March 15, 2024, 4:46 a.m. | Hugo Lauren\c{c}on, L\'eo Tronchon, Victor Sanh

cs.CV updates on arXiv.org arxiv.org

arXiv:2403.09029v1 Announce Type: cross
Abstract: Using vision-language models (VLMs) in web development presents a promising strategy to increase efficiency and unblock no-code solutions: by providing a screenshot or a sketch of a UI, a VLM could generate the code to reproduce it, for instance in a language like HTML. Despite the advancements in VLMs for various tasks, the specific challenge of converting a screenshot into a corresponding HTML has been minimally explored. We posit that this is mainly due to …

abstract arxiv code conversion cs.ai cs.cv cs.hc dataset development efficiency generate html instance language language models no-code solutions strategy type vision vision-language models vlm vlms web web development

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne