SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2510.18583 · NeurIPS · 2025

CovMatch: Cross-Covariance Guided Multimodal Dataset Distillation with Trainable Text Encoder

Hye Won, Yongmin Lee

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (6 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 0 failures of our instrument; 1 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2510.18583.json · badge: /api/ran/2510.18583.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
Yongalls/CovMatch community
Papers with Code archive
6 ran · 1 no recorded run
FunctionStatusWhere it lives
AttentionPool2d Ran
ran on a synthesized input · constructed an object; no result was computed
Yongalls/CovMatch/src/model.py
pointer only (licence: NONE) · get_code("733f63bc89b6c510")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Yongalls/CovMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Bottleneck Ran
ran on a synthesized input · constructed an object; no result was computed
Yongalls/CovMatch/src/model.py
pointer only (licence: NONE) · get_code("50b240334bdc6bc6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Yongalls/CovMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ModifiedResNet Ran
ran on a synthesized input · constructed an object; no result was computed
Yongalls/CovMatch/src/model.py
pointer only (licence: NONE) · get_code("aedc8261aa63cda3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Yongalls/CovMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ResidualAttentionBlock Ran
ran on a synthesized input · constructed an object; no result was computed
Yongalls/CovMatch/src/model.py
pointer only (licence: NONE) · get_code("6088793f94190d8d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Yongalls/CovMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Transformer Ran
ran on a synthesized input · constructed an object; no result was computed
Yongalls/CovMatch/src/model.py
pointer only (licence: NONE) · get_code("46053fd5fb7a6576")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Yongalls/CovMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

VisionTransformer Ran
ran on a synthesized input · constructed an object; no result was computed
Yongalls/CovMatch/src/model.py
pointer only (licence: NONE) · get_code("dee6bfa940b2b6a4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Yongalls/CovMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

CLIP Not yet run
unverified (harvested, no recorded run)
Yongalls/CovMatch/src/model.py
pointer only (licence: NONE) · get_code("23942a1e71ee1ce4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Yongalls/CovMatch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 2 the same month, 1 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
ResidualAttentionBlock
brick of this paper's assembly: helper
18 other papers
17 dated earlier, 1 the same month · 13 only as an assembly brick
2105.01879 (2021-05)
MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space
2205.14459 (2022-05)
CYCLIP: Cyclic Contrastive Language-Image Pretraining
2301.06958 (2023-01)
RILS: Masked Visual Reconstruction in Language Semantic Space
and 15 more not named here
Transformer
brick of this paper's assembly: model
16 other papers
15 dated earlier, 1 the same month · 10 only as an assembly brick
2105.01879 (2021-05)
MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space
2205.14459 (2022-05)
CYCLIP: Cyclic Contrastive Language-Image Pretraining
2301.06958 (2023-01)
RILS: Masked Visual Reconstruction in Language Semantic Space
and 13 more not named here
Bottleneck
brick of this paper's assembly: helper
5 other papers
4 dated earlier, 1 later · 3 only as an assembly brick
2105.01879 (2021-05)
MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space
2304.04231 (2023-04)
CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model
2309.01083 (2023-09)
Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning
and 2 more not named here
AttentionPool2d
brick of this paper's assembly: helper
4 other papers
4 dated earlier · 3 only as an assembly brick
2105.01879 (2021-05)
MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space
2304.04231 (2023-04)
CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model
2309.12867 (2023-09)
Accurate and Fast Compressed Video Captioning
and 1 more not named here
ModifiedResNet
brick of this paper's assembly: model
3 other papers
3 dated earlier · 2 only as an assembly brick
2105.01879 (2021-05)
MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space
2304.04231 (2023-04)
CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model
2309.12867 (2023-09)
Accurate and Fast Compressed Video Captioning
VisionTransformer
brick of this paper's assembly: model
2 other papers
2 dated earlier · 2 only as an assembly brick
2105.01879 (2021-05)
MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space
2304.04231 (2023-04)
CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Multimodal dataset distillation aims to synthesize a small set of image-text pairs that enables efficient training of large-scale vision-language models. While dataset distillation has shown promise in unimodal tasks, extending it to multimodal contrastive learning presents key challenges: learning cross-modal alignment and managing the high computational cost of large encoders. Prior approaches address scalability by freezing the text encoder and updating only the image encoder and text projection layer. However, we find this severely limits semantic alignment and becomes a bottleneck for performance scaling. We propose Cov-Match, a scalable dataset distillation framework that aligns the cross-covariances of real and synthetic features while regularizing feature distributions within each modality. Unlike prior approaches, CovMatch enables joint optimization of both encoders, leading to stronger cross-modal alignment and improved performance. Evaluated on Flickr30K and COCO, CovMatch outperforms state-ofthe-art multimodal distillation methods and achieves up to 6.8% absolute gains in retrieval accuracy using only 500 synthetic pairs. Our code is available at https://github.com/Yongalls/CovMatch.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2510.18583")
get_code_for_paper("2510.18583")
have("2510.18583")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2510.18583.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2510.18583.svg)](https://syntology.ai/paper/2510.18583)

Connect an agent — have() is free.