Please use this identifier to cite or link to this item: https://www.um.edu.mt/library/oar/handle/123456789/121431
Full metadata record
DC FieldValueLanguage
dc.contributor.authorZammit, Marvin-
dc.contributor.authorLiapis, Antonios-
dc.contributor.authorYannakakis, Georgios N.-
dc.date.accessioned2024-04-26T10:05:32Z-
dc.date.available2024-04-26T10:05:32Z-
dc.date.issued2024-
dc.identifier.citationZammit, M., Liapis, A., & Yannakakis, G. N. (2024). MAP-elites with transverse assessment for multimodal problems in creative domains. International Conference on Computational Intelligence in Music, Sound, Art and Design (EvoMusArt). Aberystwyth, Wales, UKen_GB
dc.identifier.urihttps://www.um.edu.mt/library/oar/handle/123456789/121431-
dc.description.abstractThe recent advances in language-based generative models have paved the way for the orchestration of multiple generators of different artefact types (text, image, audio, etc.) into one system. Presently, many open-source pre-trained models combine text with other modalities, thus enabling shared vector embeddings to be compared across different generators. Within this context we propose a novel approach to handle multimodal creative tasks using Quality Diversity evolution. Our contribution is a variation of the MAP-Elites algorithm, MAP-Elites with Transverse Assessment (MEliTA), which is tailored for multimodal creative tasks and leverages deep learned models that assess coherence across modalities. MEliTA decouples the artefacts’ modalities and promotes cross-pollination between elites. As a test bed for this algorithm, we generate text descriptions and cover images for a hypothetical video game and assign each artefact a unique modality-specific behavioural characteristic. Results indicate that MEliTA can improve text-to-image mappings within the solution space, compared to a baseline MAP-Elites algorithm that strictly treats each image-text pair as one solution. Our approach represents a significant step forward in multimodal bottom-up orchestration and lays the groundwork for more complex systems coordinating multimodal creative agents in the future.en_GB
dc.language.isoenen_GB
dc.publisherSpringeren_GB
dc.rightsinfo:eu-repo/semantics/openAccessen_GB
dc.subjectRoboticsen_GB
dc.subjectEvolutionary roboticsen_GB
dc.subjectGenetic programming (Computer science)en_GB
dc.subjectArtificial intelligenceen_GB
dc.subjectComputational intelligenceen_GB
dc.subjectAlgorithmsen_GB
dc.subjectGenerative programming (Computer science)en_GB
dc.titleMAP-elites with transverse assessment for multimodal problems in creative domainsen_GB
dc.typeconferenceObjecten_GB
dc.rights.holderThe copyright of this work belongs to the author(s)/publisher. The rights of this work are as defined by the appropriate Copyright Legislation or as modified by any successive legislation. Users may access this work and can make use of the information contained in accordance with the Copyright Legislation provided that the author must be properly acknowledged. Further distribution or reproduction in any format is prohibited without the prior permission of the copyright holder.en_GB
dc.bibliographicCitation.conferencenameInternational Conference on Computational Intelligence in Music, Sound, Art and Design (EvoMusArt)en_GB
dc.bibliographicCitation.conferenceplaceAberystwyth, Wales, United Kingdom, 03-05/04/2024en_GB
dc.description.reviewedpeer-revieweden_GB
Appears in Collections:Scholarly Works - InsDG

Files in This Item:
File Description SizeFormat 
map_elites_with_transverse_assessment_for_multimodal_problems_in_creative_domains.pdf9 MBAdobe PDFView/Open


Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.