{"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/pali-3-vision-language-models-smaller-faster","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","arxiv_id":"2310.09199","date":"2023-10-13","proceeding":null,"authors":["Xi Chen","Xiao Wang","Lucas Beyer","Alexander Kolesnikov","Jialin Wu","Paul Voigtlaender","Basil Mustafa","Sebastian Goodman","Ibrahim Alabdulmohsin","Piotr Padlewski","Daniel Salz","Xi Xiong","Daniel Vlasic","Filip Pavetic","Keran Rong","Tianli Yu","Daniel Keysers","Xiaohua Zhai","Radu Soricut"],"abstract":"This paper presents PaLI-3, a smaller, faster, and stronger vision language model (VLM) that compares favorably to similar models that are 10x larger. As part of arriving at this strong performance, we compare Vision Transformer (ViT) models pretrained using classification objectives to contrastively (SigLIP) pretrained ones. We find that, while slightly underperforming on standard image classification benchmarks, SigLIP-based PaLI shows superior performance across various multimodal benchmarks, especially on localization and visually-situated text understanding. We scale the SigLIP image encoder up to 2 billion parameters, and achieves a new state-of-the-art on multilingual cross-modal retrieval. We hope that PaLI-3, at only 5B parameters, rekindles research on fundamental pieces of complex VLMs, and could fuel a new generation of scaled-up models.","url_abs":"https://arxiv.org/abs/2310.09199v2","url_pdf":"https://arxiv.org/pdf/2310.09199v2.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":"pali-3-vision-language-models-smaller-faster","repo_url":"https://github.com/kyegomez/PALI3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"chart-question-answering","task_name":"Chart Question Answering"},{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"temporal-casual-qa","task_name":"Temporal/Casual QA"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"multilingual-cross-modal-retrieval","task_name":"multilingual cross-modal retrieval"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/chart-question-answering-on-chartqa","task":"Chart Question Answering","dataset":"ChartQA","model":"PaLI-3","rank_in_archive_order":14,"of":27,"metrics":{"1:1 Accuracy":"70"},"uses_additional_data":false},{"leaderboard":"/sota/chart-question-answering-on-chartqa","task":"Chart Question Answering","dataset":"ChartQA","model":"PaLI-3 (w/ OCR)","rank_in_archive_order":15,"of":27,"metrics":{"1:1 Accuracy":"69.5"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-casual-qa-on-next-qa","task":"Temporal/Casual QA","dataset":"NExT-QA","model":"PaLI-3","rank_in_archive_order":2,"of":8,"metrics":{"WUPS":"37.7"},"uses_additional_data":true},{"leaderboard":"/sota/visual-question-answering-on-docvqa-test","task":"Visual Question Answering (VQA)","dataset":"DocVQA test","model":"PaLI-3 (w/ OCR)","rank_in_archive_order":7,"of":33,"metrics":{"ANLS":"0.886"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-docvqa-test","task":"Visual Question Answering (VQA)","dataset":"DocVQA test","model":"PaLI-3","rank_in_archive_order":12,"of":33,"metrics":{"ANLS":"0.876"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-vqa-on","task":"Visual Question Answering (VQA)","dataset":"InfographicVQA","model":"PaLI-3 (w/ OCR)","rank_in_archive_order":6,"of":21,"metrics":{"ANLS":"62.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-vqa-on","task":"Visual Question Answering (VQA)","dataset":"InfographicVQA","model":"PaLI-3","rank_in_archive_order":8,"of":21,"metrics":{"ANLS":"57.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.09199","atlas_url":"https://app.syntology.ai/?focus=2310.09199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09199"}},"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/kyegomez/PALI3","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":3},"by_repo_kind":{"listed":{"samples":3,"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":0,"samples":[{"code_sha256_prefix":"1f7c550e65142ef8","entry":"cast_tuple","repo":"kyegomez/PALI3","repo_kind":"listed","path":"pali3/ul2.py","file_url":"https://github.com/kyegomez/PALI3/blob/HEAD/pali3/ul2.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1f7c550e65142ef8"}},{"code_sha256_prefix":"424012cb37b31172","entry":"default","repo":"kyegomez/PALI3","repo_kind":"listed","path":"pali3/ul2.py","file_url":"https://github.com/kyegomez/PALI3/blob/HEAD/pali3/ul2.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"424012cb37b31172"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"kyegomez/PALI3","repo_kind":"listed","path":"pali3/ul2.py","file_url":"https://github.com/kyegomez/PALI3/blob/HEAD/pali3/ul2.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}