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

In recent years, optimization in the learned latent space of deep generativemodels has been successfully applied to black-box optimization problems such asdrug design, image generation or neural architecture search. Existing modelsthereby leverage the ability of neural models to learn the data distributionfrom a limited amount of samples such that new samples from the distributioncan be drawn. In this work, we propose a novel image generative approach thatoptimizes the generated sample with respect to a continuously quantifiableproperty. While we anticipate absolutely no practically meaningful applicationfor the proposed framework, it is theoretically principled and allows toquickly propose samples at the mere boundary of the training data distribution.Specifically, we propose to use tree-based ensemble models as mathematicalprograms over the discrete latent space of vector quantized VAEs, which can beglobally solved. Subsequent weighted retraining on these queries allows toinduce a distribution shift. In lack of a practically relevant problem, weconsider a visually appealing application: the generation of happily smilingfaces (where the training distribution only contains less happy people) - andshow the principled behavior of our approach in terms of improved FID andhigher smile degree over baseline approaches.

Happy People -- Image Synthesis as Black-Box Optimization Problem in the Discrete Latent Space of Deep Generative Models