Papers › Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text...

Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

24 Aug 2023arXiv:2308.12966archive 2025-07-28

Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, Jingren Zhou

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.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repository (qwenlm/qwen-vl) is linked to this paper; the 2 samples below come from 1 community repository. Syntology harvested code from qwenlm/qwen-vl for another paper.

qwenlm/qwen-vl: Syntology's graph links these samples to LoRA: Low-Rank Adaptation of Large Language Models (arXiv:2106.09685; that paper's own run record: 51 ran (of which 19 constructed an object rather than computing a result; 43 with no instrument failure: 1 honoured, 0 violated, 42 with no contract checked; 8 where Syntology's instrument failed) · 33 unverified); nothing checks that they implement this paper's method.

Syntology 2 code samples harvested from 1 repository linked to this paper: 0 ran · 2 unverified.

By repository: community (archive-listed): 2 samples from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

qwenlm/qwen-vl officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to LoRA: Low-Rank Adaptation of Large Language Models (arXiv:2106.09685; that paper's own run record: 51 ran (of which 19 constructed an object rather than computing a result; 43 with no instrument failure: 1 honoured, 0 violated, 42 with no contract checked; 8 where Syntology's instrument failed) · 33 unverified); nothing checks that they implement this paper's method. report
brandon3964/multimodal-task-vector mentioned on GitHubpytorchNOASSERTIONSyntology: 2 samples, 0 ran · 2 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

2 samples harvested: 0 ran · 2 unverified. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2unverified

Licence: 2 of the 2 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from brandon3964/multimodal-task-vector. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

brandon3964/multimodal-task-vector community (archive-listed) 2 samples, 0 ran · 2 unverified
ModelHelper MTV/models.py unverified licence not identified · pointer only · 5f3088f85e22e05e · report
QwenHelper MTV/models.py unverified licence not identified · pointer only · 01391d17c606d5b6 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Qwen-VL (graph method: Qwen-VL). 2 bricks; individually on a fixture: 0 ran · 2 unverified. The assembly has not been run end-to-end.

  1. QwenHelper entry · level 0 · unverified · 01391d17c606d5b6
  2. ModelHelper helper · level 0 · unverified · 5f3088f85e22e05e

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2308.12966") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Chart Question AnsweringFS-MEVQAImage CaptioningLanguage ModelingLanguage ModellingMMR totalNatural Language Visual GroundingQuestion AnsweringReferring Expression SegmentationSpatial ReasoningVisual GroundingVisual LocalizationVisual Question AnsweringVisual Question Answering (VQA)

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Chart Question Answering ChartQA Qwen-VL-Chat 1:1 Accuracy 66.3 #17 of 27 Archive leaderboard report
Chart Question Answering ChartQA Qwen-VL 1:1 Accuracy 65.7 #19 of 27 Archive leaderboard report
FS-MEVQA SME Qwen-VL-Max #Learning Samples (N) 16 #4 of 7 Archive leaderboard report
FS-MEVQA SME Qwen-VL-Max ACC 40.33 #4 of 7 Archive leaderboard report
FS-MEVQA SME Qwen-VL-Max BLEU-4 24.30 #4 of 7 Archive leaderboard report
FS-MEVQA SME Qwen-VL-Max CIDEr 201.47 #4 of 7 Archive leaderboard report
FS-MEVQA SME Qwen-VL-Max Detection 1.05 #4 of 7 Archive leaderboard report
FS-MEVQA SME Qwen-VL-Max METEOR 23.40 #4 of 7 Archive leaderboard report
FS-MEVQA SME Qwen-VL-Max ROUGE-L 34.52 #4 of 7 Archive leaderboard report
FS-MEVQA SME Qwen-VL-Max SPICE 26.13 #4 of 7 Archive leaderboard report
MMR total MRR-Benchmark Qwen-vl-max Total Column Score 366 #7 of 14 Archive leaderboard report
MMR total MRR-Benchmark Qwen-vl-plus Total Column Score 310 #9 of 14 Archive leaderboard report
Natural Language Visual Grounding ScreenSpot Qwen-VL Accuracy (%) 5.2 #18 of 18 Archive leaderboard report
Spatial Reasoning EmbSpatial-Bench Qwen-VL-Max Generation 49.11 #2 of 5 Archive leaderboard report
Visual Question Answering MM-Vet Qwen-VL-Max GPT-4 score 66.6±0.5 #17 of 231 Archive leaderboard report
Visual Question Answering MM-Vet Qwen-VL-Plus GPT-4 score 61.1±0.2 #34 of 231 Archive leaderboard report
Visual Question Answering MM-Vet v2 Qwen-VL-Max GPT-4 score 55.8±0.2 #12 of 24 Archive leaderboard report
Visual Question Answering ViP-Bench Qwen-VL-Chat (Coordinates) GPT-4 score (bbox) 45.3 #6 of 13 Archive leaderboard report
Visual Question Answering ViP-Bench Qwen-VL-Chat (Visual Prompt) GPT-4 score (bbox) 39.2 #9 of 13 Archive leaderboard report
Visual Question Answering ViP-Bench Qwen-VL-Chat (Visual Prompt) GPT-4 score (human) 41.7 #9 of 13 Archive leaderboard report
Visual Question Answering (VQA) DocVQA test Qwen-VL-Plus ANLS 0.9024 #5 of 33 Archive leaderboard report
Visual Question Answering (VQA) DocVQA test Qwen-VL ANLS 0.651 #31 of 33 Archive leaderboard report
Visual Question Answering (VQA) DocVQA test Qwen-VL-Chat ANLS 0.626 #33 of 33 Archive leaderboard report
Visual Question Answering (VQA) InfiMM-Eval Qwen-VL-Chat Abductive 44.39 #3 of 14 Archive leaderboard report
Visual Question Answering (VQA) InfiMM-Eval Qwen-VL-Chat Analogical 30.42 #3 of 14 Archive leaderboard report
Visual Question Answering (VQA) InfiMM-Eval Qwen-VL-Chat Deductive 37.55 #3 of 14 Archive leaderboard report
Visual Question Answering (VQA) InfiMM-Eval Qwen-VL-Chat Overall score 37.39 #3 of 14 Archive leaderboard report
Visual Question Answering (VQA) InfiMM-Eval Qwen-VL-Chat Params 16B #3 of 14 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections