gflownet-3bdac277·1 events·first seen Aliases: GFlowNet
Researchers introduce TILDE (TILt-based Distributional Erasure), a method for concept unlearning in text-to-image diffusion models that frames the problem as distributional alignment rather than direct suppression. The approach defines a target distribution as the minimum-deviation conditional from the pretrained model subject to a forgetting constraint, instantiated via residual GFlowNet training. TILDE is evaluated across objects, artistic styles, and characters, claiming improved retention and distributional fidelity over prior baselines while maintaining strong forgetting. The work addresses practical deployment concerns including copyright, privacy, and safety regulations.