{"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/internlm-xcomposer2-mastering-free-form-text","title":"InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model","arxiv_id":"2401.16420","date":"2024-01-29","proceeding":null,"authors":["Xiaoyi Dong","Pan Zhang","Yuhang Zang","Yuhang Cao","Bin Wang","Linke Ouyang","Xilin Wei","Songyang Zhang","Haodong Duan","Maosong Cao","Wenwei Zhang","Yining Li","Hang Yan","Yang Gao","Xinyue Zhang","Wei Li","Jingwen Li","Kai Chen","Conghui He","Xingcheng Zhang","Yu Qiao","Dahua Lin","Jiaqi Wang"],"abstract":"We introduce InternLM-XComposer2, a cutting-edge vision-language model excelling in free-form text-image composition and comprehension. This model goes beyond conventional vision-language understanding, adeptly crafting interleaved text-image content from diverse inputs like outlines, detailed textual specifications, and reference images, enabling highly customizable content creation. InternLM-XComposer2 proposes a Partial LoRA (PLoRA) approach that applies additional LoRA parameters exclusively to image tokens to preserve the integrity of pre-trained language knowledge, striking a balance between precise vision understanding and text composition with literary talent. Experimental results demonstrate the superiority of InternLM-XComposer2 based on InternLM2-7B in producing high-quality long-text multi-modal content and its exceptional vision-language understanding performance across various benchmarks, where it not only significantly outperforms existing multimodal models but also matches or even surpasses GPT-4V and Gemini Pro in certain assessments. This highlights its remarkable proficiency in the realm of multimodal understanding. The InternLM-XComposer2 model series with 7B parameters are publicly available at https://github.com/InternLM/InternLM-XComposer.","url_abs":"https://arxiv.org/abs/2401.16420v1","url_pdf":"https://arxiv.org/pdf/2401.16420v1.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":"internlm-xcomposer2-mastering-free-form-text","repo_url":"https://github.com/internlm/internlm-xcomposer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"form","task_name":"Form"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"InternLM-XComposer2","rank_in_archive_order":58,"of":231,"metrics":{"GPT-4 score":"51.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet-v2","task":"Visual Question Answering","dataset":"MM-Vet v2","model":"IXC2-VL-7B","rank_in_archive_order":18,"of":24,"metrics":{"GPT-4 score":"42.5±0.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.16420","atlas_url":"https://app.syntology.ai/?focus=2401.16420","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}