{"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/qwen-vl-a-frontier-large-vision-language","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","arxiv_id":"2308.12966","date":"2023-08-24","proceeding":null,"authors":["Jinze Bai","Shuai Bai","Shusheng Yang","Shijie Wang","Sinan Tan","Peng Wang","Junyang Lin","Chang Zhou","Jingren Zhou"],"abstract":"In this work, we introduce the Qwen-VL series, a set of large-scale vision-language models (LVLMs) designed to perceive and understand both texts and images. Starting from the Qwen-LM as a foundation, we endow it with visual capacity by the meticulously designed (i) visual receptor, (ii) input-output interface, (iii) 3-stage training pipeline, and (iv) multilingual multimodal cleaned corpus. Beyond the conventional image description and question-answering, we implement the grounding and text-reading ability of Qwen-VLs by aligning image-caption-box tuples. The resulting models, including Qwen-VL and Qwen-VL-Chat, set new records for generalist models under similar model scales on a broad range of visual-centric benchmarks (e.g., image captioning, question answering, visual grounding) and different settings (e.g., zero-shot, few-shot). Moreover, on real-world dialog benchmarks, our instruction-tuned Qwen-VL-Chat also demonstrates superiority compared to existing vision-language chatbots. Code, demo and models are available at https://github.com/QwenLM/Qwen-VL.","url_abs":"https://arxiv.org/abs/2308.12966v3","url_pdf":"https://arxiv.org/pdf/2308.12966v3.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":"qwen-vl-a-frontier-large-vision-language","repo_url":"https://github.com/qwenlm/qwen-vl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"qwen-vl-a-frontier-large-vision-language","repo_url":"https://github.com/brandon3964/multimodal-task-vector","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"chart-question-answering","task_name":"Chart Question Answering"},{"task_slug":"fs-mevqa","task_name":"FS-MEVQA"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":null,"task_name":"Image Description"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"mmr-total","task_name":"MMR total"},{"task_slug":"natural-language-visual-grounding","task_name":"Natural Language Visual Grounding"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"},{"task_slug":"spatial-reasoning","task_name":"Spatial Reasoning"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"},{"task_slug":"visual-localization","task_name":"Visual Localization"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/chart-question-answering-on-chartqa","task":"Chart Question Answering","dataset":"ChartQA","model":"Qwen-VL-Chat","rank_in_archive_order":17,"of":27,"metrics":{"1:1 Accuracy":"66.3"},"uses_additional_data":true},{"leaderboard":"/sota/chart-question-answering-on-chartqa","task":"Chart Question Answering","dataset":"ChartQA","model":"Qwen-VL","rank_in_archive_order":19,"of":27,"metrics":{"1:1 Accuracy":"65.7"},"uses_additional_data":true},{"leaderboard":"/sota/fs-mevqa-on-sme","task":"FS-MEVQA","dataset":"SME","model":"Qwen-VL-Max","rank_in_archive_order":4,"of":7,"metrics":{"#Learning Samples (N)":"16","ACC":"40.33","BLEU-4":"24.30","CIDEr":"201.47","Detection":"1.05","METEOR":"23.40","ROUGE-L":"34.52","SPICE":"26.13"},"uses_additional_data":false},{"leaderboard":"/sota/mmr-total-on-mrr-benchmark","task":"MMR total","dataset":"MRR-Benchmark","model":"Qwen-vl-max","rank_in_archive_order":7,"of":14,"metrics":{"Total Column Score":"366"},"uses_additional_data":true},{"leaderboard":"/sota/mmr-total-on-mrr-benchmark","task":"MMR total","dataset":"MRR-Benchmark","model":"Qwen-vl-plus","rank_in_archive_order":9,"of":14,"metrics":{"Total Column Score":"310"},"uses_additional_data":true},{"leaderboard":"/sota/natural-language-visual-grounding-on","task":"Natural Language Visual Grounding","dataset":"ScreenSpot","model":"Qwen-VL","rank_in_archive_order":18,"of":18,"metrics":{"Accuracy (%)":"5.2"},"uses_additional_data":false},{"leaderboard":"/sota/spatial-reasoning-on-embspatial-bench","task":"Spatial Reasoning","dataset":"EmbSpatial-Bench","model":"Qwen-VL-Max","rank_in_archive_order":2,"of":5,"metrics":{"Generation":"49.11"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"Qwen-VL-Max","rank_in_archive_order":17,"of":231,"metrics":{"GPT-4 score":"66.6±0.5"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"Qwen-VL-Plus","rank_in_archive_order":34,"of":231,"metrics":{"GPT-4 score":"61.1±0.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet-v2","task":"Visual Question Answering","dataset":"MM-Vet v2","model":"Qwen-VL-Max","rank_in_archive_order":12,"of":24,"metrics":{"GPT-4 score":"55.8±0.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vip-bench","task":"Visual Question Answering","dataset":"ViP-Bench","model":"Qwen-VL-Chat (Coordinates)","rank_in_archive_order":6,"of":13,"metrics":{"GPT-4 score (bbox)":"45.3"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vip-bench","task":"Visual Question Answering","dataset":"ViP-Bench","model":"Qwen-VL-Chat (Visual Prompt)","rank_in_archive_order":9,"of":13,"metrics":{"GPT-4 score (bbox)":"39.2","GPT-4 score (human)":"41.7"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-docvqa-test","task":"Visual Question Answering (VQA)","dataset":"DocVQA test","model":"Qwen-VL-Plus","rank_in_archive_order":5,"of":33,"metrics":{"ANLS":"0.9024"},"uses_additional_data":true},{"leaderboard":"/sota/visual-question-answering-on-docvqa-test","task":"Visual Question Answering (VQA)","dataset":"DocVQA test","model":"Qwen-VL","rank_in_archive_order":31,"of":33,"metrics":{"ANLS":"0.651"},"uses_additional_data":true},{"leaderboard":"/sota/visual-question-answering-on-docvqa-test","task":"Visual Question Answering (VQA)","dataset":"DocVQA test","model":"Qwen-VL-Chat","rank_in_archive_order":33,"of":33,"metrics":{"ANLS":"0.626"},"uses_additional_data":true},{"leaderboard":"/sota/visual-question-answering-vqa-on-core-mm","task":"Visual Question Answering (VQA)","dataset":"InfiMM-Eval","model":"Qwen-VL-Chat","rank_in_archive_order":3,"of":14,"metrics":{"Abductive":"44.39","Analogical":"30.42","Deductive":"37.55","Overall score":"37.39","Params":"16B"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.12966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12966"}},"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/brandon3964/multimodal-task-vector","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/qwenlm/qwen-vl","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"unverified":2},"by_repo_kind":{"listed":{"samples":2,"ran":0,"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":2,"samples":[{"code_sha256_prefix":"5f3088f85e22e05e","entry":"ModelHelper","repo":"brandon3964/multimodal-task-vector","repo_kind":"listed","path":"MTV/models.py","file_url":"https://github.com/brandon3964/multimodal-task-vector/blob/HEAD/MTV/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5f3088f85e22e05e"}},{"code_sha256_prefix":"01391d17c606d5b6","entry":"QwenHelper","repo":"brandon3964/multimodal-task-vector","repo_kind":"listed","path":"MTV/models.py","file_url":"https://github.com/brandon3964/multimodal-task-vector/blob/HEAD/MTV/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"01391d17c606d5b6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}