Papers › ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities

ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities

18 May 2023arXiv:2305.11172archive 2025-07-28

Peng Wang, Shijie Wang, Junyang Lin, Shuai Bai, Xiaohuan Zhou, Jingren Zhou, Xinggang Wang, Chang Zhou

In this work, we explore a scalable way for building a general representation model toward unlimited modalities. We release ONE-PEACE, a highly extensible model with 4B parameters that can seamlessly align and integrate representations across vision, audio, and language modalities. The architecture of ONE-PEACE comprises modality adapters, shared self-attention layers, and modality FFNs. This design allows for the easy extension of new modalities by adding adapters and FFNs, while also enabling multi-modal fusion through self-attention layers. To pretrain ONE-PEACE, we develop two modality-agnostic pretraining tasks, cross-modal aligning contrast and intra-modal denoising contrast, which align the semantic space of different modalities and capture fine-grained details within modalities concurrently. With the scaling-friendly architecture and pretraining tasks, ONE-PEACE has the potential to expand to unlimited modalities. Without using any vision or language pretrained model for initialization, ONE-PEACE achieves leading results on a wide range of uni-modal and multi-modal tasks, including image classification (ImageNet), semantic segmentation (ADE20K), audio-text retrieval (AudioCaps, Clotho), audio classification (ESC-50, FSD50K, VGGSound), audio question answering (AVQA), image-text retrieval (MSCOCO, Flickr30K), and visual grounding (RefCOCO/+/g). Code is available at https://github.com/OFA-Sys/ONE-PEACE.

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="2305.11172")

Code

Syntology Ran 2 of 7 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong.

By repository: official repository: 7 samples from 1 repository, 2 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/ONE-PEACE officialmentioned in papermentioned on GitHubpytorchApache-2.0 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

7 samples harvested; 2 ran; 1 honoured the contract we drafted; 5 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
1ran · our draft was wrong
5unverified

Licence: 0 of the 7 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 OFA-Sys/ONE-PEACE. “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.

Linear OFA-Sys/ONE-PEACE/one_peace/models/components.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 8cd8cb0d1e9e63e4 · report
apply_half OFA-Sys/ONE-PEACE/one_peace/evaluate.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · 357d3a4f0be679d9 · report
Embedding OFA-Sys/ONE-PEACE/one_peace/models/components.py official repository unverified Apache-2.0 (permissive) · 04b37e9f45497473 · report
LayerNorm OFA-Sys/ONE-PEACE/one_peace/models/components.py official repository unverified Apache-2.0 (permissive) · 1d799a47485cfcf6 · report
adjust_label_smoothed_nll_loss OFA-Sys/ONE-PEACE/one_peace/criterions/audio_text_pretrain_loss.py official repository unverified Apache-2.0 (permissive) · a6989b09a93e6f96 · report
apply_bfloat16 OFA-Sys/ONE-PEACE/one_peace/evaluate.py official repository unverified Apache-2.0 (permissive) · 144a402fb971b36a · report
gather_without_grad OFA-Sys/ONE-PEACE/one_peace/criterions/audio_text_pretrain_loss.py official repository unverified Apache-2.0 (permissive) · 0778ee3f6d86f89f · report

Tasks

1 Image, 2*2 StitchiAction ClassificationAudio ClassificationAudio Question AnsweringAudio to Text RetrievalAudio-Visual Question Answering (AVQA)DenoisingImage ClassificationImage-text RetrievalImage-to-Text RetrievalQuestion AnsweringReferring Expression ComprehensionRetrievalSelf-Supervised Image ClassificationSemantic SegmentationText RetrievalText to Audio RetrievalVisual Question Answering (VQA)Zero-Shot Environment Sound ClassificationZero-shot Text-to-Image Retrievalimage-classification

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Kinetics-400 ONE-PEACE Acc@1 88.1 #26 of 207 Archive leaderboard report
Action Classification Kinetics-400 ONE-PEACE Acc@5 97.8 #26 of 207 Archive leaderboard report
Audio Classification FSD50K ONE-PEACE mAP 69.7 #1 of 10 Archive leaderboard report
Audio Classification VGGSound ONE-PEACE (Audio-Visual) Top 1 Accuracy 68.2 #3 of 23 Archive leaderboard report
Audio Classification VGGSound ONE-PEACE (Audio-Only) Top 1 Accuracy 59.6 #12 of 23 Archive leaderboard report
Image Classification ImageNet ONE-PEACE Number of params 1520M #1058 of 1060 Archive leaderboard report
Image-to-Text Retrieval COCO (Common Objects in Context) ONE-PEACE (ViT-G, w/o ranking) Recall@1 84.1 #2 of 9 Archive leaderboard report
Image-to-Text Retrieval COCO (Common Objects in Context) ONE-PEACE (ViT-G, w/o ranking) Recall@10 98.3 #2 of 9 Archive leaderboard report
Image-to-Text Retrieval COCO (Common Objects in Context) ONE-PEACE (ViT-G, w/o ranking) Recall@5 96.3 #2 of 9 Archive leaderboard report
Image-to-Text Retrieval Flickr30k ONE-PEACE (finetuned, w/o ranking) Recall@1 97.6 #3 of 11 Archive leaderboard report
Image-to-Text Retrieval Flickr30k ONE-PEACE (finetuned, w/o ranking) Recall@10 100 #3 of 11 Archive leaderboard report
Image-to-Text Retrieval Flickr30k ONE-PEACE (finetuned, w/o ranking) Recall@5 100 #3 of 11 Archive leaderboard report
Semantic Segmentation ADE20K ONE-PEACE Params (M) 1500 #2 of 235 Archive leaderboard report
Semantic Segmentation ADE20K ONE-PEACE Validation mIoU 63.0 #2 of 235 Archive leaderboard report
Text to Audio Retrieval AudioCaps ONE-PEACE R@1 42.5 #3 of 11 Archive leaderboard report
Text to Audio Retrieval AudioCaps ONE-PEACE R@10 88.4 #3 of 11 Archive leaderboard report
Text to Audio Retrieval AudioCaps ONE-PEACE R@5 77.5 #3 of 11 Archive leaderboard report
Text to Audio Retrieval Clotho ONE-PEACE R@1 22.4 #5 of 12 Archive leaderboard report
Text to Audio Retrieval Clotho ONE-PEACE R@10 62.7 #5 of 12 Archive leaderboard report
Text to Audio Retrieval Clotho ONE-PEACE R@5 49.0 #5 of 12 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-dev ONE-PEACE Accuracy 82.6 #4 of 56 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-std ONE-PEACE number 72.24 #3 of 38 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-std ONE-PEACE other 74.15 #3 of 38 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-std ONE-PEACE overall 82.52 #3 of 38 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-std ONE-PEACE yes/no 94.85 #3 of 38 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