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: single-sample causal influence in diffusion models shrinks with scale(5 posts)→

Original post →

More from Research

• Interpretability paper incoming: in-depth look at testing explanations on modern LLMs — burny_tech · 2026-10-16
• Better-learning models tend to be more interpretable, argues Nick Cammarata — burny_tech · 2026-10-16
• 'Interp was mostly hopeless before — now it's automatable': Cammarata on interpretability — burny_tech · 2026-10-16
• Cornell and Amazon revisit the 16x pretraining compute gap: diffusion LMs need only 3-8x — LucaAmb · 2026-10-16
• AI trained on the fraction of human intelligence that fit the page — r0ck3t23 · 2026-10-16
• Quotient Recurrent Reasoners hit 97.9% on Sudoku-Extreme with 78% fewer loops — burny_tech · 2026-10-16

Research channel →