Papers › mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video

mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video

1 Feb 2023arXiv:2302.00402archive 2025-07-28

Haiyang Xu, Qinghao Ye, Ming Yan, Yaya Shi, Jiabo Ye, Yuanhong Xu, Chenliang Li, Bin Bi, Qi Qian, Wei Wang, Guohai Xu, Ji Zhang, Songfang Huang, Fei Huang, Jingren Zhou

Recent years have witnessed a big convergence of language, vision, and multi-modal pretraining. In this work, we present mPLUG-2, a new unified paradigm with modularized design for multi-modal pretraining, which can benefit from modality collaboration while addressing the problem of modality entanglement. In contrast to predominant paradigms of solely relying on sequence-to-sequence generation or encoder-based instance discrimination, mPLUG-2 introduces a multi-module composition network by sharing common universal modules for modality collaboration and disentangling different modality modules to deal with modality entanglement. It is flexible to select different modules for different understanding and generation tasks across all modalities including text, image, and video. Empirical study shows that mPLUG-2 achieves state-of-the-art or competitive results on a broad range of over 30 downstream tasks, spanning multi-modal tasks of image-text and video-text understanding and generation, and uni-modal tasks of text-only, image-only, and video-only understanding. Notably, mPLUG-2 shows new state-of-the-art results of 48.0 top-1 accuracy and 80.3 CIDEr on the challenging MSRVTT video QA and video caption tasks with a far smaller model size and data scale. It also demonstrates strong zero-shot transferability on vision-language and video-language tasks. Code and models will be released in https://github.com/alibaba/AliceMind.

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

No sample from the archive's official repository (alibaba/AliceMind) is linked to this paper; the 19 samples below come from 2 community repositories. Syntology harvested code from alibaba/AliceMind for 2 other papers.

alibaba/AliceMind: Syntology's graph links these samples to StructuralLM: Structural Pre-training for Form Understanding (arXiv:2105.11210; that paper's own run record: 0 ran · 5 unverified) and Parameter-Efficient Sparsity for Large Language Models Fine-Tuning (arXiv:2205.11005; that paper's own run record: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result); nothing checks that they implement this paper's method.

Syntology 19 code samples harvested from 2 repositories linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 19 samples from 2 repositories, 17 ran (8 with no instrument failure; 9 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:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 4 of the 17 samples that ran have no recorded date.

alibaba/AliceMind officialmentioned in paperpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to StructuralLM: Structural Pre-training for Form Understanding (arXiv:2105.11210; that paper's own run record: 0 ran · 5 unverified) and Parameter-Efficient Sparsity for Large Language Models Fine-Tuning (arXiv:2205.11005; that paper's own run record: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result); nothing checks that they implement this paper's method. report
X-PLUG/mPLUG-2 mentioned on GitHubpytorchApache-2.0Syntology: 17 samples, 15 ran (7 instrument-failed) · 2 unverified report
x-plug/mplug-owl mentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
modelscope/modelscope pytorchApache-2.0Syntology: not harvested 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

19 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 2 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.

6ran · our draft was wrong
3ran; the contract check could not run
8ran
2unverified

Licence: 2 of the 19 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

X-PLUG/mPLUG-2 community (archive-listed) 17 samples, 15 ran (7 instrument-failed) · 2 unverified
whitespace_tokenize in 49 papers models/tokenization_bert.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · cf9ffa02a42184af · report fixture: signature text:str/0/str · returned list · level recorded, date not recorded
clamp_inf models/modeling_mplug2.py ran fingerprinted Apache-2.0 (permissive) · 21aff36aa456493f · report fixture: signature tensor:Tensor/1/float · returned Tensor · level recorded 2026-09-26
compute_acc in 61 papers
census: 3 implementations from 5 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · aa81d03f07735ab8 · report fixture: signature logits:Tensor/2/float, label:Tensor/1/int, reduction:str/0/str · returned float · level recorded 2026-09-22
compute_n_params in 30 papers utils.py ran · our draft was wrong Apache-2.0 (permissive) · ad12a494674d23fb · report fixture: signature model:callable/0/?, return_str:bool/0/bool · returned str · level recorded 2026-09-22
decode_int32 dataset/caption_dataset.py ran fingerprinted Apache-2.0 (permissive) · 96590457ad0c455c · report fixture: signature ann:int/0/int · returned str · level recorded 2026-09-25
drop_path in 325 papers
census: 27 implementations from 61 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 2, kind float, dtype float32
models/clip_video.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 3ac6b7d76e8e3584 · report fixture: signature x:Tensor/2/float, drop_prob:float/0/float, training:bool/0/bool · returned Tensor · level recorded, date not recorded
initialize_clip models/visual_transformers.py ran Apache-2.0 (permissive) · 3295906672ecb8a4 · report fixture: signature config:dict/0/?, num_patches:int/0/int · returned tuple · level recorded 2026-09-25
initialize_clip_video models/visual_transformers.py ran Apache-2.0 (permissive) · 53b733b2695e4c7f · report fixture: signature config:dict/0/?, num_patches:int/0/int, T:int/0/int, use_checkpoint:bool/0/bool · returned tuple · level recorded 2026-09-25
interpolate_pos_embed in 59 papers models/vit.py ran · our draft was wrong Apache-2.0 (permissive) · c6ec173f19f5c34d · report fixture: signature pos_embed_checkpoint:Tensor/3/float, visual_encoder:callable/0/? · returned Tensor · level recorded, date not recorded
load_vocab in 107 papers models/tokenization_bert.py ran · our draft was wrong Apache-2.0 (permissive) · e7fbc7a74a3457c7 · report fixture: signature vocab_file:str/0/str · returned OrderedDict · level recorded, date not recorded
resize_pos_embed in 102 papers models/visual_transformers.py ran Apache-2.0 (permissive) · 01b33ff330828e1e · report fixture: signature posemb:Tensor/3/float, posemb_new:Tensor/3/float · returned Tensor · level recorded 2026-09-25
test_collect_fn video_caption_mplug2.py ran Apache-2.0 (permissive) · cfb25231bfbf746c · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-25
tile in 109 papers
census: 5 implementations from 7 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
models/model_video_caption_mplug.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · aa5a91226269bf75 · report fixture: signature x:Tensor/3/float, dim:int/0/int, n_tile:int/0/int · returned Tensor · level recorded 2026-09-24
tile in 109 papers
census: 5 implementations from 7 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
models/predictor.py ran fingerprinted Apache-2.0 (permissive) · 69b8b31e44791260 · report fixture: signature x:Tensor/3/float, count:int/0/int, dim:int/0/int · returned Tensor · level recorded 2026-09-26
top_k_top_p_filtering in 96 papers
census: 8 implementations from 8 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
models/predictor.py ran Apache-2.0 (permissive) · 63e2cc5fb0616ee9 · report fixture: signature logits:Tensor/2/float, top_k:int/0/int, top_p:float/0/float, filter_value:float/0/float, min_tokens_to_keep:int/0/int · returned Tensor · level recorded 2026-09-26
build_predictor models/predictor.py unverified Apache-2.0 (permissive) · e496506b4b6756a4 · report
load_tf_weights_in_bert in 135 papers models/modeling_mplug2.py unverified Apache-2.0 (permissive) · 26be70dca3249c0b · report
x-plug/mplug-owl community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
get_ltor_masks_and_position_ids_from_embeddings in 8 papers mPLUG-Owl/mplug_owl/modeling_mplug_owl.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic fingerprinted MIT (permissive) · 45567e61fe09093a · report fixture: signature data:Tensor/3/float · returned tuple · level recorded 2026-09-22
get_media_indices in 9 papers mPLUG-Owl/mplug_owl/modeling_mplug_owl.py ran · our draft was wrong fingerprinted MIT (permissive) · 265f4d55ccd60d18 · report fixture: signature my_list:Tensor/1/float · returned list · level recorded 2026-09-22

Tasks

Action ClassificationImage ClassificationImage RetrievalTGIF-FrameVideo CaptioningVideo Question AnsweringVideo RetrievalVisual GroundingVisual Question AnsweringVisual Question Answering (VQA)Zero-Shot Video Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Kinetics-400 mPLUG-2 Acc@1 87.1 #41 of 207 Archive leaderboard report
Action Classification Kinetics-400 mPLUG-2 Acc@5 97.7 #41 of 207 Archive leaderboard report
Action Classification Kinetics-600 mPLUG-2 Top-1 Accuracy 89.8 #12 of 65 Archive leaderboard report
Action Classification Kinetics-600 mPLUG-2 Top-5 Accuracy 98.3 #12 of 65 Archive leaderboard report
Action Classification Kinetics-700 mPLUG-2 Top-1 Accuracy 80.4 #13 of 36 Archive leaderboard report
Action Classification Kinetics-700 mPLUG-2 Top-5 Accuracy 94.9 #13 of 36 Archive leaderboard report
Video Captioning MSR-VTT mPLUG-2 BLEU-4 57.8 #1 of 24 Archive leaderboard report
Video Captioning MSR-VTT mPLUG-2 CIDEr 80.0 #1 of 24 Archive leaderboard report
Video Captioning MSR-VTT mPLUG-2 METEOR 34.9 #1 of 24 Archive leaderboard report
Video Captioning MSR-VTT mPLUG-2 ROUGE-L 70.1 #1 of 24 Archive leaderboard report
Video Captioning MSVD mPLUG-2 BLEU-4 70.5 #5 of 16 Archive leaderboard report
Video Captioning MSVD mPLUG-2 CIDEr 165.8 #5 of 16 Archive leaderboard report
Video Captioning MSVD mPLUG-2 METEOR 48.4 #5 of 16 Archive leaderboard report
Video Captioning MSVD mPLUG-2 ROUGE-L 85.3 #5 of 16 Archive leaderboard report
Video Question Answering MSRVTT-QA mPLUG-2 Accuracy 48.0 #6 of 14 Archive leaderboard report
Video Retrieval DiDeMo mPLUG-2 text-to-video R@1 56.4 #15 of 40 Archive leaderboard report
Video Retrieval DiDeMo mPLUG-2 text-to-video R@10 85.2 #15 of 40 Archive leaderboard report
Video Retrieval DiDeMo mPLUG-2 text-to-video R@5 79.1 #15 of 40 Archive leaderboard report
Video Retrieval LSMDC mPLUG-2 text-to-video R@1 34.4 #6 of 38 Archive leaderboard report
Video Retrieval LSMDC mPLUG-2 text-to-video R@10 65.1 #6 of 38 Archive leaderboard report
Video Retrieval LSMDC mPLUG-2 text-to-video R@5 55.2 #6 of 38 Archive leaderboard report
Video Retrieval MSR-VTT-1kA mPLUG-2 text-to-video R@1 53.1 #12 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA mPLUG-2 text-to-video R@10 84.7 #12 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA mPLUG-2 text-to-video R@5 77.6 #12 of 63 Archive leaderboard report
Visual Grounding RefCOCO+ test B mPLUG-2 Accuracy (%) 86.05 #2 of 6 Archive leaderboard report
Visual Grounding RefCOCO+ testA mPLUG-2 Accuracy (%) 92.8 #2 of 7 Archive leaderboard report
Visual Grounding RefCOCO+ val mPLUG-2 Accuracy (%) 90.33 #2 of 6 Archive leaderboard report
Visual Question Answering VQA v2 test-dev mPLUG-2 Accuracy 81.11 #6 of 11 Archive leaderboard report
Visual Question Answering (VQA) MSRVTT-QA mPLUG-2 Accuracy 0.480 #3 of 34 Archive leaderboard report
Visual Question Answering (VQA) MSVD-QA mPLUG-2 Accuracy 0.581 #7 of 36 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo mPLUG-2 text-to-video R@1 45.7 #7 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo mPLUG-2 text-to-video R@10 79.2 #7 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo mPLUG-2 text-to-video R@5 71.1 #7 of 26 Archive leaderboard report
Zero-Shot Video Retrieval LSMDC mPLUG-2 text-to-video R@1 24.1 #5 of 16 Archive leaderboard report
Zero-Shot Video Retrieval LSMDC mPLUG-2 text-to-video R@10 52.0 #5 of 16 Archive leaderboard report
Zero-Shot Video Retrieval LSMDC mPLUG-2 text-to-video R@5 43.8 #5 of 16 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT mPLUG-2 text-to-video R@1 47.1 #7 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT mPLUG-2 text-to-video R@10 79.0 #7 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT mPLUG-2 text-to-video R@5 69.7 #7 of 41 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