{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/towards-flexible-multi-modal-document-models","title":"Towards Flexible Multi-modal Document Models","arxiv_id":"2303.18248","date":"2023-03-31","proceeding":"CVPR 2023 1","authors":["Naoto Inoue","Kotaro Kikuchi","Edgar Simo-Serra","Mayu Otani","Kota Yamaguchi"],"abstract":"Creative workflows for generating graphical documents involve complex inter-related tasks, such as aligning elements, choosing appropriate fonts, or employing aesthetically harmonious colors. In this work, we attempt at building a holistic model that can jointly solve many different design tasks. Our model, which we denote by FlexDM, treats vector graphic documents as a set of multi-modal elements, and learns to predict masked fields such as element type, position, styling attributes, image, or text, using a unified architecture. Through the use of explicit multi-task learning and in-domain pre-training, our model can better capture the multi-modal relationships among the different document fields. Experimental results corroborate that our single FlexDM is able to successfully solve a multitude of different design tasks, while achieving performance that is competitive with task-specific and costly baselines.","url_abs":"https://arxiv.org/abs/2303.18248v1","url_pdf":"https://arxiv.org/pdf/2303.18248v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"towards-flexible-multi-modal-document-models","repo_url":"https://github.com/CyberAgentAILab/flex-dm","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":null,"task_name":"Position"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.18248","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}