{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/modality-curation-building-universal","title":"Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval","arxiv_id":"2505.19650","date":"2025-05-26","proceeding":null,"authors":["Fanheng Kong","Jingyuan Zhang","Yahui Liu","Hongzhi Zhang","Shi Feng","Xiaocui Yang","Daling Wang","Yu Tian","Victoria W.","Fuzheng Zhang","Guorui Zhou"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2505.19650v2","url_pdf":"https://arxiv.org/pdf/2505.19650v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"modality-curation-building-universal","repo_url":"https://github.com/friedrichor/UNITE","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"cross-modal-alignment","task_name":"cross-modal alignment"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.19650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19650"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/friedrichor/UNITE","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_honours":3,"unverified":6},"by_repo_kind":{"official":{"samples":9,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"6e45201fa27cb24a","entry":"ceil_by_factor","repo":"friedrichor/UNITE","repo_kind":"official","path":"unite/model/qwen_vl_utils/vision_process.py","file_url":"https://github.com/friedrichor/UNITE/blob/HEAD/unite/model/qwen_vl_utils/vision_process.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6e45201fa27cb24a"}},{"code_sha256_prefix":"8155263d7ff19bb3","entry":"floor_by_factor","repo":"friedrichor/UNITE","repo_kind":"official","path":"unite/model/qwen_vl_utils/vision_process.py","file_url":"https://github.com/friedrichor/UNITE/blob/HEAD/unite/model/qwen_vl_utils/vision_process.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8155263d7ff19bb3"}},{"code_sha256_prefix":"e252767324188623","entry":"round_by_factor","repo":"friedrichor/UNITE","repo_kind":"official","path":"unite/model/qwen_vl_utils/vision_process.py","file_url":"https://github.com/friedrichor/UNITE/blob/HEAD/unite/model/qwen_vl_utils/vision_process.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e252767324188623"}},{"code_sha256_prefix":"dbfa3b11b2f66798","entry":"get_mask","repo":"friedrichor/UNITE","repo_kind":"official","path":"unite/model/criterions.py","file_url":"https://github.com/friedrichor/UNITE/blob/HEAD/unite/model/criterions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dbfa3b11b2f66798"}},{"code_sha256_prefix":"8da8ade2adc5fa85","entry":"get_modal_mask","repo":"friedrichor/UNITE","repo_kind":"official","path":"unite/model/criterions.py","file_url":"https://github.com/friedrichor/UNITE/blob/HEAD/unite/model/criterions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8da8ade2adc5fa85"}},{"code_sha256_prefix":"b0ea61cfeeeb48e5","entry":"get_sim","repo":"friedrichor/UNITE","repo_kind":"official","path":"unite/model/criterions.py","file_url":"https://github.com/friedrichor/UNITE/blob/HEAD/unite/model/criterions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b0ea61cfeeeb48e5"}},{"code_sha256_prefix":"9e74c77e361ca940","entry":"load_pretrained_model","repo":"friedrichor/UNITE","repo_kind":"official","path":"unite/model/builder.py","file_url":"https://github.com/friedrichor/UNITE/blob/HEAD/unite/model/builder.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9e74c77e361ca940"}},{"code_sha256_prefix":"37899f22fb191b37","entry":"pretty_print_semaphore","repo":"friedrichor/UNITE","repo_kind":"official","path":"unite/utils.py","file_url":"https://github.com/friedrichor/UNITE/blob/HEAD/unite/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"37899f22fb191b37"}},{"code_sha256_prefix":"f9939a84b9a65279","entry":"violates_moderation","repo":"friedrichor/UNITE","repo_kind":"official","path":"unite/utils.py","file_url":"https://github.com/friedrichor/UNITE/blob/HEAD/unite/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f9939a84b9a65279"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}