<ul><li>Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models</li><li>Diffusion generative models have advanced significantly, but they have become larger and more complex, creating computational challenges in resource-constrained scenarios.</li><li>Pruning and knowledge distillation can reduce computational demands while preserving generation quality, but they can also propagate undesirable behaviors.</li><li>A new bilevel optimization framework is proposed to consolidate fine-tuning and unlearning processes, selectively suppressing the generation of unwanted content in diffusion models.</li></ul>

Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models

Discover more