AI Paper Atlas

Research map / Probabilistic and scientific modeling / Bayesian optimization

Generative Modeling from Black-Box Corruptions via Self-Consistent Stochastic Interpolants

Chirag Modi, Jiequn Han, Eric Vanden-Eijnden, Joan Bruna

ICLR 2026 · Probabilistic and scientific modeling › Bayesian optimization · approach: Offline black-box optimization with surrogates

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
use SCSI instead of DPS (trained on clean data)SCSI · Gaussian blur sigma_n=0.25LPIPS: 0.025 -> 0.015Improved
use SCSI instead of DPS at low noiseSCSI · Motion blur sigma_n=1e-6LPIPS: 0.0026 -> 0.0069Hurt
use SCSI instead of Ambient DiffusionSCSI · CIFAR-10 random maskingFID: 18.85 -> 6.74 (rho 0.4 vs 0.5)Improved
use SCSI instead of EM PosteriorSCSI · CIFAR-10 random maskingFID: 6.76 -> 6.74 (rho=0.50)No clear effect
use SDE instead of ODE transport at high noise (ablation)SCSI · Two-moon, sigma_n=1.0restoration stabilityImproved
use SDE instead of ODE in high-dimensional tasks (ablation)SCSI · imaginghyperparameter sensitivityHurt
increase inner-loop transport steps T_tr from 1 to 1000 (ablation)SCSI · Two-moon AWGNWasserstein distance: 0.0491 -> 0.0593Hurt
increase T_tr from 1 to 10 (ablation)SCSI · Two-moon AWGNWasserstein distance: 0.0491 -> 0.0460No clear effect

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