Research map / Image generation / Fast diffusion sampling
Landing with the Score: Riemannian Optimization through Denoising
Andrey Kharitenko, Zebang Shen, Riccardo De Santi, Niao He, Florian Dorfler
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 |
|---|---|---|---|
| lower noise level sigma in denoising landing flow (ablation) | Denoising Landing Flow · Brockett cost on O(10) | objective value | Improved |
| use DLF with learned score instead of exact landing flow | Denoising Landing Flow · Brockett cost on O(n) | objective value | Improved |
| run DRGD from best training trajectory | Denoising Riemannian Gradient Descent · Reference tracking (unicycle, double pendulum) | tracking error | Improved |
| iterates drift off the manifold | DRGD · Reference tracking | objective value | Mixed |
Closest papers by meaning
- Fast, Accurate Manifold Denoising by Tunneling Riemannian Optimization (ICML 2025 · similarity 0.91)
- The Geometry of Noise: Why Diffusion Models Don't Need Noise Conditioning (NeurIPS 2026 · similarity 0.89)
- Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes (ICML 2024 · similarity 0.88)
- Learning-Rate-Free Stochastic Optimization over Riemannian Manifolds (ICML 2024 · similarity 0.88)
- Improving the Euclidean Diffusion Generation of Manifold Data by Mitigating Score Function Singularity (NeurIPS 2025 · similarity 0.88)
- Local Manifold Approximation and Projection for Manifold-Aware Diffusion Planning (ICML 2025 · similarity 0.88)
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.
