{"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/mblip-efficient-bootstrapping-of-multilingual","title":"mBLIP: Efficient Bootstrapping of Multilingual Vision-LLMs","arxiv_id":"2307.06930","date":"2023-07-13","proceeding":null,"authors":["Gregor Geigle","Abhay Jain","Radu Timofte","Goran Glavaš"],"abstract":"Modular vision-language models (Vision-LLMs) align pretrained image encoders with (frozen) large language models (LLMs) and post-hoc condition LLMs to `understand' the image input. With the abundance of readily available high-quality English image-text data as well as strong monolingual English LLMs, the research focus has been on English-only Vision-LLMs. Multilingual vision-language models are still predominantly obtained via expensive end-to-end pretraining, resulting in comparatively smaller models, trained on limited multilingual image data supplemented with text-only multilingual corpora. We present mBLIP, the first Vision-LLM leveraging multilingual LLMs, which we obtain in a computationally efficient manner on consumer-level hardware. To this end, we \\textit{re-align} an image encoder previously tuned to an English LLM to a new, multilingual LLM using only a few million multilingual training examples derived from a mix of vision-and-language tasks, which we obtain by machine-translating high-quality English data to 95 languages. On the IGLUE benchmark and XM3600, mBLIP yields results competitive with state-of-the-art models and it greatly outperforms strong English-only Vision-LLMs like Llava 1.5. We release our model, code, and train data at \\url{https://github.com/gregor-ge/mBLIP}.","url_abs":"https://arxiv.org/abs/2307.06930v3","url_pdf":"https://arxiv.org/pdf/2307.06930v3.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":"mblip-efficient-bootstrapping-of-multilingual","repo_url":"https://github.com/gregor-ge/mblip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2307.06930","atlas_url":"https://app.syntology.ai/?focus=2307.06930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.06930"}},"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/gregor-ge/mblip","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":0,"samples":[{"code_sha256_prefix":"41a387217f0d60ae","entry":"output_loss","repo":"gregor-ge/mblip","repo_kind":"official","path":"src/tasks/vllm/evaluation.py","file_url":"https://github.com/gregor-ge/mblip/blob/HEAD/src/tasks/vllm/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"41a387217f0d60ae"}},{"code_sha256_prefix":"257b04b56ec523a2","entry":"processing_hooks","repo":"gregor-ge/mblip","repo_kind":"official","path":"src/utils/hooks.py","file_url":"https://github.com/gregor-ge/mblip/blob/HEAD/src/utils/hooks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"257b04b56ec523a2"}},{"code_sha256_prefix":"1113dcafe2eb33cb","entry":"set_generation_mode","repo":"gregor-ge/mblip","repo_kind":"official","path":"src/tasks/vllm/evaluation.py","file_url":"https://github.com/gregor-ge/mblip/blob/HEAD/src/tasks/vllm/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1113dcafe2eb33cb"}},{"code_sha256_prefix":"c215d2db990935a2","entry":"validation_loss","repo":"gregor-ge/mblip","repo_kind":"official","path":"src/tasks/vllm/evaluation.py","file_url":"https://github.com/gregor-ge/mblip/blob/HEAD/src/tasks/vllm/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c215d2db990935a2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}