Papers › An Inverse Scaling Law for CLIP Training

An Inverse Scaling Law for CLIP Training

11 May 2023NeurIPS 2023 11arXiv:2305.07017archive 2025-07-28

Xianhang Li, Zeyu Wang, Cihang Xie

CLIP, one of the pioneering foundation models that connect images and text, has enabled many recent breakthroughs in computer vision. However, its associated training cost is prohibitively high, imposing a significant barrier to its widespread exploration. In this paper, we present a surprising finding that there exists an inverse scaling law for CLIP training, whereby the larger the image/text encoders used, the shorter the sequence length of image/text tokens that can be applied in training. Moreover, we showcase that the strategy for reducing image/text token length plays a crucial role in determining the quality of this scaling law. As a result of this finding, we are able to successfully train CLIP even with limited computational resources. For example, using 8 A100 GPUs, our CLIP models achieve zero-shot top-1 ImageNet-1k accuracies of 63.2% in ~2 days, 67.8% in ~3 days, and 69.3% in ~4 days. Our method also works well when scaling up -- with G/14, we register a new record of 83.0% ImageNet-1k zero-shot accuracy, and meanwhile accelerate the training by ~33x compared to its OpenCLIP counterpart. By reducing the computation barrier associated with CLIP, we hope to inspire more research in this field, particularly from academics. Our code is available at https://github.com/UCSC-VLAA/CLIPA.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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

Syntology 11 code samples harvested from 1 repository linked to this paper: 8 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; 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: official repository: 11 samples from 1 repository, 8 ran (8 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.

Levels written on 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ucsc-vlaa/clipa officialmentioned in papermentioned on GitHubjaxApache-2.0Syntology: 11 samples, 8 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.

Code Syntology ran Syntology

11 samples harvested: 8 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; 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.

8ran
3unverified

Licence: 2 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ucsc-vlaa/clipa. “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.

ucsc-vlaa/clipa official repository 11 samples, 8 ran (0 instrument-failed) · 3 unverified
decode_variant clipa_jax/models/convnext.py ran Apache-2.0 (permissive) · 92c6112113ef833f · report fixture: signature variant:str/0/str · returned dict · level recorded 2026-09-26
get_posemb in 5 papers clipa_jax/models/text_transformer.py ran Apache-2.0 (permissive) · 1ededb122742f89c · report fixture: signature self:MockSelf/0/?, typ:str/0/str, max_len:int/0/int, width:int/0/int, name:str/0/str, dtype:callable/0/?, cls_token:bool/0/bool · returned ArrayImpl · level recorded 2026-09-26
get_posemb in 5 papers clipa_jax/models/vit.py ran Apache-2.0 (permissive) · ab73c5ea9b60c840 · report fixture: signature self:callable/0/?, typ:str/0/str, seqshape:tuple/1/int, width:int/0/int, name:str/0/str, dtype:callable/0/?, cls_token:bool/0/bool · returned ArrayImpl · level recorded 2026-09-26
posemb_sincos_1d clipa_jax/models/text_transformer.py ran Apache-2.0 (permissive) · b2b574d0ba793b32 · report fixture: signature max_len:int/0/int, width:int/0/int, min_scale:float/0/float, max_scale:float/0/float, dtype:callable/0/?, cls_token:bool/0/bool · returned ArrayImpl · level recorded 2026-09-26
posemb_sincos_2d in 20 papers clipa_jax/models/common.py ran Apache-2.0 (permissive) · 3143c90644184650 · report fixture: signature h:int/0/int, w:int/0/int, width:int/0/int, temperature:float/0/float, dtype:callable/0/?, cls_token:bool/0/bool · returned ArrayImpl · level recorded 2026-09-26
prepare_inputs_for_generation in 58 papers clipa_torch/open_clip/coca_model.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · fb651d0a97fd4d3f · report fixture: signature input_ids:Tensor/2/int, image_inputs:Tensor/3/float, past:NoneType/0/?, attention_mask:Tensor/2/int, position_ids:Tensor/2/int · returned dict · level recorded 2026-09-26
register_pooler in 46 papers clipa_torch/open_clip/hf_model.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 2a377da4a76a2d44 · report fixture: signature cls:callable/0/? · returned type · level recorded 2026-09-26
resample_posemb clipa_jax/models/convnext.py ran Apache-2.0 (permissive) · 140a126a24e733d8 · report fixture: signature old:ndarray/3/float, new:ndarray/3/float · returned ArrayImpl · level recorded 2026-09-26
bidirectional_contrastive_loss clipa_jax/losses/common.py unverified Apache-2.0 (permissive) · 687383b642d42364 · report
get in 42 papers clipa_jax/datasets/core.py unverified Apache-2.0 (permissive) · da654725d3df8ece · report
resample_posemb clipa_jax/models/common.py unverified Apache-2.0 (permissive) · 99118ca7ebcca7e2 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Inverse Scaling Law for CLIP Training (graph method: Inverse Scaling Law for CLIP Training). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

  1. bidirectional_contrastive_loss entry · level 0 · unverified · 687383b642d42364

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2305.07017") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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