AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Aligning Optimization Trajectories with Diffusion Models for Constrained Design Generation

Giorgio Giannone, Akash Srivastava, Ole Winther, Faez Ahmed

NeurIPS 2023 · Image generation › Fast diffusion sampling · approach: Distributional control of diffusion · 11 citations (OpenAlex)

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 changedWhereMeasuredEffect
add trajectory alignment (clean-space) to DOM (ablation)DOM with kernel conditioning · in-distribution topology generationaverage compliance error (%): 13.61 -> 4.44Improved
add trajectory alignment (clean-space) to DOM (ablation)DOM with kernel conditioning · ablation, out-of-distributionmedian compliance error (%): 5.62 -> 3.47Improved
add dense kernel relaxation (ablation)DOM with clean TA · ablation, out-of-distributionmedian compliance error (%): 9.01 -> 3.47Improved
add dense kernel relaxation (ablation)DOM with clean TA · ablation, in-distributionmedian compliance error (%): 1.11 -> 0.74Improved
match trajectories in clean space instead of noisy, performance, or multi-resolution space (ablation)DOM with kernel and TA · in-distributionmedian compliance error (%): 0.74 vs 2.08 (NOISY), 2.41 (PERF), 34.95 (MULTI)Improved
replace DOM with Consistency Model objective for kernel conditioned model (ablation)kernel-conditioned diffusion · in-distributionmedian compliance error (%): 0.74 -> 2.20Hurt
use DOM instead of TopoDiff-G with only 2 sampling stepsfew-step sampling · in-distributionmedian compliance error (%): 436.83 -> 1.46Improved
use DOM instead of TopoDiff-G with 10 sampling stepsfew-step sampling · out-of-distributionmedian compliance error (%): 2.55 -> 3.69Hurt
add 10 steps of SIMP post-optimization to DOM (ablation)DOM · out-of-distributionmedian compliance error (%): 3.47 -> 1.15Improved
add only 5 steps of SIMP post-optimization (ablation)DOM · out-of-distributionfloating material (%): 8.02 -> 10.19Hurt
remove FEM preprocessing via kernel relaxation (DOM vs TopoDiff)inference pipeline · 64x64 inferenceinference time (s): 5.54 -> 2.35Improved
DOM versus TopoDiff on floating material with 100 stepsDOM · in-distributionfloating material (%): 5.79 -> 6.72Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy