Research map / Image generation / Fast diffusion sampling
Infinite-Dimensional Diffusion Models
Jakiw Pidstrigach, Youssef Marzouk, Sebastian Reich, Sven Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use smoother Gaussian noise (alpha_noise=1) and Cameron-Martin loss norm (IDDM1) instead of white noise (WNDM) (ablation) | Diffusion model · Manifold distribution on Cameron-Martin sphere (alpha_data=2, D=256) | sample smoothness | Improved |
| Use smoother Gaussian noise (IDDM1) instead of white noise (WNDM) (ablation) | Diffusion model · Manifold distribution on Cameron-Martin sphere | one-dimensional marginals | No clear effect |
| Match noise covariance to prior (alpha_noise=4, alpha_loss=2; IDDM2) instead of WNDM (ablation) | Diffusion model · Volatility estimation conditional sampling | sample smoothness class | Improved |
| Match noise covariance to prior (IDDM2) instead of WNDM (ablation) | Diffusion model · Volatility estimation conditional sampling | posterior marginal match | Improved |
| Use alpha_loss=3 instead of alpha_loss=2 in IDDM2 (ablation) | IDDM2 · Volatility estimation conditional sampling | sample quality | No clear effect |
Closest papers by meaning
- Towards Non-Asymptotic Convergence for Diffusion-Based Generative Models (ICLR 2024 · similarity 0.91)
- Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models (NeurIPS 2024 · similarity 0.90)
- Manifolds, Random Matrices and Spectral Gaps: The geometric phases of generative diffusion (ICLR 2025 · similarity 0.90)
- Revisiting Diffusion Model Predictions Through Dimensionality (NeurIPS 2026 · similarity 0.90)
- On gauge freedom, conservativity and intrinsic dimensionality estimation in diffusion models (ICLR 2024 · similarity 0.89)
- Lipschitz Singularities in Diffusion Models (ICLR 2024 · similarity 0.89)
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.
