Papers › Any Information Is Just Worth One Single Screenshot: Unifying Search With Visualized...

Any Information Is Just Worth One Single Screenshot: Unifying Search With Visualized Information Retrieval

17 Feb 2025arXiv:2502.11431archive 2025-07-28

Ze Liu, Zhengyang Liang, Junjie Zhou, Zheng Liu, Defu Lian

With the popularity of multimodal techniques, it receives growing interests to acquire useful information in visual forms. In this work, we formally define an emerging IR paradigm called Visualized Information Retrieval, or Vis-IR, where multimodal information, such as texts, images, tables and charts, is jointly represented by a unified visual format called Screenshots, for various retrieval applications. We further make three key contributions for Vis-IR. First, we create VIRA (Vis-IR Aggregation), a large-scale dataset comprising a vast collection of screenshots from diverse sources, carefully curated into captioned and question-answer formats. Second, we develop UniSE (Universal Screenshot Embeddings), a family of retrieval models that enable screenshots to query or be queried across arbitrary data modalities. Finally, we construct MVRB (Massive Visualized IR Benchmark), a comprehensive benchmark covering a variety of task forms and application scenarios. Through extensive evaluations on MVRB, we highlight the deficiency from existing multimodal retrievers and the substantial improvements made by UniSE. Our work will be shared with the community, laying a solid foundation for this emerging field.

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 21 code samples harvested from 1 repository linked to this paper: 10 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 21 samples from 1 repository, 10 ran (8 with no instrument failure; 2 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

VectorSpaceLab/MegaPairs mentioned on GitHubpytorchSyntology: 21 samples, 10 ran (2 instrument-failed) · 11 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

21 samples harvested: 10 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 11 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.

2ran · our draft was wrong
8ran
11unverified

Licence: 0 of the 21 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 VectorSpaceLab/MegaPairs. “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”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

VectorSpaceLab/MegaPairs community (archive-listed) 21 samples, 10 ran (2 instrument-failed) · 11 unverified
CLIPAttention in 5 papers modeling_MMRet_CLIP.py ran MIT (permissive) · 4683a9a2727a0c39 · report fixture: signature hidden_states:Tensor/3/float, attention_mask:NoneType/0/?, causal_attention_mask:NoneType/0/?, output_attentions:bool/0/bool · returned tuple · level recorded 2026-09-24
CLIPFlashAttention2 modeling_MMRet_CLIP.py ran MIT (permissive) · c41ed09f75a9aabd · report fixture: returned CLIPFlashAttention2 · level recorded 2026-09-22
CLIPMLP modeling_MMRet_CLIP.py ran fingerprinted MIT (permissive) · 077b0fff3b85e9e1 · report fixture: returned CLIPMLP · level recorded 2026-09-22
CLIPOutput in 5 papers modeling_MMRet_CLIP.py ran MIT (permissive) · 151d0cec9bec302a · report fixture: returned CLIPOutput · level recorded 2026-09-22
CLIPTextEmbeddings in 5 papers modeling_MMRet_CLIP.py ran MIT (permissive) · 1328c569c474f4f4 · report fixture: returned CLIPTextEmbeddings · level recorded 2026-09-22
CLIPTextModelOutput modeling_MMRet_CLIP.py ran MIT (permissive) · 0c926261ce815222 · report fixture: returned CLIPTextModelOutput · level recorded 2026-09-22
CLIPVisionEmbeddings in 5 papers modeling_MMRet_CLIP.py ran MIT (permissive) · 4665b478d4a86539 · report fixture: returned CLIPVisionEmbeddings · level recorded 2026-09-22
CLIPVisionModelOutput modeling_MMRet_CLIP.py ran MIT (permissive) · f1a002375c0ca087 · report fixture: returned CLIPVisionModelOutput · level recorded 2026-09-22
_get_vector_norm modeling_MMRet_CLIP.py ran · our draft was wrong fingerprinted MIT (permissive) · 55b643a09be2a3a3 · report fixture: signature tensor:Tensor/2/float · returned Tensor · level recorded 2026-09-22
clip_loss in 35 papers modeling_MMRet_CLIP.py ran · our draft was wrong fingerprinted MIT (permissive) · 198ed04eaf39466a · report fixture: signature similarity:Tensor/2/float · returned Tensor · level recorded 2026-09-22
CLIPEncoder in 6 papers modeling_MMRet_CLIP.py unverified MIT (permissive) · 6bfd267dd490c2fa · report
CLIPEncoderLayer in 5 papers modeling_MMRet_CLIP.py unverified MIT (permissive) · ecfa0cbe5350ba69 · report
CLIPForImageClassification modeling_MMRet_CLIP.py unverified MIT (permissive) · c545173dbfd3a5ca · report
CLIPModel in 6 papers modeling_MMRet_CLIP.py unverified MIT (permissive) · cebc360f5e2c0d89 · report
CLIPSdpaAttention modeling_MMRet_CLIP.py unverified MIT (permissive) · bd3ad163abb1493c · report
CLIPTextModel modeling_MMRet_CLIP.py unverified MIT (permissive) · deaa731a5c90399d · report
CLIPTextModelWithProjection modeling_MMRet_CLIP.py unverified MIT (permissive) · 6e1954f2d155f256 · report
CLIPTextTransformer in 5 papers modeling_MMRet_CLIP.py unverified MIT (permissive) · 0c8dd0cca123d737 · report
CLIPVisionModel modeling_MMRet_CLIP.py unverified MIT (permissive) · 5637a1e99bb7eb4f · report
CLIPVisionModelWithProjection modeling_MMRet_CLIP.py unverified MIT (permissive) · ab821aa24496d102 · report
CLIPVisionTransformer in 5 papers modeling_MMRet_CLIP.py unverified MIT (permissive) · bc7e07dd2e0185ad · 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 UniSE (graph method: UniSE). 22 bricks; individually on a fixture: 11 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified. The assembly has not been run end-to-end.

  1. CLIPModel entry · level 0 · unverified · cebc360f5e2c0d89
  2. CLIPOutput helper · level 1 · ran · 151d0cec9bec302a
  3. CLIPTextModel model · level 0 · unverified · deaa731a5c90399d
  4. CLIPVisionModel model · level 0 · unverified · 5637a1e99bb7eb4f
  5. _get_vector_norm helper · level 1 · ran · our draft was wrong · 55b643a09be2a3a3
  6. clip_loss loss · level 1 · ran · our draft was wrong · 198ed04eaf39466a
  7. CLIPTextTransformer helper · level 0 · unverified · 0c8dd0cca123d737
  8. CLIPVisionTransformer helper · level 0 · unverified · bc7e07dd2e0185ad
  9. contrastive_loss loss · level 1 · ran · honoured contract · f2e5f28608115fa6
  10. CLIPEncoder model · level 0 · unverified · 6bfd267dd490c2fa
  11. CLIPTextEmbeddings model · level 1 · ran · 1328c569c474f4f4
  12. CLIPVisionEmbeddings model · level 1 · ran · 4665b478d4a86539
  13. CLIPEncoderLayer model · level 0 · unverified · ecfa0cbe5350ba69
  14. CLIPMLP model · level 1 · ran · 077b0fff3b85e9e1
  15. CLIPAttention model · level 1 · ran · 4683a9a2727a0c39
  16. CLIPFlashAttention2 helper · level 1 · ran · c41ed09f75a9aabd
  17. CLIPSdpaAttention helper · level 0 · unverified · bd3ad163abb1493c
  18. CLIPTextModelOutput helper · level 1 · ran · 0c926261ce815222
  19. CLIPVisionModelOutput helper · level 1 · ran · f1a002375c0ca087
  20. CLIPForImageClassification helper · level 0 · unverified · c545173dbfd3a5ca
  21. CLIPTextModelWithProjection helper · level 0 · unverified · 6e1954f2d155f256
  22. CLIPVisionModelWithProjection helper · level 0 · unverified · ab821aa24496d102

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="2502.11431") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Information RetrievalRetrieval

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