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/

Zendy Plus

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

Zendy Tools

Zendy Open

Existing methods of level generation using latent variable models such asVAEs and GANs do so in segments and produce the final level by stitching theseseparately generated segments together. In this paper, we build on thesemethods by training VAEs to learn a sequential model of segment generation suchthat generated segments logically follow from prior segments. By furthercombining the VAE with a classifier that determines whether to place thegenerated segment to the top, bottom, left or right of the previous segment, weobtain a pipeline that enables the generation of arbitrarily long levels thatprogress in any of these four directions and are composed of segments thatlogically follow one another. In addition to generating more coherent levels ofnon-fixed length, this method also enables implicit blending of levels fromseparate games that do not have similar orientation. We demonstrate ourapproach using levels from Super Mario Bros., Kid Icarus and Mega Man, showingthat our method produces levels that are more coherent than previous latentvariable-based approaches and are capable of blending levels across games.

Sequential Segment-based Level Generation and Blending using Variational Autoencoders