AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Generative Inverse Design with Abstention via Diagonal Flow Matching

Miguel de Campos, Werner Krebs, Hanno Gottschalk

ICML 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Flow matching generative modeling · 0 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
anchor labels to zero and pair all design coordinates with noise (Diag-CFM instead of CFM) (ablation)conditional flow matching · Gas Turbine Combustorround-trip error: 1.85 × 10−2 -> 1.27 × 10−3Improved
zero-anchoring instead of standard CFM pairing (ablation)conditional flow matching · Gas Turbine Combustorforward MSE: 1.70 × 10−2 -> 1.39 × 10−3Improved
zero-anchoring instead of standard CFM pairing (ablation)conditional flow matching · Unifoilround-trip error: 1.10 × 10−2 -> 1.68 × 10−3Improved
zero-anchoring instead of standard CFM pairing (ablation)conditional flow matching · DTLZ2 P=12round-trip error: 3.20 × 10−2 -> 9.10 × 10−4Improved
zero-anchoring instead of standard CFM pairing (ablation)conditional flow matching · DTLZ2 P=100round-trip error: 4.52 × 10−2 -> 5.26 × 10−3Improved
zero-anchoring instead of standard CFM pairing (ablation)conditional flow matching · FashionMNIST statistics (P=784)forward MSE: 2.56 × 10−2 -> 7.20 × 10−4Improved
zero-anchoring instead of standard CFM pairing (ablation)conditional flow matching · Thin film coating (P=128)round-trip error: 2.902 × 10−2 -> 2.247 × 10−2Improved
permute order of design and label coordinates (ablation)standard CFM vs Diag-CFM · Gas Turbine Combustorfinal round-trip errorHurt
use Diag-CFM instead of INN for forward prediction at high design dimensionDiag-CFM · DTLZ2 P=100forward MSE: 1.22 × 10−3 (INN) vs 9.58 × 10−3 (Diag-CFM)Hurt
use Diag-CFM instead of CFM/INN for design diversityDiag-CFM · Gas Turbine Combustordesign diversity: 5.27 × 10−2 (INN) vs 2.95 × 10−2 (Diag-CFM)Hurt
select among K=10 generations with Zero-Deviation or Self-Consistency (ablation)Diag-CFM · select-bestimprovement over random selection: 5-31% over randomImproved
select among generations with Ensemble Variance or FM Loss (ablation)Diag-CFM · select-bestimprovement over random selectionHurt

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