{"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/nomic-embed-vision-expanding-the-latent-space","title":"Nomic Embed Vision: Expanding the Latent Space","arxiv_id":"2406.18587","date":"2024-06-06","proceeding":null,"authors":["Zach Nussbaum","Brandon Duderstadt","Andriy Mulyar"],"abstract":"This technical report describes the training of nomic-embed-vision, a highly performant, open-code, open-weights image embedding model that shares the same latent space as nomic-embed-text. Together, nomic-embed-vision and nomic-embed-text form the first unified latent space to achieve high performance across vision, language, and multimodal tasks.","url_abs":"https://arxiv.org/abs/2406.18587v1","url_pdf":"https://arxiv.org/pdf/2406.18587v1.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":"nomic-embed-vision-expanding-the-latent-space","repo_url":"https://github.com/nomic-ai/contrastors","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.18587","atlas_url":"https://app.syntology.ai/?focus=2406.18587","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}