{"id":1181183,"date":"2026-08-10T01:23:47","date_gmt":"2026-08-10T08:23:47","guid":{"rendered":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/publication\/ovis-u1-technical-report\/"},"modified":"2026-08-13T12:21:04","modified_gmt":"2026-08-13T19:21:04","slug":"ovis-u1-technical-report","status":"publish","type":"msr-research-item","link":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/publication\/ovis-u1-technical-report\/","title":{"rendered":"Ovis-U1 Technical Report"},"content":{"rendered":"\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">In this report, we introduce Ovis-U1, a 3-billion-parameter unified model that integrates multimodal understanding, text-to-image generation, and image editing capabilities. Building on the foundation of the Ovis series, Ovis-U1 incorporates a diffusion-based visual decoder paired with a bidirectional token refiner, enabling image generation tasks comparable to leading models like GPT-4o. Unlike some previous models that use a frozen MLLM for generation tasks, Ovis-U1 utilizes a new unified training approach starting from a language model. Compared to training solely on understanding or generation tasks, unified training yields better performance, demonstrating the enhancement achieved by integrating these two tasks. Ovis-U1 achieves a score of 69.6 on the OpenCompass Multi-modal Academic Benchmark, surpassing recent state-of-the-art models such as Ristretto-3B and SAIL-VL-1.5-2B. In text-to-image generation, it excels with scores of 83.72 and 0.89 on the DPG-Bench and GenEval benchmarks, respectively. For image editing, it achieves 4.00 and 6.42 on the ImgEdit-Bench and GEdit-Bench-EN, respectively. As the initial version of the Ovis unified model series, Ovis-U1 pushes the boundaries of multimodal understanding, generation, and editing.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>In this report, we introduce Ovis-U1, a 3-billion-parameter unified model that integrates multimodal understanding, text-to-image generation, and image editing capabilities. Building on the foundation of the Ovis series, Ovis-U1 incorporates a diffusion-based visual decoder paired with a bidirectional token refiner, enabling image generation tasks comparable to leading models like GPT-4o. Unlike some previous models that [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":[{"type":"user_nicename","value":"Guoxin Wang","user_id":"37089"},{"type":"text","value":"Shanshan Zhao","user_id":0},{"type":"user_nicename","value":"Xinjie Zhang","user_id":"43968"},{"type":"text","value":"Liangfu Cao","user_id":0},{"type":"text","value":"Pengxin Zhan","user_id":0},{"type":"text","value":"Lunhao Duan","user_id":0},{"type":"text","value":"Shiyin Lu","user_id":0},{"type":"text","value":"Minghao Fu","user_id":0},{"type":"text","value":"Xiaohao Chen","user_id":0},{"type":"text","value":"Jianshan Zhao","user_id":0},{"type":"text","value":"Yang Li","user_id":0},{"type":"text","value":"Qing-Guo Chen","user_id":0}],"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"arXiv.org","msr_editors":"","msr_how_published":"","msr_isbn":"","msr_issue":"","msr_journal":"ArXiv","msr_number":"","msr_organization":"","msr_pages_string":"","msr_page_range_start":"","msr_page_range_end":"","msr_series":"","msr_volume":"abs\/2506.23044","msr_copyright":"","msr_conference_name":"","msr_doi":"10.48550\/arXiv.2506.23044","msr_arxiv_id":"2506.23044","msr_mag_id":"","msr_other_authors":"","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_release_tracker_id":"","msr_highlight_type":"","msr_date_display_format":"","msr_main_download_label":"","msr_external_link_label":"","msr_doi_label":"","msr_published_date":"2025-06-28","msr_startdate":"","msr_presentation_date":"","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"","msr_journal_url":"","msr_year":2025,"msr_month":6,"msr_day":28,"msr_microsoftintellectualproperty":false,"msr_pub_id":"21d551654bb9ad61f2cf31b150181842d38df035","msr_publication_uploader":[{"type":"url","title":"https:\/\/dblp.org\/rec\/journals\/corr\/abs-2506-23044.html","label_id":243109,"id":false,"viewUrl":false},{"type":"url","title":"https:\/\/arxiv.org\/abs\/2506.23044","label_id":243109,"id":false,"viewUrl":false}],"msr_related_uploader":[],"msr_original_fields_of_study":[],"msr_s2_paper_id":"21d551654bb9ad61f2cf31b150181842d38df035","msr_s2_pdf_url":"","msr_citation_count_updated":"","msr_citation_count":64,"msr_influential_citations":3,"msr_reference_count":66,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[{"provider":"s2","id":"21d551654bb9ad61f2cf31b150181842d38df035"},{"provider":"doi","id":"10.48550\/arXiv.2506.23044"},{"provider":"arxiv","id":"2506.23044"},{"provider":"dblp","id":"journals\/corr\/abs-2506-23044"},{"provider":"corpusid","id":"280011073"}],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13556,13562],"msr-publication-type":[193715],"msr-publisher":[],"msr-publication-cta":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[256039,246691],"msr-conference":[],"msr-journal":[268188],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-1181183","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-computer-vision","msr-locale-en_us","msr-field-of-study-artifcial-intelligence","msr-field-of-study-computer-science"],"msr_publishername":"","msr_edition":"arXiv.org","msr_affiliation":"","msr_published_date":"2025-06-28","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"ArXiv","msr_volume":"abs\/2506.23044","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":0,"msr_main_download":"","msr_publicationurl":"","msr_doi":"10.48550\/arXiv.2506.23044","msr_publication_uploader":[{"type":"url","title":"https:\/\/dblp.org\/rec\/journals\/corr\/abs-2506-23044.html","label_id":243109,"id":false,"viewUrl":false},{"type":"url","title":"https:\/\/arxiv.org\/abs\/2506.23044","label_id":243109,"id":false,"viewUrl":false}],"msr_related_uploader":[],"msr_citation_count":64,"msr_citation_count_updated":"","msr_s2_paper_id":"21d551654bb9ad61f2cf31b150181842d38df035","msr_influential_citations":3,"msr_reference_count":66,"msr_arxiv_id":"2506.23044","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[],"msr-author-ordering":[{"type":"user_nicename","value":"Guoxin Wang","user_id":37089,"rest_url":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Guoxin Wang"},{"type":"text","value":"Shanshan Zhao","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Xinjie Zhang","user_id":43968,"rest_url":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Xinjie Zhang"},{"type":"text","value":"Liangfu Cao","user_id":0,"rest_url":false},{"type":"text","value":"Pengxin Zhan","user_id":0,"rest_url":false},{"type":"text","value":"Lunhao Duan","user_id":0,"rest_url":false},{"type":"text","value":"Shiyin Lu","user_id":0,"rest_url":false},{"type":"text","value":"Minghao Fu","user_id":0,"rest_url":false},{"type":"text","value":"Xiaohao Chen","user_id":0,"rest_url":false},{"type":"text","value":"Jianshan Zhao","user_id":0,"rest_url":false},{"type":"text","value":"Yang Li","user_id":0,"rest_url":false},{"type":"text","value":"Qing-Guo Chen","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"article","related_content":[],"_links":{"self":[{"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1181183","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":2,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1181183\/revisions"}],"predecessor-version":[{"id":1181650,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1181183\/revisions\/1181650"}],"wp:attachment":[{"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1181183"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=1181183"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1181183"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=1181183"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=1181183"},{"taxonomy":"msr-publication-cta","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-cta?post=1181183"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=1181183"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1181183"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=1181183"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=1181183"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=1181183"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=1181183"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1181183"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1181183"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}