A final-output-only loss with learned neuron masks erases concepts from flow-based image generators more robustly than per-step fine-tuning methods.
Unsafe diffusion: On the generation of unsafe images and hateful memes from text-to-image models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Minimalist Concept Erasure in Generative Models
A final-output-only loss with learned neuron masks erases concepts from flow-based image generators more robustly than per-step fine-tuning methods.