English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

While diffusion models demonstrate a remarkable capability for generatinghigh-quality images, their tendency to `replicate' training data raises privacyconcerns. Although recent research suggests that this replication may stem fromthe insufficient generalization of training data captions and duplication oftraining images, effective mitigation strategies remain elusive. To addressthis gap, our paper first introduces a generality score that measures thecaption generality and employ large language model (LLM) to generalize trainingcaptions. Subsequently, we leverage generalized captions and propose a noveldual fusion enhancement approach to mitigate the replication of diffusionmodels. Our empirical results demonstrate that our proposed methods cansignificantly reduce replication by 43.5% compared to the original diffusionmodel while maintaining the diversity and quality of generations. Code isavailable at https://github.com/HowardLi0816/dual-fusion-diffusion.

Mitigate Replication and Copying in Diffusion Models with Generalized Caption and Dual Fusion Enhancement