited and filter-invariant.
citing papers explorer
-
Learning high-dimensional quantum entanglement through physics-guided neural networks
A physics-guided FiLM convolutional neural network with soft OAM conservation loss reconstructs the joint radial-azimuthal modal distribution of high-dimensional SPDC entanglement at high fidelity and 128x speedup over numerical simulation.
-
Entanglement certification in bulk nonlinear crystals for degenerate and non-degenerate SPDC: spectral filter effects on transverse spatial correlations
Spectral filters produce a flat-dip-rise profile in near-field conditional position width for non-degenerate SPDC, narrowing by ~10% at a bandwidth set by the crystal phase-matching width, while degenerate cases remain pump-limited and filter-invariant.