AppleAnalysisAI ModelsAugust 14, 2026

When unlearning is free: low-influence points cut compute ~50%

Read original source →machinelearning.apple.com

Apple ML Research proposes an unlearning framework that drops low-influence training points before removal, shrinking the forget set. Across language and vision tasks, computational savings reach up to ~50 percent versus methods that treat all forget-set points equally.

1 source

More stories today

Open the live feed