Unlearning methods that strongly erase concepts from text-to-image diffusion models consistently degrade performance on attribute binding, spatial reasoning, and counting tasks.
Towards resilient safety-driven unlearning for diffusion models against down- stream fine-tuning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Erasure or Erosion? Evaluating Compositional Degradation in Unlearned Text-To-Image Diffusion Models
Unlearning methods that strongly erase concepts from text-to-image diffusion models consistently degrade performance on attribute binding, spatial reasoning, and counting tasks.