Papers › LongProLIP: A Probabilistic Vision-Language Model with Long Context Text

LongProLIP: A Probabilistic Vision-Language Model with Long Context Text

11 Mar 2025arXiv:2503.08048archive 2025-07-28

Sanghyuk Chun, Sangdoo Yun

Recently, Probabilistic Language-Image Pre-Training (ProLIP) has been proposed to tackle the multiplicity issue of vision-language (VL) tasks. Despite their success in probabilistic representation learning at a scale, the ProLIP models cannot handle long context texts longer than 64 context length, which limits their ability to capture rich contextual information from longer text sequences. To address this issue, this paper proposes a fine-tuning strategy for ProLIP to accept longer texts, e.g., 256 text tokens. Experimental results on Urban-1k and the DataComp evaluation suite show that the proposed LongProLIP recipe can improve understanding of long contexts while minimizing the negative effect of fine-tuning.We also observe a trade-off between the long context understanding (measured by Urban-1k) and general zero-shot capability (measured by evaluation datasets by DataComp). Code is available at https://github.com/naver-ai/prolip

PaperPDFCodeCode 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 16 code samples: 14 from 1 repository linked to this paper, 2 identical to code harvested from another paper's repository. Across all 16: 7 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; 6 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 5 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: 14 samples from 1 repository, 5 ran (1 with no instrument failure; 4 where Syntology's instrument failed); 2 identical to code first harvested elsewhere. 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 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 5 of the 7 samples that ran have no recorded date.

naver-ai/prolip officialmentioned in papermentioned on GitHubpytorchSyntology: 14 samples, 5 ran (4 instrument-failed) · 9 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

16 samples harvested: 7 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; 6 where Syntology's instrument failed) · 9 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.

5ran · our draft was wrong
1ran; the contract check could not run
1ran
9unverified

Licence: 16 of the 16 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 naver-ai/prolip. 3 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another paper. 2 samples are listed last, in a group without a repository. “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.

naver-ai/prolip official repository 14 samples, 5 ran (4 instrument-failed) · 9 unverified
ResidualAttentionBlock in 38 papers src/prolip/model.py ran · metamorphic tier: invariant fingerprinted licence not identified · pointer only · 022a5391f0e240ca · report fixture: signature q_x:Tensor/3/float, k_x:NoneType/0/?, v_x:NoneType/0/?, attn_mask:NoneType/0/? · returned Tensor · level recorded 2026-09-22
get_input_dtype in 30 papers src/prolip/model.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · 4d038cd90610dfa0 · report fixture: signature precision:str/0/str · returned dtype · level recorded, date not recorded
get_model_preprocess_cfg src/prolip/model.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · feaac0348de86b5a · report fixture: signature model:callable/0/? · returned dict · level recorded, date not recorded
get_model_preprocess_cfg src/prolip/model.py ran · our draft was wrong licence not identified · pointer only · 4ea5dcdf3bdde1b0 · report fixture: signature model:callable/0/? · returned dict · level recorded, date not recorded
text_global_pool in 6 papers src/prolip/model.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only · b0071d319dff7f45 · report fixture: signature x:Tensor/3/float, text:Tensor/2/float, pool_type:str/0/str · returned tuple · level recorded 2026-09-22
ProLIP src/prolip/model.py unverified licence not identified · pointer only · 20ab228b3362392c · report
ProLIPTextCfg src/prolip/model.py unverified licence not identified · pointer only · 088887788aa71e94 · report
ProLIPVisionCfg src/prolip/model.py unverified licence not identified · pointer only · 56e68dadc6499c62 · report
TextTransformer src/prolip/model.py unverified licence not identified · pointer only · bdb64edca7f927cb · report
Transformer in 173 papers src/prolip/model.py unverified licence not identified · pointer only · 5918de7404e9237b · report
VisionTransformer in 53 papers src/prolip/model.py unverified licence not identified · pointer only · 84aa74aff57a00bc · report
_build_text_tower src/prolip/model.py unverified licence not identified · pointer only · c6232c0ea06aba61 · report
_build_vision_tower src/prolip/model.py unverified licence not identified · pointer only · 6631a3008026f80f · report
get_cast_dtype in 67 papers src/prolip/model.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · 0529ec3d12d83d1c · report
Repository not located 2 samples, 2 ran (2 instrument-failed) · 0 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
get_cast_dtype in 67 papers repository not located ran · our draft was wrong licence of this copy not recorded · dcd422d66b0581d8 · report fixture: signature precision:str/0/str · returned dtype · level recorded, date not recorded
get_input_dtype in 30 papers repository not located ran · our draft was wrong licence of this copy not recorded · b476c8cfbf0f1f47 · report fixture: signature precision:str/0/str · returned dtype · level recorded, date not recorded

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 LongProLIP (graph method: ProLIP). 19 bricks; individually on a fixture: 10 ran (of which 2 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) · 9 unverified. The assembly has not been run end-to-end.

  1. ProLIP entry · level 0 · unverified · 20ab228b3362392c
  2. ProLIPTextCfg model · level 0 · unverified · 088887788aa71e94
  3. ProLIPVisionCfg model · level 0 · unverified · 56e68dadc6499c62
  4. _build_text_tower model · level 0 · unverified · c6232c0ea06aba61
  5. _build_vision_tower model · level 0 · unverified · 6631a3008026f80f
  6. LayerNorm helper · level 1 · ran · 2ce325eef914eb38
  7. LayerNormFp32 helper · level 1 · ran · f5a2164abfcb21f3
  8. QuickGELU helper · level 1 · ran · 8c5c4de012c0aab9
  9. TextTransformer model · level 0 · unverified · bdb64edca7f927cb
  10. VisionTransformer helper · level 0 · unverified · 84aa74aff57a00bc
  11. Transformer model · level 0 · unverified · 5918de7404e9237b
  12. _expand_token helper · level 1 · ran · our draft was wrong · 476766d1bc74cdeb
  13. text_global_pool helper · level 1 · ran; the contract check could not run (RAISES) · b0071d319dff7f45
  14. get_2d_sincos_pos_embed helper · level 1 · ran · honoured contract · caca77a0bdc72e75
  15. ResidualAttentionBlock helper · level 1 · ran · 022a5391f0e240ca
  16. get_2d_sincos_pos_embed_from_grid helper · level 0 · unverified · 4fd80de79832745d
  17. LayerScale helper · level 1 · ran · a77a876f784480d3
  18. get_1d_sincos_pos_embed_from_grid helper · level 1 · ran; the contract check could not run · 4bdd36eab04c3f62
  19. _ntuple helper · level 1 · ran · our draft was wrong · 553ee0765abad219

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="2503.08048") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Language ModelingLanguage ModellingLong-Context UnderstandingRepresentation Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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