{"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/paligemma-a-versatile-3b-vlm-for-transfer","title":"PaliGemma: A versatile 3B VLM for transfer","arxiv_id":"2407.07726","date":"2024-07-10","proceeding":null,"authors":["Lucas Beyer","Andreas Steiner","André Susano Pinto","Alexander Kolesnikov","Xiao Wang","Daniel Salz","Maxim Neumann","Ibrahim Alabdulmohsin","Michael Tschannen","Emanuele Bugliarello","Thomas Unterthiner","Daniel Keysers","Skanda Koppula","Fangyu Liu","Adam Grycner","Alexey Gritsenko","Neil Houlsby","Manoj Kumar","Keran Rong","Julian Eisenschlos","Rishabh Kabra","Matthias Bauer","Matko Bošnjak","Xi Chen","Matthias Minderer","Paul Voigtlaender","Ioana Bica","Ivana Balazevic","Joan Puigcerver","Pinelopi Papalampidi","Olivier Henaff","Xi Xiong","Radu Soricut","Jeremiah Harmsen","Xiaohua Zhai"],"abstract":"PaliGemma is an open Vision-Language Model (VLM) that is based on the SigLIP-So400m vision encoder and the Gemma-2B language model. It is trained to be a versatile and broadly knowledgeable base model that is effective to transfer. It achieves strong performance on a wide variety of open-world tasks. We evaluate PaliGemma on almost 40 diverse tasks including standard VLM benchmarks, but also more specialized tasks such as remote-sensing and segmentation.","url_abs":"https://arxiv.org/abs/2407.07726v2","url_pdf":"https://arxiv.org/pdf/2407.07726v2.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":"paligemma-a-versatile-3b-vlm-for-transfer","repo_url":"https://github.com/google-research/big_vision","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.07726","atlas_url":"https://app.syntology.ai/?focus=2407.07726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07726"}},"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/google-research/big_vision","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"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":0,"samples":[{"code_sha256_prefix":"df9a26063072a047","entry":"combine_and_keep_eval","repo":"google-research/big_vision","repo_kind":"official","path":"big_vision/configs/proj/paligemma/transfers/common.py","file_url":"https://github.com/google-research/big_vision/blob/HEAD/big_vision/configs/proj/paligemma/transfers/common.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"df9a26063072a047"}},{"code_sha256_prefix":"7d9a969e39538694","entry":"combine_and_keep_train","repo":"google-research/big_vision","repo_kind":"official","path":"big_vision/configs/proj/paligemma/transfers/common.py","file_url":"https://github.com/google-research/big_vision/blob/HEAD/big_vision/configs/proj/paligemma/transfers/common.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7d9a969e39538694"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}