Improving the Euclidean Diffusion Generation of Manifold Data by Mitigating Score Function Singularity

Documenti analoghi

• Riemannian Denoising Diffusion Probabilistic Models
  di: Liu, Zichen, et al.
  Pubblicazione: (2025)
• Free Energy Surface Sampling via Reduced Flow Matching
  di: Liu, Zichen, et al.
  Pubblicazione: (2026)
• Diffusion Model for Manifold Data: Score Decomposition, Curvature, and Statistical Complexity
  di: Zhang, Zixuan, et al.
  Pubblicazione: (2026)
• Asymptotic Learning Curves for Diffusion Models with Random Features Score and Manifold Data
  di: George, Anand Jerry, et al.
  Pubblicazione: (2026)
• Multivariate Time Series Forecasting with Hybrid Euclidean-SPD Manifold Graph Neural Networks
  di: Fang, Yong, et al.
  Pubblicazione: (2025)