Causal Counterfactual Framework Ablates Training Data Without Retraining

maier_ak · x · 2026-08-25

The team built a causal counterfactual framework that asks "what-if" a training example never existed. Using a diffusion-ensemble—many sub-models each trained on a data slice—they can ablate any component and generate a model without retraining.

Related event: Nature Communications study: individual sample influence in diffusion models shrinks with data scale(5 posts)→

Original post →

More from Research

Research channel →