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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2303.16839")

Code

Syntology Ran 3 of 3 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 3 ran · violated contract.

By repository: community (archive-listed): 3 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

lucidrains/mammut-pytorch mentioned on GitHubpytorchMIT 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; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · violated contract

Licence: 0 of the 3 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 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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

divisible_by lucidrains/mammut-pytorch/mammut_pytorch/mammut_pytorch.py community (archive-listed) ran · violated contract fingerprinted MIT (permissive) · 856d86b39c6005b4 · report
default lucidrains/mammut-pytorch/mammut_pytorch/mammut_pytorch.py community (archive-listed) ran · violated contract fingerprinted MIT (permissive) · 60fff7c3c400d7ff · report
exists lucidrains/mammut-pytorch/mammut_pytorch/mammut_pytorch.py community (archive-listed) ran · violated contract MIT (permissive) · aa5486a3650902d8 · report

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