Papers › EVA-CLIP: Improved Training Techniques for CLIP at Scale

EVA-CLIP: Improved Training Techniques for CLIP at Scale

27 Mar 2023arXiv:2303.15389archive 2025-07-28

Quan Sun, Yuxin Fang, Ledell Wu, Xinlong Wang, Yue Cao

Contrastive language-image pre-training, CLIP for short, has gained increasing attention for its potential in various scenarios. In this paper, we propose EVA-CLIP, a series of models that significantly improve the efficiency and effectiveness of CLIP training. Our approach incorporates new techniques for representation learning, optimization, and augmentation, enabling EVA-CLIP to achieve superior performance compared to previous CLIP models with the same number of parameters but significantly smaller training costs. Notably, our largest 5.0B-parameter EVA-02-CLIP-E/14+ with only 9 billion seen samples achieves 82.0 zero-shot top-1 accuracy on ImageNet-1K val. A smaller EVA-02-CLIP-L/14+ with only 430 million parameters and 6 billion seen samples achieves 80.4 zero-shot top-1 accuracy on ImageNet-1K val. To facilitate open access and open research, we release the complete suite of EVA-CLIP to the community at https://github.com/baaivision/EVA/tree/master/EVA-CLIP.

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

No sample from the archive's official repository (baaivision/eva) is linked to this paper; the 4 samples below come from 1 community repository. Syntology harvested code from baaivision/eva for 2 other papers.

baaivision/eva: Syntology's graph links these samples to EVA: Exploring the Limits of Masked Visual Representation Learning at Scale (arXiv:2211.07636; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified) and EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters (arXiv:2402.04252; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method.

Syntology 4 code samples harvested from 1 repository linked to this paper: 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) · 3 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): 4 samples from 1 repository, 1 ran (1 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 sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

baaivision/eva officialmentioned in paperpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EVA: Exploring the Limits of Masked Visual Representation Learning at Scale (arXiv:2211.07636; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified) and EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters (arXiv:2402.04252; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
Yui010206/CREMA mentioned on GitHubpytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion (arXiv:2402.05889; that paper's own run record: 8 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; 7 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
jaehong31/raccoon mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RACCooN: A Versatile Instructional Video Editing Framework with Auto-Generated Narratives (arXiv:2405.18406; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
PaddlePaddle/PaddleMIX paddleSyntology: 4 samples, 1 ran (0 instrument-failed) · 3 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

4 samples harvested: 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) · 3 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.

1ran
3unverified

Licence: 0 of the 4 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 PaddlePaddle/PaddleMIX. “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.

PaddlePaddle/PaddleMIX community (archive-listed) 4 samples, 1 ran (0 instrument-failed) · 3 unverified
create_ui paddlemix/MULLM_WebUI/interface.py ran Apache-2.0 (permissive) · 00373b30be1d98cd · report fixture: returned Blocks · level recorded 2026-09-24
get_model_info in 13 papers paddlemix/MULLM_WebUI/common.py unverified Apache-2.0 (permissive) · f523f7dc0633013b · report
get_model_path in 22 papers paddlemix/MULLM_WebUI/common.py unverified Apache-2.0 (permissive) · ac470b0ec166399d · report
get_template in 10 papers paddlemix/MULLM_WebUI/common.py unverified Apache-2.0 (permissive) · 903eaa561fc807bb · report

Tasks

Image ClassificationRepresentation LearningZero-Shot Action RecognitionZero-Shot Transfer Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ObjectNet EVA-02-CLIP-E/14+ Top-1 Accuracy 79.6 #4 of 106 Archive leaderboard report
Zero-Shot Action Recognition UCF101 EVA-CLIP-E/14+ Top-1 Accuracy 83.1 #8 of 35 Archive leaderboard report
Zero-Shot Transfer Image Classification Food-101 EVA-CLIP-E/14+ Top 1 Accuracy 94.9 #4 of 5 Archive leaderboard report
Zero-Shot Transfer Image Classification ImageNet EVA-CLIP-E/14+ Accuracy (Private) 82 #12 of 23 Archive leaderboard report
Zero-Shot Transfer Image Classification ImageNet V2 EVA-CLIP-E/14+ Accuracy (Private) 75.7 #9 of 13 Archive leaderboard report
Zero-Shot Transfer Image Classification ImageNet-A EVA-CLIP-E/14+ Accuracy (Private) 82.1 #8 of 13 Archive leaderboard report
Zero-Shot Transfer Image Classification ImageNet-R EVA-CLIP-E/14+ Accuracy 94.5 #7 of 12 Archive leaderboard report
Zero-Shot Transfer Image Classification ImageNet-Sketch EVA-CLIP-E/14+ Accuracy (Private) 71.6 #6 of 7 Archive leaderboard report
Zero-Shot Transfer Image Classification ObjectNet EVA-CLIP-E/14+ Accuracy (Private) 79.6 #7 of 9 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

CLIP

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