Papers › MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning...

MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs

17 Jun 2024arXiv:2406.11833archive 2025-07-28

Ziyu Liu, Tao Chu, Yuhang Zang, Xilin Wei, Xiaoyi Dong, Pan Zhang, Zijian Liang, Yuanjun Xiong, Yu Qiao, Dahua Lin, Jiaqi Wang

Generating natural and meaningful responses to communicate with multi-modal human inputs is a fundamental capability of Large Vision-Language Models(LVLMs). While current open-source LVLMs demonstrate promising performance in simplified scenarios such as single-turn single-image input, they fall short in real-world conversation scenarios such as following instructions in a long context history with multi-turn and multi-images. Existing LVLM benchmarks primarily focus on single-choice questions or short-form responses, which do not adequately assess the capabilities of LVLMs in real-world human-AI interaction applications. Therefore, we introduce MMDU, a comprehensive benchmark, and MMDU-45k, a large-scale instruction tuning dataset, designed to evaluate and improve LVLMs' abilities in multi-turn and multi-image conversations. We employ the clustering algorithm to ffnd the relevant images and textual descriptions from the open-source Wikipedia and construct the question-answer pairs by human annotators with the assistance of the GPT-4o model. MMDU has a maximum of 18k image+text tokens, 20 images, and 27 turns, which is at least 5x longer than previous benchmarks and poses challenges to current LVLMs. Our in-depth analysis of 15 representative LVLMs using MMDU reveals that open-source LVLMs lag behind closed-source counterparts due to limited conversational instruction tuning data. We demonstrate that ffne-tuning open-source LVLMs on MMDU-45k signiffcantly address this gap, generating longer and more accurate conversations, and improving scores on MMDU and existing benchmarks (MMStar: +1.1%, MathVista: +1.5%, ChartQA:+1.2%). Our contributions pave the way for bridging the gap between current LVLM models and real-world application demands. This project is available at https://github.com/Liuziyu77/MMDU.

PaperPDFCodeCode Syntology ran

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

Syntology 13 code samples: 9 from 1 repository linked to this paper, 4 identical to code harvested from another paper's repository. Across all 13: 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 5 ran (2 with no instrument failure; 3 where Syntology's instrument failed); 4 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 7 samples that ran have no recorded date.

liuziyu77/mmdu officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 9 samples, 5 ran (3 instrument-failed) · 4 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.

Code Syntology ran Syntology

13 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
2ran; the contract check could not run
6unverified

Licence: 6 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from liuziyu77/mmdu. 4 samples are listed last, in a group without a repository. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

liuziyu77/mmdu official repository 9 samples, 5 ran (3 instrument-failed) · 4 unverified
build_transform in 170 papers model_generation/InternVL_chat_gen_ans.py ran · our draft was wrong Apache-2.0 (permissive) · 57e95166ade5f25c · report fixture: signature input_size:int/0/int · returned Compose · level recorded 2026-09-24
dynamic_preprocess in 40 papers model_generation/InternVL_chat_gen_ans.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · d610b5eabe0c9db1 · report fixture: signature image:Image/0/?, min_num:int/0/int, max_num:int/0/int, image_size:int/0/int, use_thumbnail:bool/0/bool · returned list · level recorded 2026-09-22
find_closest_aspect_ratio in 45 papers model_generation/InternVL_chat_gen_ans.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed Apache-2.0 (permissive) here; the stored copy is pointer only · bd77f5f8067f18e9 · report fixture: signature aspect_ratio:float/0/float, target_ratios:list/1/tuple, width:int/0/int, height:int/0/int, image_size:int/0/int · returned tuple · level recorded 2026-09-22
load_image in 273 papers model_generation/mmdu_LLaVa_gen_ans.py ran · honoured contract Apache-2.0 (permissive) · 9b3c1cb391672ccb · report fixture: signature image_file:str/0/str · returned Image · level recorded 2026-09-22
load_images in 48 papers model_generation/mmdu_LLaVa_gen_ans.py ran · honoured contract Apache-2.0 (permissive) · d5044bdde33c54c2 · report fixture: signature image_files:list/1/str · returned list · level recorded 2026-09-22
mllm_openai model_generation/Claude3opus_gen_ans.py unverified Apache-2.0 (permissive) · 6d3ac51d93b6fa7b · report
mllm_openai model_generation/GPT4o_gen_ans.py unverified Apache-2.0 (permissive) · 9e43f38ac5b5a4f9 · report
mllm_openai model_generation/GPT4turbo_gen_ans.py unverified Apache-2.0 (permissive) · def81a4cd2af1cad · report
mllm_openai model_generation/Qwen_VL_Max_gen_ans.py unverified Apache-2.0 (permissive) · 25182bd581875ec4 · report
Repository not located 4 samples, 2 ran (1 instrument-failed) · 2 unverified
4 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
parse_score in 49 papers repository not located ran · violated contract fingerprinted licence of this copy not recorded · 763f6fe20bd52fbb · report fixture: signature review:str/0/str · returned list · level recorded, date not recorded
split_to_even_chunks in 41 papers repository not located ran; the contract check could not run (RAISES) · metamorphic tier: well formed licence of this copy not recorded · 10893c4608c08075 · report fixture: signature indices:list/1/int, lengths:dict/0/?, num_chunks:int/0/int · returned list · level recorded, date not recorded
get_mm_adapter_state_maybe_zero_3 in 44 papers repository not located unverified licence of this copy not recorded · bb35e3ac741bb2c9 · report
maybe_zero_3 in 74 papers repository not located unverified licence of this copy not recorded · 735025744c1ab0cf · report

Tasks

Visual Question Answering

Datasets

Introduced by this paper, per the archive.

MMDU

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Question Answering MM-Vet InternLM-XC2 + MMDU-45k GPT-4 score 38.8 #122 of 231 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.

Methods

Focus

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