Papers › Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval

Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval

26 May 2025arXiv:2505.19650archive 2025-07-28

Fanheng Kong, Jingyuan Zhang, Yahui Liu, Hongzhi Zhang, Shi Feng, Xiaocui Yang, Daling Wang, Yu Tian, Victoria W., Fuzheng Zhang, Guorui Zhou

Multimodal information retrieval (MIR) faces inherent challenges due to the heterogeneity of data sources and the complexity of cross-modal alignment. While previous studies have identified modal gaps in feature spaces, a systematic approach to address these challenges remains unexplored. In this work, we introduce UNITE, a universal framework that tackles these challenges through two critical yet underexplored aspects: data curation and modality-aware training configurations. Our work provides the first comprehensive analysis of how modality-specific data properties influence downstream task performance across diverse scenarios. Moreover, we propose Modal-Aware Masked Contrastive Learning (MAMCL) to mitigate the competitive relationships among the instances of different modalities. Our framework achieves state-of-the-art results on multiple multimodal retrieval benchmarks, outperforming existing methods by notable margins. Through extensive experiments, we demonstrate that strategic modality curation and tailored training protocols are pivotal for robust cross-modal representation learning. This work not only advances MIR performance but also provides a foundational blueprint for future research in multimodal systems. Our project is available at https://friedrichor.github.io/projects/UNITE.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2505.19650")

Code

Syntology Ran 3 of 9 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 3 ran · honoured contract.

By repository: official repository: 9 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

friedrichor/UNITE officialmentioned on GitHubpytorchApache-2.0 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

9 samples harvested; 3 ran; 3 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · honoured contract
6unverified

Licence: 0 of the 9 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 friedrichor/UNITE. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

ceil_by_factor friedrichor/UNITE/unite/model/qwen_vl_utils/vision_process.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · 6e45201fa27cb24a · report
floor_by_factor friedrichor/UNITE/unite/model/qwen_vl_utils/vision_process.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · 8155263d7ff19bb3 · report
round_by_factor friedrichor/UNITE/unite/model/qwen_vl_utils/vision_process.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · e252767324188623 · report
get_mask friedrichor/UNITE/unite/model/criterions.py official repository unverified Apache-2.0 (permissive) · dbfa3b11b2f66798 · report
get_modal_mask friedrichor/UNITE/unite/model/criterions.py official repository unverified Apache-2.0 (permissive) · 8da8ade2adc5fa85 · report
get_sim friedrichor/UNITE/unite/model/criterions.py official repository unverified Apache-2.0 (permissive) · b0ea61cfeeeb48e5 · report
load_pretrained_model friedrichor/UNITE/unite/model/builder.py official repository unverified Apache-2.0 (permissive) · 9e74c77e361ca940 · report
pretty_print_semaphore friedrichor/UNITE/unite/utils.py official repository unverified Apache-2.0 (permissive) · 37899f22fb191b37 · report
violates_moderation friedrichor/UNITE/unite/utils.py official repository unverified Apache-2.0 (permissive) · f9939a84b9a65279 · report

Tasks

Contrastive LearningInformation RetrievalRepresentation LearningRetrievalcross-modal alignment

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Contrastive Learning

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