Research map / Image generation / Fast diffusion sampling
Practical and Asymptotically Exact Conditional Sampling in Diffusion Models
Luhuan Wu, Brian L. Trippe, Christian A Naesseth, David Blei, John Patrick Cunningham
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 |
|---|---|---|---|
| increase number of particles K (ablation) | TDS · MNIST class-conditional generation | classification accuracy | Improved |
| TDS vs Gradient Guidance (K=1) | TDS · 2D Gaussian conditional mean estimation | mean estimation error | Improved |
| increase particles K in motif scaffolding (ablation) | TDS on FrameDiff · Motif scaffolding 5IUS | success rate | Improved |
| add motif location and rotation degrees of freedom (ablation) | TDS (K=1) · Motif scaffolding 5IUS | success rate: 0% -> higher | Improved |
| increase twist scale (ablation) | TDS (8 particles) · Motif scaffolding 5IUS | success rate | Mixed |
| TDS on FrameDiff instead of conditionally trained RFdiffusion | motif scaffolding · 24-problem benchmark | success rate: 11/24 vs 11/24 higher | Mixed |
Closest papers by meaning
- BridgeTwist: Twisting Schrödinger Bridges for Training-Free Conditional Sampling (NeurIPS 2026 · similarity 0.89)
- Conditional Synthesis of 3D Molecules with Time Correction Sampler (NeurIPS 2024 · similarity 0.89)
- On scalable and efficient training of diffusion samplers (NeurIPS 2025 · similarity 0.88)
- Efficient Integrators for Diffusion Generative Models (ICLR 2024 · similarity 0.88)
- Consistent Sampling and Simulation: Molecular Dynamics with Energy-Based Diffusion Models (NeurIPS 2025 · similarity 0.88)
- A Mean-Field Framework for Inference-Time Distributional Control of Diffusion Models (NeurIPS 2026 · 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.
