Methods › Computer Vision › Vision and Language Pre-Trained Models › OFA
OFA
Introduced by Peng Wang et al. in OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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.
In Syntology name not resolved (unknown_name). Other entries in Syntology's graph carry this name; the lookup's note below says what that means for this name.
From the lookup's note on this name: Nothing resolved to this name, but 5 entries in Syntology's graph carry it; the most cited is the paper “OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework” (arXiv:2202.03052, 1,104 citations). The lookup reads this as a miss of its own name matching, not a gap in coverage: the graph holds the name under a spelling the lookup did not reach. For arXiv:2202.03052: its page on this site · ask the lookup about it.
Near matches the lookup lists, each a different name: OFA-TAD; OFA-MAS; One for All (OFA); One For All (OFA); OFA-Diffusion Compression.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 32 · with a code link: 14 · where Syntology ran a sample: 6 (6 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (6 of 32 tagged: 6 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 32 of 32, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
MARCO: Hardware-Aware Neural Architecture Search for Edge Devices with Multi-Agent Reinforcement Learning and Conformal Prediction Filtering 16 Jun 2025 · 0 repositories · arXiv:2506.13755
-
Private MEV Protection RPCs: Benchmark Stud 26 May 2025 · 0 repositories · arXiv:2505.19708
-
Object-Focus Actor for Data-efficient Robot Generalization Dexterous Manipulation 21 May 2025 · 0 repositories · arXiv:2505.15098
-
Learning Object Focused Attention 10 Apr 2025 · 0 repositories · arXiv:2504.08166
-
Efficient Adaptation For Remote Sensing Visual Grounding 29 Mar 2025 · 0 repositories · arXiv:2503.23083
-
Exploring Advanced Techniques for Visual Question Answering: A Comprehensive Comparison 20 Feb 2025 · 0 repositories · arXiv:2502.14827
-
Analysis of the Order Flow Auction under Proposer-Builder Separation 17 Feb 2025 · 0 repositories · arXiv:2502.12026
-
Memory-Optimized Once-For-All Network 5 Sep 2024 · 2 repositories · arXiv:2409.05900
-
Enhancing Journalism with AI: A Study of Contextualized Image Captioning for News Articles using LLMs and LMMs 8 Aug 2024 · 0 repositories · arXiv:2408.04331
-
Second Place Solution of WSDM2023 Toloka Visual Question Answering Challenge 5 Jul 2024 · 0 repositories · arXiv:2407.04255
-
Mixture of Rationale: Multi-Modal Reasoning Mixture for Visual Question Answering 3 Jun 2024 · 0 repositories · arXiv:2406.01402
-
The Solution for the CVPR2024 NICE Image Captioning Challenge 19 Apr 2024 · 0 repositories · arXiv:2404.12739
-
ANGOFA: Leveraging OFA Embedding Initialization and Synthetic Data for Angolan Language Model 3 Apr 2024 · 1 repository · arXiv:2404.02534
-
OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining 15 Nov 2023 · 1 repository · arXiv:2311.08849Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
The Solution for the CVPR2023 NICE Image Captioning Challenge 10 Oct 2023 · 0 repositories · arXiv:2310.06879
-
Lightweight In-Context Tuning for Multimodal Unified Models 8 Oct 2023 · 0 repositories · arXiv:2310.05109
-
One for All: Towards Training One Graph Model for All Classification Tasks 29 Sep 2023 · 1 repository · arXiv:2310.00149Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 9 unverified (of 18 harvested samples) · 5 pointer-only (licence)
-
Physics Inspired Hybrid Attention for SAR Target Recognition 27 Sep 2023 · 1 repository · arXiv:2309.15697
-
ALIP: Adaptive Language-Image Pre-training with Synthetic Caption 16 Aug 2023 · 1 repository · arXiv:2308.08428Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified (of 10 harvested samples) · 10 pointer-only (licence)
-
Table and Image Generation for Investigating Knowledge of Entities in Pre-trained Vision and Language Models 3 Jun 2023 · 1 repository · arXiv:2306.02115Syntology official: no sample here; runs from other or unrecorded repositories · 10 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; 2 where Syntology's instrument failed) · 1 unverified (of 11 harvested samples) · 7 pointer-only (licence)
-
OFAR: A Multimodal Evidence Retrieval Framework for Illegal Live-streaming Identification 25 Apr 2023 · 0 repositories · arXiv:2304.12608
-
oBERTa: Improving Sparse Transfer Learning via improved initialization, distillation, and pruning regimes 30 Mar 2023 · 0 repositories · arXiv:2303.17612
-
OFA²: A Multi-Objective Perspective for the Once-for-All Neural Architecture Search 23 Mar 2023 · 1 repository · arXiv:2303.13683
-
Enhancing Once-For-All: A Study on Parallel Blocks, Skip Connections and Early Exits 3 Feb 2023 · 0 repositories · arXiv:2302.01888
-
BinaryVQA: A Versatile Test Set to Evaluate the Out-of-Distribution Generalization of VQA Models 28 Jan 2023 · 1 repository · arXiv:2301.12032
-
MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning 21 Dec 2022 · 1 repository · arXiv:2212.10773Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimension 23 Nov 2022 · 1 repository · arXiv:2211.12759
-
How good are deep models in understanding the generated images? 23 Aug 2022 · 0 repositories · arXiv:2208.10760
-
Improving Predictive Performance and Calibration by Weight Fusion in Semantic Segmentation 22 Jul 2022 · 0 repositories · arXiv:2207.11211
-
Does Interference Exist When Training a Once-For-All Network? 20 Apr 2022 · 1 repository · arXiv:2204.09210
-
One Agent To Rule Them All: Towards Multi-agent Conversational AI 15 Mar 2022 · 1 repository · arXiv:2203.07665
-
OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework 7 Feb 2022 · 4 repositories · arXiv:2202.03052Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
Tasks archive 2025-07-28
20 shown of 64 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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