{"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/x-2-vlm-all-in-one-pre-trained-model-for","title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","arxiv_id":"2211.12402","date":"2022-11-22","proceeding":null,"authors":["Yan Zeng","Xinsong Zhang","Hang Li","Jiawei Wang","Jipeng Zhang","Wangchunshu Zhou"],"abstract":"Vision language pre-training aims to learn alignments between vision and language from a large amount of data. Most existing methods only learn image-text alignments. Some others utilize pre-trained object detectors to leverage vision language alignments at the object level. In this paper, we propose to learn multi-grained vision language alignments by a unified pre-training framework that learns multi-grained aligning and multi-grained localization simultaneously. Based on it, we present X$^2$-VLM, an all-in-one model with a flexible modular architecture, in which we further unify image-text pre-training and video-text pre-training in one model. X$^2$-VLM is able to learn unlimited visual concepts associated with diverse text descriptions. Experiment results show that X$^2$-VLM performs the best on base and large scale for both image-text and video-text tasks, making a good trade-off between performance and model scale. Moreover, we show that the modular design of X$^2$-VLM results in high transferability for it to be utilized in any language or domain. For example, by simply replacing the text encoder with XLM-R, X$^2$-VLM outperforms state-of-the-art multilingual multi-modal pre-trained models without any multilingual pre-training. The code and pre-trained models are available at https://github.com/zengyan-97/X2-VLM.","url_abs":"https://arxiv.org/abs/2211.12402v2","url_pdf":"https://arxiv.org/pdf/2211.12402v2.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":"x-2-vlm-all-in-one-pre-trained-model-for","repo_url":"https://github.com/zengyan-97/x2-vlm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"x-2-vlm-all-in-one-pre-trained-model-for","repo_url":"https://github.com/zengyan-97/x-vlm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"text-to-video-retrieval","task_name":"Text to Video Retrieval"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"},{"task_slug":"xlm-r","task_name":"XLM-R"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"xlm-r","method_name":"XLM-R"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-modal-retrieval-on-coco-2014","task":"Cross-Modal Retrieval","dataset":"COCO 2014","model":"X2-VLM (large)","rank_in_archive_order":2,"of":36,"metrics":{"Image-to-text R@1":"84.4","Image-to-text R@10":"98.5","Image-to-text R@5":"96.5","Text-to-image R@1":"67.7","Text-to-image R@10":"92.5","Text-to-image R@5":"87.5"},"uses_additional_data":true},{"leaderboard":"/sota/cross-modal-retrieval-on-coco-2014","task":"Cross-Modal Retrieval","dataset":"COCO 2014","model":"X2-VLM (base)","rank_in_archive_order":5,"of":36,"metrics":{"Image-to-text R@1":"83.5","Image-to-text R@10":"98.5","Image-to-text R@5":"96.3","Text-to-image R@1":"66.2","Text-to-image R@10":"92.2","Text-to-image R@5":"87.1"},"uses_additional_data":true},{"leaderboard":"/sota/cross-modal-retrieval-on-flickr30k","task":"Cross-Modal Retrieval","dataset":"Flickr30k","model":"X2-VLM (large)","rank_in_archive_order":1,"of":27,"metrics":{"Image-to-text R@1":"98.8","Image-to-text R@10":"100","Image-to-text R@5":"100","Text-to-image R@1":"91.8","Text-to-image R@10":"99.5","Text-to-image R@5":"98.6"},"uses_additional_data":true},{"leaderboard":"/sota/cross-modal-retrieval-on-flickr30k","task":"Cross-Modal Retrieval","dataset":"Flickr30k","model":"X2-VLM (base)","rank_in_archive_order":2,"of":27,"metrics":{"Image-to-text R@1":"98.5","Image-to-text R@10":"100","Image-to-text R@5":"100","Text-to-image R@1":"90.4","Text-to-image R@10":"99.3","Text-to-image R@5":"98.2"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-msr-vtt-1ka","task":"Video Retrieval","dataset":"MSR-VTT-1kA","model":"X2-VLM (large)","rank_in_archive_order":18,"of":63,"metrics":{"text-to-video R@1":"49.6","text-to-video R@10":"84.2","text-to-video R@5":"76.7"},"uses_additional_data":false},{"leaderboard":"/sota/video-retrieval-on-msr-vtt-1ka","task":"Video Retrieval","dataset":"MSR-VTT-1kA","model":"X2-VLM (base)","rank_in_archive_order":28,"of":63,"metrics":{"text-to-video R@1":"47.6","text-to-video R@10":"84.2","text-to-video R@5":"74.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-grounding-on-refcoco-test-b","task":"Visual Grounding","dataset":"RefCOCO+ test B","model":"X2-VLM (large)","rank_in_archive_order":3,"of":6,"metrics":{"Accuracy (%)":"81.8"},"uses_additional_data":false},{"leaderboard":"/sota/visual-grounding-on-refcoco-test-b","task":"Visual Grounding","dataset":"RefCOCO+ test B","model":"X2-VLM (base)","rank_in_archive_order":5,"of":6,"metrics":{"Accuracy (%)":"78.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-grounding-on-refcoco-testa","task":"Visual Grounding","dataset":"RefCOCO+ testA","model":"X2-VLM (large)","rank_in_archive_order":3,"of":7,"metrics":{"Accuracy (%)":"92.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-grounding-on-refcoco-testa","task":"Visual Grounding","dataset":"RefCOCO+ testA","model":"X2-VLM (base)","rank_in_archive_order":5,"of":7,"metrics":{"Accuracy (%)":"90.3"},"uses_additional_data":false},{"leaderboard":"/sota/visual-grounding-on-refcoco-val","task":"Visual Grounding","dataset":"RefCOCO+ val","model":"X2-VLM (large)","rank_in_archive_order":3,"of":6,"metrics":{"Accuracy (%)":"87.6"},"uses_additional_data":false},{"leaderboard":"/sota/visual-grounding-on-refcoco-val","task":"Visual Grounding","dataset":"RefCOCO+ val","model":"X2-VLM (base)","rank_in_archive_order":5,"of":6,"metrics":{"Accuracy (%)":"85.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-msrvtt-qa-1","task":"Visual Question Answering (VQA)","dataset":"MSRVTT-QA","model":"X2-VLM (large)","rank_in_archive_order":15,"of":34,"metrics":{"Accuracy":"0.455"},"uses_additional_data":true},{"leaderboard":"/sota/visual-question-answering-on-msrvtt-qa-1","task":"Visual Question Answering (VQA)","dataset":"MSRVTT-QA","model":"X2-VLM (base)","rank_in_archive_order":16,"of":34,"metrics":{"Accuracy":"0.45"},"uses_additional_data":true},{"leaderboard":"/sota/visual-question-answering-on-msvd-qa-1","task":"Visual Question Answering (VQA)","dataset":"MSVD-QA","model":"X2-VLM (large)","rank_in_archive_order":17,"of":36,"metrics":{"Accuracy":"0.546"},"uses_additional_data":true},{"leaderboard":"/sota/visual-question-answering-on-msvd-qa-1","task":"Visual Question Answering (VQA)","dataset":"MSVD-QA","model":"X2-VLM (base)","rank_in_archive_order":18,"of":36,"metrics":{"Accuracy":"0.528"},"uses_additional_data":true},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-dev","model":"X2-VLM (large)","rank_in_archive_order":7,"of":56,"metrics":{"Accuracy":"81.9"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-dev","model":"X2-VLM (base)","rank_in_archive_order":11,"of":56,"metrics":{"Accuracy":"80.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-std","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-std","model":"X2-VLM (large)","rank_in_archive_order":4,"of":38,"metrics":{"overall":"81.8"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-std","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-std","model":"X2-VLM (base)","rank_in_archive_order":7,"of":38,"metrics":{"overall":"80.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-reasoning-on-nlvr2-dev","task":"Visual Reasoning","dataset":"NLVR2 Dev","model":"X2-VLM (large)","rank_in_archive_order":2,"of":15,"metrics":{"Accuracy":"88.7"},"uses_additional_data":false},{"leaderboard":"/sota/visual-reasoning-on-nlvr2-dev","task":"Visual Reasoning","dataset":"NLVR2 Dev","model":"X2-VLM (base)","rank_in_archive_order":4,"of":15,"metrics":{"Accuracy":"86.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-reasoning-on-nlvr2-test","task":"Visual Reasoning","dataset":"NLVR2 Test","model":"X2-VLM (large)","rank_in_archive_order":2,"of":14,"metrics":{"Accuracy":"89.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-reasoning-on-nlvr2-test","task":"Visual Reasoning","dataset":"NLVR2 Test","model":"X2-VLM (base)","rank_in_archive_order":5,"of":14,"metrics":{"Accuracy":"87.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2211.12402","atlas_url":"https://app.syntology.ai/?focus=2211.12402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.12402"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zengyan-97/x2-vlm","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zengyan-97/x-vlm","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran_draft_wrong":1,"ran":1,"ran_fixture":1,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":6,"samples":[{"code_sha256_prefix":"51e7514fd736cca3","entry":"build_mlp","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"51e7514fd736cca3"}},{"code_sha256_prefix":"10aeef229798e5ff","entry":"get_acc","repo":"zengyan-97/x2-vlm","repo_kind":"official","path":"XGQA.py","file_url":"https://github.com/zengyan-97/x2-vlm/blob/HEAD/XGQA.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"mcp_get_code":{"code_sha256":"10aeef229798e5ff"}},{"code_sha256_prefix":"c7f85279d772ea19","entry":"itm_eval","repo":"zengyan-97/x2-vlm","repo_kind":"official","path":"Retrieval.py","file_url":"https://github.com/zengyan-97/x2-vlm/blob/HEAD/Retrieval.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"mcp_get_code":{"code_sha256":"c7f85279d772ea19"}},{"code_sha256_prefix":"e3d6fbf640a143ee","entry":"reinit_scheduler_properties_mysched","repo":"zengyan-97/x2-vlm","repo_kind":"official","path":"Pretrain.py","file_url":"https://github.com/zengyan-97/x2-vlm/blob/HEAD/Pretrain.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"mcp_get_code":{"code_sha256":"e3d6fbf640a143ee"}},{"code_sha256_prefix":"3365d5bf2acc203f","entry":"run_image_iter","repo":"zengyan-97/x2-vlm","repo_kind":"official","path":"Pretrain.py","file_url":"https://github.com/zengyan-97/x2-vlm/blob/HEAD/Pretrain.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"mcp_get_code":{"code_sha256":"3365d5bf2acc203f"}},{"code_sha256_prefix":"ee513e1972c86c60","entry":"run_region_iter","repo":"zengyan-97/x2-vlm","repo_kind":"official","path":"Pretrain.py","file_url":"https://github.com/zengyan-97/x2-vlm/blob/HEAD/Pretrain.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"mcp_get_code":{"code_sha256":"ee513e1972c86c60"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}