AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

End-to-End Differentiable Diffusion Conditioning for Physics-Informed Optimization

Ricardo Luna Gutierrez, Vineet Gundecha, Rahman Ejaz, Varchas Gopalaswamy, Riccardo Betti, Sahand Ghorbanpour, Aarne Lees, Soumyendu Sarkar

NeurIPS 2026 · Image generation › Fast diffusion sampling · approach: Fast diffusion ODE solvers · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes an end-to-end differentiable diffusion conditioning method for offline model-based optimization of physical systems, as described in the truncated abstract.

Problem

Offline model-based optimization of high-dimensional physical systems, where designs must be improved using only a fixed dataset and no test-time access to the true objective; existing methods suffer from conservatism, unconstrained surrogate exploitation, or act as static inference.

Approach

Uses a diffusion model conditioned end-to-end through a differentiable pipeline for physics-informed optimization; the abstract is truncated so the specific mechanism is not fully stated.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
optimize the conditioning with gradients through the DDIM chain instead of a forward-only conditioning sweep (Brute Force)frozen diffusion proposer · ICF Topneutron yield improvement (%): 3.93 -> 10.06Improved
optimize the conditioning with gradients through the DDIM chain instead of a forward-only conditioning sweep (Brute Force)frozen diffusion proposer · ICF Standardneutron yield improvement (%): 4.66 -> 17.98Improved
use D2C instead of the best generative baseline GTGdata center scheduling · Data center schedulingcarbon footprint reduction (%): 5.50 -> 8.98Improved
optimize conditioning instead of latent noise (real-world tasks) (ablation)D2C · ICF and DCconstraint-satisfying gainImproved
optimize initial latent noise (conditioning fixed to c=1.0) instead of the 1-D conditioning (ablation)D2C · Design-Benchnormalized scoreImproved
D2C versus DDOM on Ant MorphologyD2C · Design-Bench Antnormalized score: 0.925 (DDOM) vs 0.876Hurt
D2C versus GTG on D'KittyD2C · Design-Bench D'Kittynormalized score: 0.976 (GTG) vs 0.974No clear effect
run D2C on expert-designed pulses with direct LILAC simulationD2C · ICF expert pulses (20)average yield gain (%): +9.8%Improved

Limitations

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