Research map / Image generation / Fast diffusion sampling
Riemannian Diffusion Models
Chin-Wei Huang, Milad Aghajohari, Joey Bose, Prakash Panangaden, Aaron Courville
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 |
|---|---|---|---|
| learn importance-sampling proposal over time integral (ablation) | RDM · Earthquake | training loss variance | Improved |
| integrate inference SDE with 100 time steps vs direct Brownian sampling (ablation) | RDM · Glycine torus | training loss | No clear effect |
| use fewer numerical integration time steps (ablation) | RDM · Glycine torus | estimated loss | Hurt |
| RDM vs Riemannian Score-Based model | Riemannian Score-Based · Volcano | test NLL: -5.56 -> -6.61 | Improved |
| RDM vs Mixture of Power Spherical on RNA torus | MoPS · RNA torus | test NLL: 4.08 -> -3.70 | Improved |
Closest papers by meaning
- Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes (ICML 2024 · similarity 0.91)
- Efficient Diffusion Models for Symmetric Manifolds (ICML 2025 · similarity 0.89)
- Improving the Euclidean Diffusion Generation of Manifold Data by Mitigating Score Function Singularity (NeurIPS 2025 · similarity 0.88)
- Unified Framework for Diffusion Generative Models in SO(3): Applications in Computer Vision and Astrophysics (AAAI 2024 · similarity 0.87)
- Riemannian Consistency Model (NeurIPS 2025 · similarity 0.87)
- Toward a Unified Geometry Understanding : Riemannian Diffusion Framework for Graph Generation and Prediction (NeurIPS 2025 · similarity 0.87)
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.
