{"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/prefix-language-models-are-unified-modal","title":"Write and Paint: Generative Vision-Language Models are Unified Modal Learners","arxiv_id":"2206.07699","date":"2022-06-15","proceeding":null,"authors":["Shizhe Diao","Wangchunshu Zhou","Xinsong Zhang","Jiawei Wang"],"abstract":"Recent advances in vision-language pre-training have pushed the state-of-the-art on various vision-language tasks, making machines more capable of multi-modal writing (image-to-text generation) and painting (text-to-image generation). However, few studies investigate if these two essential capabilities can be learned together and boost each other, making a versatile and powerful multi-modal foundation model. In this work, we disclose the potential of symmetric generative vision-language pre-training in learning to write and paint concurrently, and propose a new unified modal model, named DaVinci, trained with prefix language modeling and prefix image modeling, a simple generative self-supervised objective on image-text pairs. Thanks to the proposed prefix multi-modal modeling framework, DaVinci is simple to train, scalable to huge data, adaptable to both writing and painting tasks, and also strong on other vision, text, and multi-modal understanding tasks. DaVinci achieves competitive performance on a wide range of 27 generation/understanding tasks and demonstrates the superiority of combining vision/language generative pre-training. Furthermore, we carefully benchmark the performance of different vision-language pre-training objectives on different scales of pre-training datasets on a heterogeneous and broad distribution coverage. Our results demonstrate the potential of exploiting self-supervision in both language and vision inputs, and establish new, stronger baselines for future comparisons at different data scales. The code and pre-trained models are available at https://github.com/shizhediao/DaVinci.","url_abs":"https://arxiv.org/abs/2206.07699v3","url_pdf":"https://arxiv.org/pdf/2206.07699v3.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":"prefix-language-models-are-unified-modal","repo_url":"https://github.com/shizhediao/davinci","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-to-text","task_name":"Image to text"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.07699","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.07699"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/shizhediao/davinci","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran_fixture":1,"ran_honours":1,"ran":1,"unverified":6},"by_repo_kind":{"official":{"samples":9,"ran":3,"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":9,"samples":[{"code_sha256_prefix":"131a82fd65128218","entry":"accuracy","repo":"shizhediao/davinci","repo_kind":"official","path":"image_linprobe.py","file_url":"https://github.com/shizhediao/davinci/blob/HEAD/image_linprobe.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"mcp_get_code":{"code_sha256":"131a82fd65128218"}},{"code_sha256_prefix":"bd3578806ecf5ac2","entry":"adjust_learning_rate","repo":"shizhediao/davinci","repo_kind":"official","path":"image_finetune.py","file_url":"https://github.com/shizhediao/davinci/blob/HEAD/image_finetune.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"mcp_get_code":{"code_sha256":"bd3578806ecf5ac2"}},{"code_sha256_prefix":"aa5a91226269bf75","entry":"tile","repo":"shizhediao/davinci","repo_kind":"official","path":"models/davinci_pretrain.py","file_url":"https://github.com/shizhediao/davinci/blob/HEAD/models/davinci_pretrain.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":false,"mcp_get_code":{"code_sha256":"aa5a91226269bf75"}},{"code_sha256_prefix":"7cc42a822caf6361","entry":"bpe_post_process","repo":"shizhediao/davinci","repo_kind":"official","path":"eval_coco.py","file_url":"https://github.com/shizhediao/davinci/blob/HEAD/eval_coco.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":"7cc42a822caf6361"}},{"code_sha256_prefix":"719b9682b050e2c1","entry":"build_transform","repo":"shizhediao/davinci","repo_kind":"official","path":"image_finetune.py","file_url":"https://github.com/shizhediao/davinci/blob/HEAD/image_finetune.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":"719b9682b050e2c1"}},{"code_sha256_prefix":"4db905959447729d","entry":"load_tf_weights_in_bert","repo":"shizhediao/davinci","repo_kind":"official","path":"models/bert.py","file_url":"https://github.com/shizhediao/davinci/blob/HEAD/models/bert.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":"4db905959447729d"}},{"code_sha256_prefix":"8164123ea94d7bb5","entry":"top_k_top_p_filtering","repo":"shizhediao/davinci","repo_kind":"official","path":"models/davinci_pretrain.py","file_url":"https://github.com/shizhediao/davinci/blob/HEAD/models/davinci_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":"8164123ea94d7bb5"}},{"code_sha256_prefix":"0a929b32383b0b8b","entry":"validate","repo":"shizhediao/davinci","repo_kind":"official","path":"image_finetune.py","file_url":"https://github.com/shizhediao/davinci/blob/HEAD/image_finetune.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":"0a929b32383b0b8b"}},{"code_sha256_prefix":"b5ded0e5cccea0b1","entry":"validate","repo":"shizhediao/davinci","repo_kind":"official","path":"image_linprobe.py","file_url":"https://github.com/shizhediao/davinci/blob/HEAD/image_linprobe.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":"b5ded0e5cccea0b1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}