Papers › Long-CLIP: Unlocking the Long-Text Capability of CLIP

Long-CLIP: Unlocking the Long-Text Capability of CLIP

22 Mar 2024arXiv:2403.15378archive 2025-07-28

Beichen Zhang, Pan Zhang, Xiaoyi Dong, Yuhang Zang, Jiaqi Wang

Contrastive Language-Image Pre-training (CLIP) has been the cornerstone for zero-shot classification, text-image retrieval, and text-image generation by aligning image and text modalities. Despite its widespread adoption, a significant limitation of CLIP lies in the inadequate length of text input. The length of the text token is restricted to 77, and an empirical study shows the actual effective length is even less than 20. This prevents CLIP from handling detailed descriptions, limiting its applications for image retrieval and text-to-image generation with extensive prerequisites. To this end, we propose Long-CLIP as a plug-and-play alternative to CLIP that supports long-text input, retains or even surpasses its zero-shot generalizability, and aligns the CLIP latent space, making it readily replace CLIP without any further adaptation in downstream frameworks. Nevertheless, achieving this goal is far from straightforward, as simplistic fine-tuning can result in a significant degradation of CLIP's performance. Moreover, substituting the text encoder with a language model supporting longer contexts necessitates pretraining with vast amounts of data, incurring significant expenses. Accordingly, Long-CLIP introduces an efficient fine-tuning solution on CLIP with two novel strategies designed to maintain the original capabilities, including (1) a knowledge-preserved stretching of positional embedding and (2) a primary component matching of CLIP features. With leveraging just one million extra long text-image pairs, Long-CLIP has shown the superiority to CLIP for about 20% in long caption text-image retrieval and 6% in traditional text-image retrieval tasks, e.g., COCO and Flickr30k. Furthermore, Long-CLIP offers enhanced capabilities for generating images from detailed text descriptions by replacing CLIP in a plug-and-play manner.

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

Syntology 15 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 8 ran (5 with no instrument failure; 3 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 between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 8 samples that ran have no recorded date.

beichenzbc/long-clip officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 15 samples, 8 ran (3 instrument-failed) · 7 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

15 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
1ran; the contract check could not run
3ran
7unverified

Licence: 10 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 10 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 beichenzbc/long-clip. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

beichenzbc/long-clip official repository 15 samples, 8 ran (3 instrument-failed) · 7 unverified
convert_to_custom_text_state_dict in 59 papers open_clip_long/model.py ran · violated contract Apache-2.0 (permissive) here; the stored copy is pointer only · f19962ebb134b3d7 · report fixture: signature state_dict:dict/0/? · returned dict · level recorded, date not recorded
get_1d_sincos_pos_embed_from_grid in 75 papers
census: 8 implementations from 17 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind float, dtype float64
open_clip_long/pos_embed.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) here; the stored copy is pointer only · 4bdd36eab04c3f62 · report fixture: signature embed_dim:int/0/int, pos:ndarray/1/float · returned ndarray · level recorded 2026-09-22
get_2d_sincos_pos_embed in 170 papers open_clip_long/pos_embed.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 9417ae492629cf06 · report fixture: signature embed_dim:int/0/int, grid_size:int/0/int, cls_token:bool/0/bool · returned ndarray · level recorded 2026-09-26
get_cast_dtype in 67 papers open_clip_long/model.py ran · our draft was wrong Apache-2.0 (permissive) · dcd422d66b0581d8 · report fixture: signature precision:str/0/str · returned dtype · level recorded, date not recorded
get_input_dtype in 30 papers open_clip_long/model.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · b476c8cfbf0f1f47 · report fixture: signature precision:str/0/str · returned dtype · level recorded, date not recorded
load_state_dict in 114 papers open_clip_long/factory.py ran Apache-2.0 (permissive) · 0b94bc3f6eb369a4 · report fixture: returned dict · level recorded 2026-09-24
prepare_inputs_for_generation in 58 papers open_clip_long/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 open_clip_long/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
gather_features in 78 papers open_clip_long/loss.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · ddcbd45e940484ee · report
get_2d_sincos_pos_embed_from_grid in 140 papers open_clip_long/pos_embed.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 4fd80de79832745d · report
get_model_config in 45 papers open_clip_long/factory.py unverified Apache-2.0 (permissive) · 5c7cf820e99443ff · report
get_tokenizer in 156 papers open_clip_long/factory.py unverified Apache-2.0 (permissive) · 2665f49f3b92c031 · report
load_openai_model in 16 papers open_clip_long/openai.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 8811c5d06f3a2eaa · report
neighbour_exchange in 22 papers open_clip_long/loss.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · e332856e3c2fc814 · report
neighbour_exchange_bidir in 19 papers open_clip_long/loss.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 5b1fd364afcf3c05 · report

Tasks

Image GenerationImage RetrievalLanguage ModellingRetrievalText to Image GenerationText-to-Image GenerationZero-Shot Learning

1 archive task tag without a task page not shown.

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