Schrödinger Bridge-based generative semantic communication (SBGSC) enables direct optimal distribution transport from semantics to images, cutting hallucinations and achieving 38% better FID, 49.3% better SSIM, and over 8x faster inference than prior GSC methods.
A class of wasserstein metrics for probability distributions
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
KL divergence between a general distribution and a perturbed Gaussian reference remains stable with an optimal sqrt(ε) degradation rate under finite second-moment conditions.
citing papers explorer
-
Optimally Bridging Semantics and Data: Generative Semantic Communication via Schr\"odinger Bridge
Schrödinger Bridge-based generative semantic communication (SBGSC) enables direct optimal distribution transport from semantics to images, cutting hallucinations and achieving 38% better FID, 49.3% better SSIM, and over 8x faster inference than prior GSC methods.
-
Optimal Stability of KL Divergence under Gaussian Perturbations
KL divergence between a general distribution and a perturbed Gaussian reference remains stable with an optimal sqrt(ε) degradation rate under finite second-moment conditions.