Unlearning methods that strongly erase concepts from text-to-image diffusion models consistently degrade performance on attribute binding, spatial reasoning, and counting tasks.
Unified concept editing in diffusion models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative 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.
- Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Models