Papers › OFA: Unifying Architectures, Tasks, and Modalities Through a Simple...

OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

7 Feb 2022arXiv:2202.03052archive 2025-07-28

Peng Wang, An Yang, Rui Men, Junyang Lin, Shuai Bai, Zhikang Li, Jianxin Ma, Chang Zhou, Jingren Zhou, Hongxia Yang

In this work, we pursue a unified paradigm for multimodal pretraining to break the scaffolds of complex task/modality-specific customization. We propose OFA, a Task-Agnostic and Modality-Agnostic framework that supports Task Comprehensiveness. OFA unifies a diverse set of cross-modal and unimodal tasks, including image generation, visual grounding, image captioning, image classification, language modeling, etc., in a simple sequence-to-sequence learning framework. OFA follows the instruction-based learning in both pretraining and finetuning stages, requiring no extra task-specific layers for downstream tasks. In comparison with the recent state-of-the-art vision & language models that rely on extremely large cross-modal datasets, OFA is pretrained on only 20M publicly available image-text pairs. Despite its simplicity and relatively small-scale training data, OFA achieves new SOTAs in a series of cross-modal tasks while attaining highly competitive performances on uni-modal tasks. Our further analysis indicates that OFA can also effectively transfer to unseen tasks and unseen domains. Our code and models are publicly available at https://github.com/OFA-Sys/OFA.

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="2202.03052")

Code

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

By repository: official repository: 1 sample from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ofa-sys/ofa officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
JHKim-snu/GVCCI mentioned on GitHubpytorch report
JHKim-snu/PGA mentioned on GitHubpytorch report
modelscope/modelscope pytorchApache-2.0 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

1 sample harvested; 1 ran; 1 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.

1ran · honoured contract

Licence: 0 of the 1 sample 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 ofa-sys/ofa. “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.

apply_half ofa-sys/ofa/evaluate.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · 357d3a4f0be679d9 · report

Tasks

Image CaptioningImage ClassificationImage GenerationLanguage ModelingLanguage ModellingObject CategorizationReferring ExpressionReferring Expression ComprehensionSelf-Supervised Image ClassificationText GenerationText SummarizationText-to-Image GenerationVisual EntailmentVisual GroundingVisual Question AnsweringVisual Question Answering (VQA)Visual Reasoningimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Captioning COCO Captions OFA BLEU-4 44.9 #2 of 41 Archive leaderboard report
Image Captioning COCO Captions OFA CIDER 154.9 #2 of 41 Archive leaderboard report
Image Captioning COCO Captions OFA METEOR 32.5 #2 of 41 Archive leaderboard report
Image Captioning COCO Captions OFA SPICE 26.6 #2 of 41 Archive leaderboard report
Object Categorization GRIT OFA_Large Categorization (ablation) 22.6 #4 of 4 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) OFA (Large) Number of Params 473M #22 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) OFA (Large) Top 1 Accuracy 85.6% #22 of 65 Archive leaderboard report
Text Summarization GigaWord OFA ROUGE-1 39.81 #6 of 41 Archive leaderboard report
Text Summarization GigaWord OFA ROUGE-2 20.66 #6 of 41 Archive leaderboard report
Text Summarization GigaWord OFA ROUGE-L 37.11 #6 of 41 Archive leaderboard report
Visual Entailment SNLI-VE test OFA Accuracy 91.2 #1 of 8 Archive leaderboard report
Visual Entailment SNLI-VE val OFA Accuracy 91.0 #1 of 9 Archive leaderboard report
Visual Question Answering GRIT OFA VQA (ablation) 72.4 #1 of 1 Archive leaderboard report
Visual Question Answering VQA v2 test-dev OFA Accuracy 82.0 #3 of 11 Archive leaderboard report
Visual Question Answering VQA v2 test-std OFA number 71.44 #2 of 3 Archive leaderboard report
Visual Question Answering VQA v2 test-std OFA other 73.35 #2 of 3 Archive leaderboard report
Visual Question Answering VQA v2 test-std OFA overall 81.98 #2 of 3 Archive leaderboard report
Visual Question Answering VQA v2 test-std OFA yes/no 94.66 #2 of 3 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

Introduced by this paper: OFA

1x1 ConvolutionAdamAttentionAttention DropoutAverage PoolingBERTBatch NormalizationBottleneck Residual BlockColorJitterConvolutionDense ConnectionsDropoutFeedforward NetworkGlobal Average PoolingInfoNCEKaiming InitializationLayer NormalizationLinear LayerLinear Warmup With Linear DecayMax PoolingMoCoMoCo v3Multi-Head AttentionNT-XentOFARandom Gaussian BlurRandom Resized CropReLUResidual BlockResidual ConnectionSimCLRSoftmaxWeight DecayWordPiece

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