{"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/mindomni-unleashing-reasoning-generation-in","title":"MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO","arxiv_id":"2505.13031","date":"2025-05-19","proceeding":null,"authors":["Yicheng Xiao","Lin Song","Yukang Chen","Yingmin Luo","Yuxin Chen","Yukang Gan","Wei Huang","Xiu Li","Xiaojuan Qi","Ying Shan"],"abstract":"Recent text-to-image systems face limitations in handling multimodal inputs and complex reasoning tasks. We introduce MindOmni, a unified multimodal large language model that addresses these challenges by incorporating reasoning generation through reinforcement learning. MindOmni leverages a three-phase training strategy: i) design of a unified vision language model with a decoder-only diffusion module, ii) supervised fine-tuning with Chain-of-Thought (CoT) instruction data, and iii) our proposed Reasoning Generation Policy Optimization (RGPO) algorithm, utilizing multimodal feedback to effectively guide policy updates. Experimental results demonstrate that MindOmni outperforms existing models, achieving impressive performance on both understanding and generation benchmarks, meanwhile showcasing advanced fine-grained reasoning generation capabilities, especially with mathematical reasoning instruction. All codes will be made public at \\href{https://github.com/EasonXiao-888/MindOmni}{https://github.com/EasonXiao-888/MindOmni}.","url_abs":"https://arxiv.org/abs/2505.13031v1","url_pdf":"https://arxiv.org/pdf/2505.13031v1.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":"mindomni-unleashing-reasoning-generation-in","repo_url":"https://github.com/easonxiao-888/mindomni","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-generation","task_name":"Image Generation"},{"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":"mathematical-reasoning","task_name":"Mathematical Reasoning"},{"task_slug":"multimodal-large-language-model","task_name":"Multimodal Large Language Model"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-wise","task":"Image Generation","dataset":"WISE","model":"MindOmni\n(w/ cot)","rank_in_archive_order":1,"of":14,"metrics":{"Biology":"0.76","Chemistry":"0.52","Cultural":"0.75","Overall":"0.71","Physics":"0.72","Space":"0.76","Time":"0.70"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-wise","task":"Image Generation","dataset":"WISE","model":"MindOmni\n(w/o cot)","rank_in_archive_order":10,"of":14,"metrics":{"Biology":"0.36","Chemistry":"0.32","Cultural":"0.40","Overall":"0.43","Physics":"0.52","Space":"0.62","Time":"0.38"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-geneval","task":"Text-to-Image Generation","dataset":"GenEval","model":"MindOmni","rank_in_archive_order":3,"of":20,"metrics":{"Color Attri.":"0.71","Colors":"0.90","Counting":"0.71","Overall":"0.83","Position":"0.71","Single Obj.":"0.99","Two Obj.":"0.94"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2505.13031","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}