Research map / Image generation / Fast diffusion sampling
Riemannian Score-Based Generative Modelling
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| RSGM vs best baseline on Volcano | RSGM · Volcano | NLL: -4.92 vs -6.05 (Riemannian CNF) | Hurt |
| RSGM vs Moser Flow on Flood | RSGM · Flood | NLL: 0.57 -> 0.45 | Helped |
| RSGM vs Moser Flow on Fire | RSGM · Fire | NLL: -1.28 -> -1.33 | Helped |
| RSGM on Earthquake vs stereographic SGM | RSGM · Earthquake | NLL: -0.19 vs -0.19 | No clear effect |
| RSGM vs Moser Flow on high-dim torus | RSGM · torus T^d | likelihood | Helped |
| RSGM vs Exp-wrapped SGM on SO(3) M=64 | RSGM · SO(3) | log-likelihood: -0.58 -> -0.49 | Helped |
| RSGM vs Moser Flow on SO(3) function evaluations | RSGM · SO(3) M=16 | NFE (1e3): 2.3 -> 0.1 | Helped |
Closest papers by meaning
- Unified Framework for Diffusion Generative Models in SO(3): Applications in Computer Vision and Astrophysics (AAAI 2024 · similarity 0.88)
- Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models (NeurIPS 2025 · similarity 0.87)
- Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes (ICML 2024 · similarity 0.86)
- Improving the Euclidean Diffusion Generation of Manifold Data by Mitigating Score Function Singularity (NeurIPS 2025 · similarity 0.86)
- Algorithm- and Data-Dependent Generalization Bounds for Diffusion Models (NeurIPS 2025 · similarity 0.86)
- Kernel-Gradient Drifting Models (NeurIPS 2026 · similarity 0.85)
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.