Papers › MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks

MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks

29 Mar 2023arXiv:2303.16839archive 2025-07-28

Weicheng Kuo, AJ Piergiovanni, Dahun Kim, Xiyang Luo, Ben Caine, Wei Li, Abhijit Ogale, Luowei Zhou, Andrew Dai, Zhifeng Chen, Claire Cui, Anelia Angelova

The development of language models have moved from encoder-decoder to decoder-only designs. In addition, we observe that the two most popular multimodal tasks, the generative and contrastive tasks, are nontrivial to accommodate in one architecture, and further need adaptations for downstream tasks. We propose a novel paradigm of training with a decoder-only model for multimodal tasks, which is surprisingly effective in jointly learning of these disparate vision-language tasks. This is done with a simple model, called MaMMUT. It consists of a single vision encoder and a text decoder, and is able to accommodate contrastive and generative learning by a novel two-pass approach on the text decoder. We demonstrate that joint learning of these diverse objectives is simple, effective, and maximizes the weight-sharing of the model across these tasks. Furthermore, the same architecture enables straightforward extensions to open-vocabulary object detection and video-language tasks. The model tackles a diverse range of tasks, while being modest in capacity. Our model achieves the state of the art on image-text and text-image retrieval, video question answering and open-vocabulary detection tasks, outperforming much larger and more extensively trained foundational models. It shows very competitive results on VQA and Video Captioning, especially considering its capacity. Ablations confirm the flexibility and advantages of our approach.

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 3 code samples harvested from 1 repository linked to this paper: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 3 samples from 1 repository, 3 ran (3 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 date is recorded for any of the 3 samples that ran: their levels were written before Syntology's graph kept the date.

lucidrains/mammut-pytorch mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 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

3 samples harvested: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. 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.

3ran · violated contract

Licence: 2 of the 3 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 lucidrains/mammut-pytorch. “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.

lucidrains/mammut-pytorch community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
divisible_by in 33 papers mammut_pytorch/mammut_pytorch.py ran · violated contract fingerprinted MIT (permissive) · 856d86b39c6005b4 · report fixture: signature numer:int/0/int, denom:int/0/int · returned bool · level recorded, date not recorded
default in 430 papers mammut_pytorch/mammut_pytorch.py ran · violated contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 60fff7c3c400d7ff · report fixture: signature val:int/0/int, d:int/0/int · returned int · level recorded, date not recorded
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
mammut_pytorch/mammut_pytorch.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · aa5486a3650902d8 · report fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded

Tasks

Cross-Modal RetrievalDecoderImage RetrievalObject DetectionOpen Vocabulary Object DetectionOpen-vocabulary object detectionQuestion AnsweringRetrievalVideo CaptioningVideo Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)object-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-Modal Retrieval COCO 2014 MaMMUT (ours) Image-to-text R@1 70.7 #36 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 MaMMUT (ours) Image-to-text R@10 93.7 #36 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 MaMMUT (ours) Image-to-text R@5 89.1 #36 of 36 Archive leaderboard report
Image Retrieval Flickr30k MaMMUT (ours) Image-to-text R@1 94.9 #4 of 9 Archive leaderboard report
Image Retrieval Flickr30k MaMMUT (ours) Image-to-text R@10 99.9 #4 of 9 Archive leaderboard report
Image Retrieval Flickr30k MaMMUT (ours) Image-to-text R@5 99.5 #4 of 9 Archive leaderboard report
Image Retrieval Flickr30k MaMMUT (ours) Recall@1 82.5 #4 of 9 Archive leaderboard report
Image Retrieval Flickr30k MaMMUT (ours) Recall@10 98 #4 of 9 Archive leaderboard report
Image Retrieval Flickr30k MaMMUT (ours) Recall@5 96 #4 of 9 Archive leaderboard report
Question Answering COCO Visual Question Answering (VQA) real images 1.0 open ended MaMMUT (2B) Test 80.8 #1 of 1 Archive leaderboard report
Video Captioning MSR-VTT MaMMUT (ours) CIDEr 73.6 #7 of 24 Archive leaderboard report
Video Captioning MSVD MaMMUT CIDEr 195.6 #1 of 16 Archive leaderboard report
Visual Question Answering COCO Visual Question Answering (VQA) real images 2.0 open ended MaMMUT (2B) Percentage correct 80.7 #1 of 1 Archive leaderboard report
Visual Question Answering (VQA) MSRVTT-QA MaMMUT Accuracy 0.495 #2 of 34 Archive leaderboard report
Visual Question Answering (VQA) MSVD-QA MaMMUT (ours) Accuracy .602 #3 of 36 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