{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/megapairs-massive-data-synthesis-for","title":"MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval","arxiv_id":"2412.14475","date":"2024-12-19","proceeding":null,"authors":["Junjie Zhou","Zheng Liu","Ze Liu","Shitao Xiao","Yueze Wang","Bo Zhao","Chen Jason Zhang","Defu Lian","Yongping Xiong"],"abstract":"Despite the rapidly growing demand for multimodal retrieval, progress in this field remains severely constrained by a lack of training data. In this paper, we introduce MegaPairs, a novel data synthesis method that leverages vision language models (VLMs) and open-domain images, together with a massive synthetic dataset generated from this method. Our empirical analysis shows that MegaPairs generates high-quality data, enabling the multimodal retriever to significantly outperform the baseline model trained on 70$\\times$ more data from existing datasets. Moreover, since MegaPairs solely relies on general image corpora and open-source VLMs, it can be easily scaled up, enabling continuous improvements in retrieval performance. In this stage, we produced more than 26 million training instances and trained several models of varying sizes using this data. These new models achieve state-of-the-art zero-shot performance across 4 popular composed image retrieval (CIR) benchmarks and the highest overall performance on the 36 datasets provided by MMEB. They also demonstrate notable performance improvements with additional downstream fine-tuning. Our produced dataset, well-trained models, and data synthesis pipeline will be made publicly available to facilitate the future development of this field.","url_abs":"https://arxiv.org/abs/2412.14475v1","url_pdf":"https://arxiv.org/pdf/2412.14475v1.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":"megapairs-massive-data-synthesis-for","repo_url":"https://github.com/VectorSpaceLab/MegaPairs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"zero-shot-composed-image-retrieval-zs-cir","task_name":"Zero-Shot Composed Image Retrieval (ZS-CIR)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-on-cirr","task":"Image Retrieval","dataset":"CIRR","model":"MMRet-MLLM","rank_in_archive_order":10,"of":17,"metrics":{"(Recall@5+Recall_subset@1)/2":"75.7","Recall@10":"85.1"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-fashion-iq","task":"Image Retrieval","dataset":"Fashion IQ","model":"MMRet-MLLM","rank_in_archive_order":17,"of":22,"metrics":{"(Recall@10+Recall@50)/2":"46.1","Recall@10":"35.6"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"CIRCO","model":"MMRet-MLLM","rank_in_archive_order":1,"of":43,"metrics":{"mAP@10":"43.4"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"CIRCO","model":"MMRet-Large (CLIP L/14)","rank_in_archive_order":2,"of":43,"metrics":{"mAP@10":"40.2"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset":"CIRCO","model":"MMRet-Base (CLIP B/16)","rank_in_archive_order":6,"of":43,"metrics":{"mAP@10":"35.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.14475","atlas_url":"https://app.syntology.ai/?focus=2412.14475","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2412.14475"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2412.14475\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2412.14475"},"call":"get_concepts_for_paper(arxiv_id=\"2412.14475\")"}],"by_repo":[{"repo":"VectorSpaceLab/MegaPairs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2502.11431"],"harvested_for_calls":[{"arxiv_id":"2502.11431","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2502.11431"},"call":"get_harvested_code_for_paper(arxiv_id=\"2502.11431\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"e9c8fe3d1fcef221ec8cb85759d8c8929164546bf2431372b1dfda3a5cff4066","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}