{"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/lion-empowering-multimodal-large-language-1","title":"LION: Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge","arxiv_id":null,"date":"2024-01-01","proceeding":"CVPR 2024 1","authors":["Gongwei Chen","Leyang Shen","Rui Shao","Xiang Deng","Liqiang Nie"],"abstract":"    Multimodal Large Language Models (MLLMs) have endowed LLMs with the ability to perceive and understand multi-modal signals. However most of the existing MLLMs mainly adopt vision encoders pretrained on coarsely aligned image-text pairs leading to insufficient extraction and reasoning of visual knowledge. To address this issue we devise a dual-Level vIsual knOwledge eNhanced Multimodal Large Language Model (LION) which empowers the MLLM by injecting visual knowledge in two levels. 1) Progressive incorporation of fine-grained spatial-aware visual knowledge. We design a vision aggregator cooperated with region-level vision-language (VL) tasks to incorporate fine-grained spatial-aware visual knowledge into the MLLM. To alleviate the conflict between image-level and region-level VL tasks during incorporation we devise a dedicated stage-wise instruction-tuning strategy with mixture-of-adapters. This progressive incorporation scheme contributes to the mutual promotion between these two kinds of VL tasks. 2) Soft prompting of high-level semantic visual evidence. We facilitate the MLLM with high-level semantic visual evidence by leveraging diverse image tags. To mitigate the potential influence caused by imperfect predicted tags we propose a soft prompting method by embedding a learnable token into the tailored text instruction. Comprehensive experiments on several multi-modal benchmarks demonstrate the superiority of our model (e.g. improvement of 5% accuracy on VSR and 3% CIDEr on TextCaps over InstructBLIP 5% accuracy on RefCOCOg over Kosmos-2).    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2024/html/Chen_LION_Empowering_Multimodal_Large_Language_Model_with_Dual-Level_Visual_Knowledge_CVPR_2024_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2024/papers/Chen_LION_Empowering_Multimodal_Large_Language_Model_with_Dual-Level_Visual_Knowledge_CVPR_2024_paper.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":"lion-empowering-multimodal-large-language-1","repo_url":"https://github.com/rshaojimmy/jiutian","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"multimodal-large-language-model","task_name":"Multimodal Large Language Model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}