{"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/mplug-owl3-towards-long-image-sequence","title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","arxiv_id":"2408.04840","date":"2024-08-09","proceeding":null,"authors":["Jiabo Ye","Haiyang Xu","Haowei Liu","Anwen Hu","Ming Yan","Qi Qian","Ji Zhang","Fei Huang","Jingren Zhou"],"abstract":"Multi-modal Large Language Models (MLLMs) have demonstrated remarkable capabilities in executing instructions for a variety of single-image tasks. Despite this progress, significant challenges remain in modeling long image sequences. In this work, we introduce the versatile multi-modal large language model, mPLUG-Owl3, which enhances the capability for long image-sequence understanding in scenarios that incorporate retrieved image-text knowledge, interleaved image-text, and lengthy videos. Specifically, we propose novel hyper attention blocks to efficiently integrate vision and language into a common language-guided semantic space, thereby facilitating the processing of extended multi-image scenarios. Extensive experimental results suggest that mPLUG-Owl3 achieves state-of-the-art performance among models with a similar size on single-image, multi-image, and video benchmarks. Moreover, we propose a challenging long visual sequence evaluation named Distractor Resistance to assess the ability of models to maintain focus amidst distractions. Finally, with the proposed architecture, mPLUG-Owl3 demonstrates outstanding performance on ultra-long visual sequence inputs. We hope that mPLUG-Owl3 can contribute to the development of more efficient and powerful multimodal large language models.","url_abs":"https://arxiv.org/abs/2408.04840v2","url_pdf":"https://arxiv.org/pdf/2408.04840v2.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":"mplug-owl3-towards-long-image-sequence","repo_url":"https://github.com/x-plug/mplug-owl","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":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-question-answering-on-mvbench","task":"Video Question Answering","dataset":"MVBench","model":"mPLUG-Owl3(7B)","rank_in_archive_order":8,"of":22,"metrics":{"Avg.":"59.5"},"uses_additional_data":false},{"leaderboard":"/sota/video-question-answering-on-next-qa","task":"Video Question Answering","dataset":"NExT-QA","model":"mPLUG-Owl3(8B)","rank_in_archive_order":18,"of":47,"metrics":{"Accuracy":"78.6"},"uses_additional_data":false},{"leaderboard":"/sota/video-question-answering-on-tvbench","task":"Video Question Answering","dataset":"TVBench","model":"mPLUG-Owl3","rank_in_archive_order":21,"of":28,"metrics":{"Average Accuracy":"42.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"mPLUG-Owl3","rank_in_archive_order":111,"of":231,"metrics":{"GPT-4 score":"40.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-vqa-on-vlm2-bench","task":"Visual Question Answering (VQA)","dataset":"VLM2-Bench","model":"mPLUG-Owl3-7B","rank_in_archive_order":7,"of":9,"metrics":{"Average Score on VLM2-bench (9 subtasks)":"37.85","GC-mat":"17.37","GC-trk":"18.26","OC-cnt":"62.97","OC-cpr":"49.17","OC-grp":"31.00","PC-VID":"13.50","PC-cnt":"58.86","PC-cpr":"63.50","PC-grp":"26.00"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.04840","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}